PH: +91-9888934889 E-Mail: editornrjitis@gmail.com ISSN: 2350-1278

National Research Journal of Information Technology & Information Science

An International Reputed Peer Reviewed Refereed Research Journal I Open Access Journal I Impact Factor: 7.9
Submit Papers Online
  • Home
  • Current Issue
  • Archives
  • Editorial Board
  • Submit Paper
  • Indexing
  • Research Areas
  • Author Instructions
  • For Authors
    • Manuscript Guidelines
    • Copyright Agreement Form
    • View Paper Template
  • Subscribe Journal
  • Contact
Business Economics
Sales And Marketing
Human Resource Management
Banking And Finance
Information Technology And Information Science
Education And Psychology
Biotechnology And Biosciences
Literary Aesthetics
Social Science
Business Economics Sales And Marketing Human Resource Management Banking And Finance Social Science
Information Technology And Information Science Education And Psychology Biotechnology And Biosciences Literary Aesthetics

Editorial Policy About Peer Reviewed Journal Publication Ethics & Practices Plagiarism Policy Open Access, Licencing & Copyright Disclaimer Policy Privacy Policy FAQ Special Issue About The Journal

Join Our Editorial Board

Latest Announcements

  • CALL FOR PAPERS 2025 (January-June)

    01-01-2025
    SUBMIT PAPERS IN OUR RESEARCH JOURNAL! 2025
    National Research Journal of Information Technology and Information Science  contributes in the growth and application of Research & Technology, by delivering the latest information contained in research papers, which enables them to enhance understanding for advancements in research activities. We intends to Disseminate and promote the research works of research scholars, Academia.

  • Subscribe This Journal

    01-01-2025
    We Request to Subscribe our Journals for the Noble Cause to Spread Knowledge, Wisdom and also to Protect Intellectual Property Rights of Scholars Across the World.

    Subscription Price: 3500/- (Bi-Annual)

    CALL NOW!
    +91-9888934889, 7986925354

Publish
Conference
Or Seminar
papers in our journal

Read More

NRJITIS - National Research Journal of Information Technology & Information Science


About The Journal


The National Research Journal of Information Technology and Information Science (NRJITIS) (ISSN: 2350-1278)  is a peer reviewed Journal academic publication dedicated to advancing research and knowledge in the fields of Information Technology (IT) and Information Science. The journal serves as a platform for scholars, practitioners, and industry professionals to share innovative research findings, emerging technologies, and practical applications. It covers a broad range of topics including data science, cybersecurity, artificial intelligence, software engineering, information systems, digital transformation, and human-computer interaction & Library Sciences and other multidisciplinary related topics. The journal aims to foster interdisciplinary collaboration and contribute to the evolving landscape of IT and information science through high-quality, original research.

The Journal is Published By "National Press Associates"

  • Publisher Website: www.npajournals.org
  • Journal Name: National Research Journal of Information Technology and Information Science
  • ISSN: 2350-1278
  • Impact Factor: 7.9
  • Peer Review Process: Double Blind Peer Review Process
  • Low Article Processing Fees
  • Frequency of Publication: Biannual (2 Issues Per Year)
  • Languages: English
  • Accessibility: Open Access
  • Plagiarism Checker: Turnitin

The journal invites submission of manuscripts that meet the general criteria of significance and scientific excellence, and will publish:

  1. Original articles (research paper, short communications, etc)
  2. Review articles
  3. Conference reports
  4. Book reviews, etc.

Interested in submitting to this journal? We recommend that you review the About the Journal page for the journal's section policies, as well as the Author Guidelines.

Journal Email ID: editornrjitis@gmail.com

ENQUIRY NOW: +91-9888934889 (WhatsApp Link)


Current Issue

Year: 2026   Volume No: 13, January, Year: 2026 (Special Issue)

Paper Title LOW COST SMALL SIZE PATCH ANTENNA FOR WEARABLE APPLICATIONS
Author Name Sushil Kakkar & Shweta Rani
Country India
DOI https://doi.org/10.5281/zenodo.18933614
Page No. 1-6

Abstract View PDF Download Certificate
LOW COST SMALL SIZE PATCH ANTENNA FOR WEARABLE APPLICATIONS
Author: Sushil Kakkar & Shweta Rani

ABSTRACT
Present day wearable technology possesses a significant contribution in health monitoring systems. A small size cost effective patch antenna for wearable applications has been elaborated in this paper. The presented antenna is square in shape and designed with FR4 substrate. The dimensions of the antenna have been optimized using numerous simulations. In view to obtain the effect of slot on the performance of antenna, a rigorous analysis has also been performed.

Keywords: Antenna, micorstrip, wearable, radiation pattern.

Paper Title AN EXTENSIVE ANALYSIS OF GREEN COMPUTING: BENEFITS, CHALLENGES AND ROLE
Author Name Navneet Kaur Sandhu & Mohammad Wasiq
Country India
DOI https://doi.org/10.5281/zenodo.18933740
Page No. 7-10

Abstract View PDF Download Certificate
AN EXTENSIVE ANALYSIS OF GREEN COMPUTING: BENEFITS, CHALLENGES AND ROLE
Author: Navneet Kaur Sandhu & Mohammad Wasiq

ABSTRACT
The phrase "green computing" refers to the methods employed by the sector to reduce the amount of hazardous elements released into the environment as a result of the use of ICT resources. About 2% of carbon emissions come from this use, which is equivalent to aircraft. This information inspired the idea of green computing, or environmentally friendly computing. Numerous gadgets, mechanisms, and software have been created as a result of advancements in modern technology, and numerous studies have been carried out to maximize and expand the green computing capabilities of these technologies. Therefore, to determine the current developments, difficulties, and prospects for further research, a review and summary of studies based on green computing are necessary. Through an exploration of the twelve areas of green computing, this study reviewed and summarized green computing in each area study. Following a comprehensive comparison and analysis, this study offers answers to the suggested cutting-edge research questions. Additionally, this study outlines the present difficulties and prospects for further research in each field of green computing. This study will offer insights and ideas to institutions, researchers, and organizations involved in green computing research. Additionally, environmental groups, businesses, and government organizations working to lower energy use and carbon emissions will also gain from this review study.

Keywords: Green Computing, ICT, Carbon, Energy, Environment.

Paper Title ENHANCING REAL-TIME MONITORING: THE ROLE OF WIRELESS SENSOR NETWORKS IN MODERN APPLICATIONS WITH VMIMO
Author Name Mandeep Kaur Sekhon & Jagdeep Kaur
Country India
DOI https://doi.org/10.5281/zenodo.18933895
Page No. 11-15

Abstract View PDF Download Certificate
ENHANCING REAL-TIME MONITORING: THE ROLE OF WIRELESS SENSOR NETWORKS IN MODERN APPLICATIONS WITH VMIMO
Author: Mandeep Kaur Sekhon & Jagdeep Kaur

ABSTRACT
This literature review examines the fundamental concepts, applications, and advancements in Wireless Sensor Networks (WSNs), focusing on energy-efficient communication techniques using Single-Input Single-Output (SISO), Single-Input Multiple-Output (SIMO), Multiple-Input Single-Output (MISO), and Multiple-Input Multiple-Output (MIMO) systems. It highlights improvements in MIMO technology, explores energy models with MIMO, and evaluates performance metrics. The need for Virtual MIMO (vMIMO) is discussed, alongside strategies to make it energy efficient. A detailed comparison of vMIMO and traditional MIMO in terms of energy efficiency and an analysis of the challenges in implementing vMIMO in WSNs are provided. Suitable images and diagrams illustrate key concepts. The evolution of wireless communication technology has led to the development of Multiple Input Multiple Output (MIMO) systems, which utilize multiple antennas at both the transmitter and receiver ends to improve communication performance. In recent years, Virtual MIMO (vMIMO) has emerged as a promising alternative, particularly in Wireless Sensor Networks (WSNs), where energy efficiency is paramount due to the limited battery life of sensor nodes. This paper provides a detailed comparison of virtual MIMO and traditional MIMO in terms of energy efficiency, along with the main challenges associated with implementing virtual MIMO in WSNs.

General Terms
This paper explores the role of Wireless Sensor Networks (WSNs) in enhancing real-time monitoring through energyefficient communication techniques, including MIMO and vMIMO. It focuses on the advancements in MIMO technology, need for vMIMO and its benefits and main challenges of implementing vMIMO in WSNs are analyzed. A comparison between traditional MIMO and vMIMO is provided, highlighting their architectural and operational differences.

Keywords: WSN, Traditional MIMO, vMIMO, MIMO vs vMIMO.

Paper Title EXPLORING MACHINE LEARNING TECHNIQUES FOR THE DETECTION OF DDOS ATTACKS: A COMPREHENSIVE REVIEW
Author Name Rajni, Daljit Kaur, Inderdeep Kaur, Parminder Kaur & Harmandar Kaur
Country India
DOI https://doi.org/10.5281/zenodo.18933964
Page No. 16-27

Abstract View PDF Download Certificate
EXPLORING MACHINE LEARNING TECHNIQUES FOR THE DETECTION OF DDOS ATTACKS: A COMPREHENSIVE REVIEW
Author: Rajni, Daljit Kaur, Inderdeep Kaur, Parminder Kaur & Harmandar Kaur

ABSTRACT
As DDoS attacks get increasingly sophisticated, traditional detection approaches fail to keep up with the changing threat landscape. Machine learning provides powerful capabilities for detecting and mitigating assaults in real time. This review paper investigates various machine learning algorithms used to detect DDoS attacks, categorizing them as supervised,
unsupervised, and deep learning approaches. Supervised learning algorithms, such as Support Vector Machines (SVM) and Decision Trees, have been widely utilized to categorize attack patterns, although unsupervised learning techniques, such as clustering, provide advantages in detecting novel assaults without the need for labeled data. Deep learning models, notably Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), have shown exceptional performance in large-scale, dynamic assault scenarios. This review also examines the role of datasets, named KDDCup99 and CICIDS, which are used to train these models, and their success is evaluated using important performance indicators such as
accuracy, precision, and recall. This study examines recent breakthroughs, datasets, and performance indicators in order to guide future research and improve the resilience of cybersecurity defenses against DDoS attacks.

Paper Title A COMPREHENSIVE STUDY ON TRANSFORMER DESIGN USING NUMERICAL TECHNIQUES
Author Name Sarpreet Kaur
Country India
DOI https://doi.org/10.5281/zenodo.18934030
Page No. 28-35

Abstract View PDF Download Certificate
A COMPREHENSIVE STUDY ON TRANSFORMER DESIGN USING NUMERICAL TECHNIQUES
Author: Sarpreet Kaur

ABSTRACT
The aim of this study was to review the application of finite element techniques for solving complex transformer structures using modern software. The Finite Element Method (FEM), developed over the past 70 years to address intricate problems in civil and aeronautical engineering, has since found valuable applications in electrical engineering for solving complex
design challenges. This paper explores the use of FEM in transformer design, highlighting its effectiveness as a numerical tool for simulating structural components, optimizing materials, enhancing reliability, performing failure analysis, taking corrective actions, and verifying new designs under various loading conditions. The study concludes that FEM is a highly efficient approach for transformer design and analysis.

Keywords- Numerical Techniques, Finite Element Method, Transformer Design.

Paper Title A COMPARATIVE SURVEY OF RAO OPTIMIZATION ALGORITHMS: MULTI-OBJECTIVE APPLICATIONS AND HYBRID TECHNIQUES IN ENGINEERING DESIGN
Author Name Shubhangi Jagdish Kamble
Country India
DOI https://doi.org/10.5281/zenodo.18934242
Page No. 36-44

Abstract View PDF Download Certificate
A COMPARATIVE SURVEY OF RAO OPTIMIZATION ALGORITHMS: MULTI-OBJECTIVE APPLICATIONS AND HYBRID TECHNIQUES IN ENGINEERING DESIGN
Author: Shubhangi Jagdish Kamble

ABSTRACT
This paper presents a comprehensive survey of the Rao optimization algorithm focusing on its applications in the omnidirectional domain, including robotics, image processing, machine learning, and renewable energy systems. Rao’s adaptability and robustness make it an effective tool for solving complex, high-dimensional, nonlinear, and dynamic optimization problems. A key contribution is the exploration of hybrid Rao algorithms, such as Rao-Particle Swarm Optimization (PSO), Rao-Differential Evolution (DE), and Rao-Genetic Algorithms (GA) to address challenges like slow convergence in high-dimensional spaces. The paper highlights Rao's potential in real-time applications, such as autonomous robot path planning and machine learning hyper-parameter tuning. Additionally, it examines Rao’s role in multi-objective optimization, a crucial aspect of engineering design and system optimization. The study underscores Rao's strengths in handling dynamic optimization tasks, balancing exploration and exploitation, and improving convergence speed through hybrid approaches. A comparative analysis with other meta-heuristic algorithms like GA, PSO, and DE shows Rao’s superior global search capability and computational efficiency. The results demonstrate Rao’s versatility and potential for solving real-world optimization problems, especially in high-dimensional, dynamic environments. This survey provides valuable insights for researchers and practitioners aiming to use Rao optimization for complex, real-time, and
multi-objective tasks in various domains.

Keywords— Rao optimization, renewable energy systems, hybrid algorithms, multi-objective optimization, robotics, image processing, machine learning

Paper Title DEEP LEARNING FOR REAL-TIME ROUTE OPTIMIZATION IN TOURISM APPLICATIONS
Author Name Disha Sharma, Usman Ali, Aman Kumar Aditya, Gurleen Kaur & Astha Rathore
Country India
DOI https://doi.org/10.5281/zenodo.18934961
Page No. 45-51

Abstract View PDF Download Certificate
DEEP LEARNING FOR REAL-TIME ROUTE OPTIMIZATION IN TOURISM APPLICATIONS
Author: Disha Sharma, Usman Ali, Aman Kumar Aditya, Gurleen Kaur & Astha Rathore

ABSTRACT
Weak environmental factors, such as weather conditions, shifting user preferences, along with road traffic control impact travel efficiency in tourism. Therefore, real-time route optimization models are needed for ensuring smooth and efficient travel for the user. The paper explore how deep learning methods can boost route optimization in tourism systems. The application uses real-time position system and traffic report and weather forecast data to adjust travel routes which delivers customized and optimized routes. Travelers obtain adaptable route recommendations from the system after it factors in their preferences and past travel data and external boundary restrictions to enhance their whole travel experience. If we compare the traditional models over the models used in this paper that is Deep learning-models then we could clearly see a better flexibility and higher accuracy as well as increased computational efficiency. The integration of deep learning
technology improves real-time decision processes in tourism-based navigation systems which leads to time reduction and increases user satisfaction levels.

General Terms
Deep Learning, Route Optimization, Tourism Navigation, Real-time Systems, Traffic Management, Weather Forecasting, User Preferences, Computational Efficiency

Keywords: Deep learning, route optimization, tourism, real time navigation, traffic prediction, personalized travel

Paper Title AI DRIVEN FRAUD DETECTION-TRANSFORMING DIGITAL SECURITY IN AN EVOLVING LANDSCAPE
Author Name Himanshi, Shivansh Mishra, Parichay Sharma & Aditya Raj
Country India
DOI https://doi.org/10.5281/zenodo.18950567
Page No. 52-59

Abstract View PDF Download Certificate
AI DRIVEN FRAUD DETECTION-TRANSFORMING DIGITAL SECURITY IN AN EVOLVING LANDSCAPE
Author: Himanshi, Shivansh Mishra, Parichay Sharma & Aditya Raj

ABSTRACT
New-generation digital security receives a transformation from AI-driven fraud detection because this method achieves higher accuracy and faster efficiency in real-time throughout the fast- evolving cyber environment. Today's fraud detection systems face problems and spots new security threats as they occur which results in monetary damage and reduced public
faith. The research demonstrates how artificial intelligence approaches merge into three classifications to minimize fraudulent detection inaccuracies. The key element of Explainable AI (XAI) ensures transparency through which AI- based decisions become reliably understandable by users. AI obtains immediate processing capability for large data volumes
which allows systems to detect abnormalities to deter cyberattacks during their development phase. Security systems become stronger through Artificial Intelligence because AI protects the digital space from both present and emerging fraud techniques.

General Terms
Pattern recognition, Explainable AI (XAI), Deep learning

Keywords: Artificial Intelligence, Digital Security, Cyber Attacks, Fraudulent Detection, and Digital Space.

Paper Title DETECTION AND IDENTIFICATION OF MEDICINAL PLANT USING AI AND IMAGE PROCESSING
Author Name Mahesh Kini, Rakesh, Sagar M H, Sanjay R & Preethesh Clive D Souza
Country India
DOI https://doi.org/10.5281/zenodo.18950752
Page No. 50-55

Abstract View PDF Download Certificate
DETECTION AND IDENTIFICATION OF MEDICINAL PLANT USING AI AND IMAGE PROCESSING
Author: Mahesh Kini, Rakesh, Sagar M H, Sanjay R & Preethesh Clive D Souza

ABSTRACT:
From ancient times, plants have played a crucial role in Ayurveda as a source of medicine. Accurate recognition of medicinal plants is essential in preparing Ayurvedic formulations, which has traditionally relied on manual expertise. However, due to the increasing demand for large-scale herbal medicine production, automating this process is now necessary. This paper presents a systematic approach for identifying medicinal plants using the Random Forest algorithm, a robust ensemble-based machine learning technique. The method employs a combination of color, texture, and structural characteristics extracted from plant images to classify them effectively. The experimental findings confirm the efficiency of this approach in achieving high classification accuracy, offering a scalable and reliable solution for the herbal medicine industry. By integrating artificial intelligence into this domain, the process not only ensures accuracy but also minimizes
reliance on human expertise, thereby facilitating mass production while maintaining quality and authenticity.

Keywords— Medicinal Plants, Plant Identification, Machine Learning, Image Recognition, Convolutional Neural Networks (CNNs), Support Vector Machines (SVM).

Paper Title BIOMETRIC AUTHENTICATION BEYOND FINGERPRINT SENSORS
Author Name Pragya Rajput, Raghav Somani, Harleet Kaur, Shraddha Sharma, Shruti Pundir & Riya Sharma
Country India
DOI https://doi.org/10.5281/zenodo.18951037
Page No. 56-66

Abstract View PDF Download Certificate
BIOMETRIC AUTHENTICATION BEYOND FINGERPRINT SENSORS
Author: Pragya Rajput, Raghav Somani, Harleet Kaur, Shraddha Sharma, Shruti Pundir & Riya Sharma

ABSTRACT
Modern security systems depend on biometric authentication as their main foundation because it presents better security than conventional authentication methods using passwords and PINs. Fingerprint sensors remain popular. However, their vulnerability to spoofing and sensitivity to environmental conditions necessitate more advanced authentication systems. A study of security/authentication techniques investigates new facial recognition and voice pattern authentication modalities
together with continuous measurement systems and privacy-protecting and AI-related methods. The research introduces transformative frameworks that unite AI with IoT capabilities to handle scalability needs while guaranteeing inclusivity and improving system energy efficiency toward future biometric technology.

Keywords : Biometric authentication, continuous authentication, and adaptive systems, along with artificial intelligence (AI), privacy-preserving techniques, and multimodal biometrics, are increasingly integrated with the Internet of Things (IoT) to enhance security and usability.

Paper Title 6G WIRELESS NETWORK: POTENTIAL ARCHITECTURE AND APPLICATIONS
Author Name Rajesh Sachdeva, Vishal Kumar Arora, Ankur Gupta & Shalini Sachdeva
Country India
DOI https://doi.org/10.5281/zenodo.18951252
Page No. 67-74

Abstract View PDF Download Certificate
6G WIRELESS NETWORK: POTENTIAL ARCHITECTURE AND APPLICATIONS
Author: Rajesh Sachdeva, Vishal Kumar Arora, Ankur Gupta & Shalini Sachdeva

ABSTRACT
The standardization activities of the 5G communications are clearly over and deployment has commenced globally. To endure the competitive edge of wireless networks, industrial and academia synergy have begun to conceptualize the next generation of wireless communication systems (namely, sixth generation, (6G)) aimed at laying the foundation for the
communication needs after a decade. A new wireless communication system integrated with artificial intelligence and blockchain technology is expected to be launched between 2027 and 2030. Though 5G has not been launched worldwide yet there are some major concerns, that can be addressed. These concerns may include improved QoS, low latency rate and
higher system capacity. This paper presents the architecture and some of the applications of future 6G wireless communication and its network architecture. Many of the emerging technologies such as artificial intelligence, blockchain technology, quantum communications, terahertz communications, three-dimensional networking, big data analytics that
can assist the 6G architecture development in guaranteeing the QoS will be discussed. We present the expected applications with the requirements and the possible technologies for 6G communication. We also outline the possible
applications and research directions to reach this goal.

Keywords 5G, 6G, QoS, Blockchain technology, artificial intelligence, quantum communications

Paper Title ADVANCING BORDER SECURITY AND NATIONAL DEFENSE: THE ROLE OF FACIAL RECOGNITION TECHNOLOGY IN MODERN SURVEILLANCE SYSTEMS
Author Name Aditya Chauhan & Harish Nagar
Country India
DOI https://doi.org/10.5281/zenodo.18951317
Page No. 75-82

Abstract View PDF Download Certificate
ADVANCING BORDER SECURITY AND NATIONAL DEFENSE: THE ROLE OF FACIAL RECOGNITION TECHNOLOGY IN MODERN SURVEILLANCE SYSTEMS
Author: Aditya Chauhan & Harish Nagar

ABSTRACT—
Facial recognition technology is revolutionizing the borders security and national defense scene at an extremely fast pace. This paper explores the role FRT could play in further improving surveillance, identification, and threat prevention mechanisms in critical zones of security. In the current state of practice, we analyze the effectiveness of FRT in identity verification, monitoring, and real- time threat assessment. It is because of its potential, however technology also gives rise to significant issues, including massive concerns, such as privacy issues and ethics, and also the requirement for proper regulatory frameworks. Assessing the security advantages versus the dangers related to privacy might be crucial in knowing how future innovations, especially integration strategies, and policy recommendations may be devised for the use of FRT appropriately and responsibly at national security.

Index Terms—Facial recognition technology, border security, national defense, surveillance, identity verification, privacy,
security policy, threat detection, ethical implications.

Paper Title PAYMENTS AND FACIAL RECOGNITION: THE FUTURE OF CONTACTLESS TRANSACTIONS
Author Name Deepanshi & Harish
Country India
DOI https://doi.org/10.5281/zenodo.18951461
Page No. 83-90

Abstract View PDF Download Certificate
PAYMENTS AND FACIAL RECOGNITION: THE FUTURE OF CONTACTLESS TRANSACTIONS
Author: Deepanshi & Harish

ABSTRACT
Facial recognition technology has emerged as a real game-changing tool in the realm of contactless payments, particularly with increasing claims of security, convenience, and user friendliness. In this paper, the integration of facial recognition in payment solutions is assessed in terms of its impact on transaction speed, fraud prevention, and consumer acceptance. Current advancements, potential security vulnerabilities, and ethical concerns are examined to conduct a deep analysis of how facial recognition can redefine digital transactions. The study also briefly discusses matters of privacy issues and regulation matters with an emphasis on measures that assure user trust and reliability of the system. The result puts forth the promise for the possibility that facial recognition could become one of the very widely accepted, efficient, and safe contactless payment methods very soon.

Index Terms—Facial Recognition, Contactless Payments, Digital Transactions, Payment Security, Biometric Authentication, Privacy, Consumer Acceptance, Fraud Prevention, User Experience, Regulatory

Paper Title AI-DRIVEN APPROACHES FOR IDENTIFYING GENETIC MUTATIONS
Author Name Aditya, Deepak Yadav & Aashima Narula
Country India
DOI https://doi.org/10.5281/zenodo.18951672
Page No. 91-96

Abstract View PDF Download Certificate
AI-DRIVEN APPROACHES FOR IDENTIFYING GENETIC MUTATIONS
Author: Aditya, Deepak Yadav & Aashima Narula

ABSTRACT
Genetic mutation detection is important for detecting genomic variation to cause disease. Such mutations as single nucleotide changes, insertions, and deletions can be found by a computational approach. This new method correctly identifies genetic variations by analyzing genetic data and comparing it to reference genomes. It thus shows high accuracy results that would allow research in understanding the mechanisms of the disease as well as genetic disorders. This research will help me improve mutation detection techniques, which have applications in the fields of medical
science and genetics.

Keyword: Genetic Mutation Detection, Machine Learning, Random Forest, Mutation Classification, Feature Importance

Paper Title FACIAL AUGMENTATION-DRIVEN ENHANCEMENTS IN DEEPFAKE DETECTION
Author Name Pragya Rajput, Ujjwal Kumar, Parit Rajput, Gautam Das, Raja Siddharth A R & Shubham
Country India
DOI https://doi.org/10.5281/zenodo.18951814
Page No. 97-108

Abstract View PDF Download Certificate
FACIAL AUGMENTATION-DRIVEN ENHANCEMENTS IN DEEPFAKE DETECTION
Author: Pragya Rajput, Ujjwal Kumar, Parit Rajput, Gautam Das, Raja Siddharth A R & Shubham

ABSTRACT
Deep fake technology brings significant concerns regardless of the domain in which it is applied from misinformation to cyber criminals and privacy violation. This new technology is a real danger to several fields as it can disseminate fake news, contribute to the increase of the number of cyberthreats and compromise the protection of personal data. The techniques previously used in detecting deep fake basically do not follow the rather high evolutionary rates of these generation techniques hence yielding a very high level of false positives and false negatives. This work seeks to investigate the viability of FA as an innovative method that strengthens the signal and the spatial resolution of deepfake detection techniques. This research aims to create multiple and complex datasets by combining the changes in facial features
comprising expressions, lighting and occlusion to assist the training of detection models. To assess the proposed approach in depth, the current and one of the most developed machine learning models including CNNs and high-level models are used. Last but not the least, we observed that when the proposed method includes dynamically augmented data, it added
even more value to the detection and reduces error rates substantially; thus it offers more effective ways to counter deep fake threats. These findings outline how knowledge of new strategies to counter the contamination of digital media or the protection against improper use of the deepfake technology is important.

Keywords: Deepfake Detection, Dynamic Face Augmentation, Generative Adversarial Networks (GANs), Machine Learning, Convolutional Neural Networks (CNNs), Data Augmentation, Misinformation, Cybersecurity, Image Analysis, Model Performance.

Paper Title DEVELOPMENT OF AN ONLINE SOCIETY COMPLAINT PORTAL
Author Name Pragya Rajput, Ayush Singh, Ankit kr. Singh, Prashant Chaudhary, Naphees Iqubal & Harsh Vardhan Singh
Country India
DOI https://doi.org/10.5281/zenodo.18952038
Page No. 109-114

Abstract View PDF Download Certificate
DEVELOPMENT OF AN ONLINE SOCIETY COMPLAINT PORTAL
Author: Pragya Rajput, Ayush Singh, Ankit kr. Singh, Prashant Chaudhary, Naphees Iqubal & Harsh Vardhan Singh

ABSTRACT:
The online Society Complaint Portal is designed to offer a simple and accessible platform for citizens to report complaints about societal issues, including infrastructure, public services, and safety concerns. The system features GPS geotagging, user verification, and the ability to handle complaints across multiple departments. Users can submit complaints, monitor their progress, and get timely updates from the appropriate authorities, all while enhancing transparency and efficiency in addressing public issues.

Keywords: Machine Learning, IoT (Internet of Things), Database Management, User Experience (UX), Security Protocols.

Paper Title POST QUANTUM CRYPTOGRAPHY: PREPARING FOR THE FUTURE
Author Name Vanshika Dhingra, Pragya Rajput & Annanya Nayar
Country India
DOI https://doi.org/10.5281/zenodo.18952416
Page No. 115-124

Abstract View PDF Download Certificate
POST QUANTUM CRYPTOGRAPHY: PREPARING FOR THE FUTURE
Author: Vanshika Dhingra, Pragya Rajput & Annanya Nayar

ABSTRACT
The novel threat posed by quantum computation is undermining classical public-key cryptographic systems that depend on RSA and ECC. To mitigate these difficulties, Block suggests An Adaptive Cryptographic Model to Future Quantum Networks’ which proposes a new model that includes Post quantum cryptography (PQC), Quantum Key Distribution (QKD), and AI based security tools. The exploratory case study approach is used which is composed of multiple components including the literature review, the design of the cryptographic agility framework, the experimental implementation, the conduct of security test, and also the compliance assessment. The block was implemented in simulated environments, monitoring quantum network’s ability to withstand quantum attack, efficiency, as well as the network’s
ability to manage encryption keys in real-time. The research was conducted in accordance to NIST PQC standards that merged with global regulatory frameworks in order to ensure that the provided results are adaptable and compliant across different regions. Cryptographic models which approached the adapted form did appear to meet the adequate level of security and increase the scalability and the agility of the cryptography within the quantum network. The prospective work contains fully homomorphic encryption (FHE) set, quantum identity management with a post-quantum blockchain security paradigm. This work assists tangible endeavours toward the development of quantum-secured next-generation communication system where data will be preserved for long periods of time, while remaining compliant with the regulations and protected from unauthorized access.

Keywords— Post-Quantum Cryptography, Quantum Key Distribution, AI Security, Cryptographic Agility, Quantum Networks.

Paper Title REAL-TIME STRESS DETECTION USING CNN IN DEEP LEARNING
Author Name Tandra Debarati Shome & Laxmi Maurya
Country India
DOI https://doi.org/10.5281/zenodo.18952636
Page No. 125-131

Abstract View PDF Download Certificate
REAL-TIME STRESS DETECTION USING CNN IN DEEP LEARNING
Author: Tandra Debarati Shome & Laxmi Maurya

ABSTRACT
Stress has become a part of everyday life, affecting people of all ages. It creates significant challenges for well-being and productivity. Despite advancements in physiological techniques for stress detection, there are still hurdles in making these solutions real-time, affordable, and accessible to everyone. Psychological stress is closely tied to emotions, and understanding this connection plays a key role in analyzing human behavior, particularly in computational psychology. While deep learning techniques, like Convolutional Neural Networks (CNNs), have shown great promise in detecting facial emotions from images, their potential for identifying mental stress remains underexplored. The system provides a holistic approach to understand and evaluate stress through images and video processing.

Keywords- Stress detection, CNN model, Emotions classes, image processing.

Paper Title SECUREAUTHENTICATION SYSTEM USING BIOMETRIC
Author Name Azhar, Joti Sharma, Himani, Shiv Sharan Dixit, Shubham Kumar & Arpit Negi
Country India
DOI https://doi.org/10.5281/zenodo.18952761
Page No. 132-138

Abstract View PDF Download Certificate
SECUREAUTHENTICATION SYSTEM USING BIOMETRIC
Author: Azhar, Joti Sharma, Himani, Shiv Sharan Dixit, Shubham Kumar & Arpit Negi

ABSTRACT
In today's world of digital transformation, a secure and reliable authentication system is necessary to prevent unauthorized access and breaches in both actual and virtual data. Traditional authentication mechanisms like password-based and PINbased systems are vulnerable to various forms of security threats such as phishing, credential leaks, or brute-force attacks.
Biometric authentication for a good alternative authenticated verification mode is found to either contain unique physiological or behavioral distinct user characteristics fingerprints, face or iris recognition, or biometrics. This research undertakes an investigation into the effectiveness, security, and challenges of biometric authentication. It studies the space mapping of integration multimodal biometrics, encryption, and machine learning algorithms to enhance security and minimize spoof identity risks. The study also addresses the advantage-disadvantage argument of security versus privacy versus user transparency and considers all the topics of concern related to data storage, biometric spoofing, and ethics in
these terms.

Keywords—Biometrics, Authentication, security, Encryption, Credentials, machine learning, PINs.

Paper Title HARNESSING MACHINE LEARNINGTECHNIQUES TO DIAGNOSE TOMATO PLANT DISEASES
Author Name S. Aruna, R. Abinaya, A. Vanithasr & A. Vasanthakumar
Country India
DOI https://doi.org/10.5281/zenodo.18953033
Page No. 139-149

Abstract View PDF Download Certificate
HARNESSING MACHINE LEARNINGTECHNIQUES TO DIAGNOSE TOMATO PLANT DISEASES
Author: S. Aruna, R. Abinaya, A. Vanithasr & A. Vasanthakumar

ABSTRACT—
Agriculture is basic in the development of any nation and also contributes to economic stability. Tomato production constitutes a significant aspect of agriculture in Tamil Nadu and India. It is facing yield and quality issues. However, disease in crops lowers the health of tomato leaves and the
productivity of a tomato plant. This study has focused on an approach to develop a Convolutional Neural Network (CNN) model improved with data augmentation for detecting diseases in tomato leaves. It identifies and classifies multiple diseases on tomato leaves accurately at 89% with over 35
epochs during training. All validation metrics support the strength and effectiveness of the model: AUC score, precision, and recall. The software solution also serves both detection and practical application by suggesting appropriate chemicals for recognized diseases such as early blight, septoria
leaf spot, and powdery mildew. This function makes it easier to manage the disease as a whole and a loss on crops is not so severe. It was trained on images of tomato leaves, some of which were obtained from the Plant Village repository in order to have variation in the datasets to make them practical for use in the real world. The research underlines the possibility of technology integration in agricultural practices and proposes an effective method of focusing on the prevention of disease outbreak and its link to appropriate management activities. This adds crop productivity but also promotes sustainable agricultural practices which enhances economic and environmental stability.

Keywords— Convolutional Neural Network, Data Augmentation, Tomato Leaf Disease Detection.

Paper Title DYNAMIC MULTI-SUBSCRIPTION AZURE RESOURCE AUTOMATION USING TERRAFORM
Author Name Kartik Bhardwaj, Alish Pandey, Rhythmpreet Kaur & Ramandeep Singh
Country India
DOI https://doi.org/10.5281/zenodo.18953393
Page No. 150 -154

Abstract View PDF Download Certificate
DYNAMIC MULTI-SUBSCRIPTION AZURE RESOURCE AUTOMATION USING TERRAFORM
Author: Kartik Bhardwaj, Alish Pandey, Rhythmpreet Kaur & Ramandeep Singh

ABSTRACT
Governance and provisioning of Azure resources across various subscriptions remains a challenging task, largely due to the limitations of Terraform’s azurerm provider by design. While Terraform enjoys widespread acclaim as an Infrastructure-as-Code (IaC) capabilities fall short in tool, multi-subscription automation. It describes a novel approach combining python scripting, pipeline automation using YAML in azure devops and Terraform to achieve a scalable, performant and fully automated resource provisioning spanning multiple Azure subscriptions. In particular, Terraform variable files ( .tfvars ) with subscription data imported from a structured CSV file, eliminating the need for any manual configuration. A matrix strategy on a YAML pipeline orchestrates the run of Terraform steps—init, plan and apply— in parallel across multiple workspaces significantly speeding up deployment while reducing overhead. For large-scale, enterprise deployments, this setup is particularly useful as storing Terraform state files in a centralized Azure Storage account enhances both maintainability and conflict prevention. So presenting a systematized automation-based method that minimizes human interaction and streamlines the provisioning process while improving consistency of state is the significant finding of this work, translating into a better cloud automation approach. Well suited for multi-cloud deployments, the approach is both a sound architectural and operational best practice that help alleviate some of the most common scalability and operational challenges that all cloud practitioners experience.

Keywords: Azure, Terraform, Multi-Subscription Automation, YAML Pipelines, Python Scripting, Cloud Automation.

Paper Title CYBER-RESILIENT NETWORK ARCHITECTURE FOR SMART GRID
Author Name Azhar Ashraf, Shishir Singh, Devesh Kumar Upadhyay, Shruti Sharma, & Nimmanagoti Anil
Country India
DOI https://doi.org/10.5281/zenodo.18975445
Page No. 160-167

Abstract View PDF Download Certificate
CYBER-RESILIENT NETWORK ARCHITECTURE FOR SMART GRID
Author: Azhar Ashraf, Shishir Singh, Devesh Kumar Upadhyay, Shruti Sharma, & Nimmanagoti Anil

ABSTRACT—
For smart grids dealing with changing cyber threats, guaranteeing a cyber resilient network is important. This project uses artificial intelligence, specifically Convolutional Neural Networks (CNN), to improve grid security by detecting and mitigating phishing, malware, and DDoS threats. The system correctly detects phishing 33.1% of the time, malware 31.4% of the time, and DDoS attacks 32.4% of the time, with low false positive rates of 0.7% for phishing, 1.0% for malware, and 1.4% for DDoS. To precisely spot all unusual login behaviours, the system thoroughly integrates real-time threat intelligence, in-depth behavioural analysis, and immediate proactive alerts, ultimately achieving a 90% accuracy rate. User feedback confirms its effectiveness and usability through a satisfaction rate of 92% and an adoption rate of 78%. The system secures all communications through encryption, two-factor authentication, and identity verification, fully complying with GDPR and NIST SP 800-63B. This AI framework both strengthens how secure the grid is and keeps operations strong by always
adjusting to new dangers.

Keywords: cybersecurity automation in power systems, secure grid communication, AI-powered security, smart grid security compliance, and machine learning for cybersecurity; Adaptive security architecture; proactive cyber defence; intrusion detection and prevention; threat intelligence in energy networks; and cyber- resilient smart grids.

Paper Title PRIVACY-PRESERVING THREAT SHARING ACROSS ORGANIZATIONS
Author Name Rahul Bhardwaj, Pooja, Ritik Raushan, Akanksha Jain & Azhar Ashraf Gadoo
Country India
DOI https://doi.org/10.5281/zenodo.18975549
Page No. 168-176

Abstract View PDF Download Certificate
PRIVACY-PRESERVING THREAT SHARING ACROSS ORGANIZATIONS
Author: Rahul Bhardwaj, Pooja, Ritik Raushan, Akanksha Jain & Azhar Ashraf Gadoo

ABSTRACT –
Cybersecurity threats have become quite sophisticated, and organizations depend on real-time threat intelligence sharing to protect themselves against the rise of attacks. However, privacy, data confidentiality and competitive risks often restrict their collaboration to the data exchange only. In this paper one, we present a privacy-preserving threat-sharing framework
allowing parties to exchange sensitive threat intelligence information while preventing sensitive internal information leak. only get access to the raw data, while aggregated threat data can be shared with lead analytics. We explore its applicability in threat-sharing within varying contexts, showing organizations manners of leveraging aggregated intelligence without
revealing avenues for proprietary or sensitive data compromise. We show that the use of privacy-preserving mechanisms can greatly facilitate cross-organizational collaboration for cybersecurity and can be compliant with regulatory and legal obligations. This paper provides insights into the broader discussion of secure cyber defence strategies, stressing the role of privacy in promoting collaboration against cyber threats.

Keywords: Cybersecurity, Threat Intelligence Sharing, Privacy-Preserving Framework, Cryptographic Techniques, Differential Privacy, Secure Multi-Party Computation (MPC), Cross- Organizational Collaboration.

Paper Title SENTIMENT ANALYSIS IN SOCIAL MEDIA: TECHNIQUESAND APPLICATIONS
Author Name Pragya Rajput, Aditya Jain, Lovish Gupta & Abhishek Thakur
Country India
DOI https://doi.org/10.5281/zenodo.18975651
Page No. 177-184

Abstract View PDF Download Certificate
SENTIMENT ANALYSIS IN SOCIAL MEDIA: TECHNIQUESAND APPLICATIONS
Author: Pragya Rajput, Aditya Jain, Lovish Gupta & Abhishek Thakur

ABSTRACT—
Sentiment analysis is one of the important research fields in natural language processing, which is currently gaininga lot of significance due to the increasing growth of social media. This paper provides an overall review of the techniques concerning sentiment analysis, strictly developed for social media contexts. We will discuss a wide variety of methodologies, from classical statistical methods to state-of-the-art machine learning and deep learning methods. It discusses preprocessing methods, feature extraction strategies, and model evaluation metrics by outlining implications for effective sentiment detection. Further, it outlines some of the key applications of sentiment analysison social media platforms, such as brand management, public opinion monitoring, and crisis management. Current challenges such as dealing with noisy data, handling ambiguity in sentiment, and ensuring model generalization across diverse social media platforms are identified. Finally, we discuss some emerging trendsin sentiment analysis research and future directions, among them the integration of multimodal
data and the application of transfer learning. This review intends to provide a holistic viewof sentiment analysis techniques and their practical applications, thus offering insights into important areas for both researchers and practitioners in the field.

Index Terms—Sentiment Analysis, Social Media, Machine Learning, Natural Language Processing, Feature Extraction

Paper Title AI BASED AGRICULTURE SOLUTIONS FOR FARMERS
Author Name Milind Mishra
Country India
DOI https://doi.org/10.5281/zenodo.18975747
Page No. 185-191

Abstract View PDF Download Certificate
AI BASED AGRICULTURE SOLUTIONS FOR FARMERS
Author: Milind Mishra

ABSTRACT:
Agriculture is the spine of numerous economies; however, ranchers regularly confront challenges such as eccentric climate, soil debasement, bug invasions, and wasteful asset utilization. This research about presents an AI-based Android application outlined to enable agriculturists with real-time, data-driven experiences to improve efficiency and maintainability. The proposed framework leverages machine learning and computer vision to give edit illness discovery, climate determining, soil wellbeing investigation, and abdicate expectation. Furthermore, the app coordinating IoT-based
keen cultivating and chatbot back for moment master direction. By utilizing profound learning calculations and lackey symbolism, the framework guarantees exactness farming, decreasing asset wastage whereas maximizing surrender. The consider investigates the effect of AI-driven decision-making in farming, illustrating how the proposed arrangement can
revolutionize conventional cultivating hones and bridge the advanced partition for country agriculturist.

Keywords: AI in Agriculture, Smart Farming, Crop Disease Detection, Precision Agriculture, Machine Learning, Android App.

Paper Title BLOCKCHAIN-BASED DIGITAL ELECTIONS: ENHANCING TRANSPARENCY AND SECURITY
Author Name Bhavi, Azhar Ashraf Gadoo, Anshul Sharma & Prince Gupta
Country India
DOI https://doi.org/10.5281/zenodo.18975887
Page No. 192-199

Abstract View PDF Download Certificate
BLOCKCHAIN-BASED DIGITAL ELECTIONS: ENHANCING TRANSPARENCY AND SECURITY
Author: Bhavi, Azhar Ashraf Gadoo, Anshul Sharma & Prince Gupta

ABSTRACT
While digitalization has continued to alter electoral processes, the integrity, transparency, and security of elections are increasingly complicated. This paper explores ways through which blockchain addresses key challenges in digital elections, such as voter fraud, data manipulation, and lack of transparency, by availing its decentralized nature and cryptographic security
features to increase the trust in digital voting systems. While analyzing theoretical models and case studies, the research shows that blockchain has the potential to fashion an electoral system that will be tamper-proof and transparent, with a guarantee of accuracy and integrity in election results. Implementation of blockchain for digital elections is not all roses, though.
For this technology to realize full potential, issues regarding scalability, privacy concerns, and regulatory compliance need to be addressed. This paper critically analyses these practical chal- lenges and discusses strategies to overcome them. The research, therefore, intends to show how blockchain can change the face of the electoral process and is supposed to provide a roadmap for integrating blockchain technology into digital elections in order for modern democracies to come closer to an increasingly secure, transparent, and reliable voting system.

Index Terms—Blockchain Technology, Digital Elections, Elec- toral Integrity, Transparency, Security, Tamper-Proof Voting, Voter Fraud Prevention, Cryptographic Protocols, Decentral- ization, Scalability, Privacy Concerns, Regulatory Compliance, Voting System Transformation

Paper Title REAL-TIME CONNECTIVITY CROSS-PLATFORM ACCESSIBILITY ENHANCED USER EXPERIENCE CENTRALIZED DATA MANAGEMENT
Author Name Bibek Budhathoki, Sumit Arora & Azhar Ashraf
Country India
DOI https://doi.org/10.5281/zenodo.18975944
Page No. 200-207

Abstract View PDF Download Certificate
REAL-TIME CONNECTIVITY CROSS-PLATFORM ACCESSIBILITY ENHANCED USER EXPERIENCE CENTRALIZED DATA MANAGEMENT
Author: Bibek Budhathoki, Sumit Arora & Azhar Ashraf

ABSTRACT
In the age of digital transformation, it has become imperative to provide real-time connectivity and cross-platform access to ensure uninterrupted user interaction across devices. This study delves into novel frameworks and approaches to improve the user experience with a centralized data management system. By combining state-of-the-art cloud computing, edge processing, and AI-optimized optimizations, this research pro- poses a scalable method to provide uninterrupted, synchronized access to data. The envisioned system facilitates smooth data flow, minimizes latency, and supports interoperability, ultimately resulting in an effortless and enriched digital ecosystem.

Index Terms—Real-time connectivity, Cross-platform accessi- bility, Enhanced user experience, Centralized data management, Cloud computing, Edge processing, AI-driven optimization, Data synchronization, Interoperability, Digital transformation.

Paper Title EVOLVEED: AI-DRIVEN PERSONALIZED LEARNING
Author Name Pragya Rajput, Ankit Kumar Singh, Barenya Behera, Prachi Mittal, Radhika & Disha Singh
Country India
DOI https://doi.org/10.5281/zenodo.18976086
Page No. 208-216

Abstract View PDF Download Certificate
EVOLVEED: AI-DRIVEN PERSONALIZED LEARNING
Author: Pragya Rajput, Ankit Kumar Singh, Barenya Behera, Prachi Mittal, Radhika & Disha Singh

ABSTRACT
The swift progressions in artificial intelligence (AI) has been a major reason of the bloom seen by the world of academics facilitating personalized and accommodative learning experiences. The diverse intellectual styles and paces of individuals are generally discarded by conventional learning techniques which can lead to withdrawal and lack of efficient learning journey. The curriculum and the intensity of challenges a student faces are dynamically adjusted based on their progress and learning inclinations by EvolveED, an AI-driven personalized learning platform. An engrossing and effective learning journey is assured by EvolveED for the reason that it capitalizes on adaptive algorithms, real-time feedback mechanisms
and behavioral analysis. The video engagement system formulated on eye-tracking which supervises focus of a student when attending scholastic sessions is one of the most notable aspect of the platform. Any lack of concentration or shifting of gaze from the screen results in a time out making sure the learners are earnestly occupied with the content. EvolveED
not only elevates inclusion but thus also nurtures a more collaborative and learner-oriented environment. The methodologies utilized in the platform, their real-world influence on educational attainment and the overall and
comprehensive significance of AI have been considered in this paper. The challenges of achieving AI-driven in instructive solutions and proposals for future approaches for additional refinement and scaling of the presented approach have also been addressed.

General Terms Personalized learning, Artificial Intelligence, Machine learning, Algorithm Design, Learning Analytics, Educational technology, Behavioral Analysis.

Keywords
AI-driven learning, personalized tuition, adaptive algorithms, real-time feedback, student engagement, eyetracking mechanism.

Paper Title SMART OPTIMIZATION: REVOLUTIONIZING RESEARCH ALGORITHMS FOR SEAMLESS USER EXPERIENCE
Author Name Pragya Rajput, Prikshit Singh, Arnav Kumar & Yoginder Singh
Country India
DOI https://doi.org/10.5281/zenodo.18976198
Page No. 217-225

Abstract View PDF Download Certificate
SMART OPTIMIZATION: REVOLUTIONIZING RESEARCH ALGORITHMS FOR SEAMLESS USER EXPERIENCE
Author: Pragya Rajput, Prikshit Singh, Arnav Kumar & Yoginder Singh

ABSTRACT
This research addresses the limitations of traditional research algorithms, such as data scarcity, cold-start Problems, scalability challenges, and inefficient ranking. The proposed optimization framework integrates hybrid recommender systems, deep learning-based ranking methods, and a cluster-based algorithm selection mechanism to enhance user experience and retrieval efficiency. It employs collaborative filtering, content-based filtering, and hybrid approaches while leveraging ranking metrics like Rank-Biased Precision (RBP) and Normalized Discounted Cumulative Gain (NDCG) to improve content relevance. Additionally, a network-friendly optimization model enhances computational efficiency without compromising search quality. Experimental evaluation on real-world datasets, including financial product recommendations and digital libraries, demonstrates significant improvements in precision, recall, and user satisfaction. The research introduces a personalized, adaptive approach that optimizes recommendation algorithms, bridging computational efficiency with enhanced user engagement for next-generation intelligent systems.

Keywords—Research Algorithm Optimization, Machine Learning, Recommender Systems, User Experience Enhancement, Ranking-based Optimization, Deep Learning, Adaptive Research Models

Paper Title INVESTIGATING THE IMPACT OF CLIMATE CHANGE ON AGRICULTURE: ANALYZING CROP YIELD VARIABILITY AND ADAPTIVE STRATEGIES
Author Name Pragya Rajput, Harshmeet Singh, Komaldeep Singh & Noorpreet Singh Saini
Country India
DOI https://doi.org/10.5281/zenodo.18976339
Page No. 226-233

Abstract View PDF Download Certificate
INVESTIGATING THE IMPACT OF CLIMATE CHANGE ON AGRICULTURE: ANALYZING CROP YIELD VARIABILITY AND ADAPTIVE STRATEGIES
Author: Pragya Rajput, Harshmeet Singh, Komaldeep Singh & Noorpreet Singh Saini

ABSTRACT—
Climate change is one of the great challenges facing agriculture in the world because it changes weather patterns, affects the health of the soil, and lowers crop production. This study explores the complex relationship between climate change and agriculture with an emphasis on how variability in crop yields arises due to a change in climatic variables, including temperature fluctuations, changes in precipitation, and extreme weather events. The paper integrates short- and long-term impacts of climate change on various crops in different regions with special attention to the vulnerable farming
community. Adaptive strategies, including climate-resilient crops, improved irrigation techniques, and technological innovations, are further considered as potential sources of mitigation against the adverse effects of climate change on agricultural productivity. Results suggest that sustainable agricultural practices are supported by a confluence of multiple factors over research and findings from science, policy intervention, and technological innovation in this changing climate.

Index Terms—Climate change, agriculture, crop yield variabil- ity, adaptive strategies, extreme weather events, soil health, irriga- tion techniques, climate-resilient crops, agricultural productivity.

Paper Title EMERGENCY SUPPORT SYSTEM: AN INTEGRATED ANDROID AND WEB-BASED PORTAL FOR LIFELINE SERVICES
Author Name Harsh Gaur, Bhavya Kapoor & Azhar Ashraf
Country India
DOI https://doi.org/10.5281/zenodo.18976540
Page No. 234-239

Abstract View PDF Download Certificate
EMERGENCY SUPPORT SYSTEM: AN INTEGRATED ANDROID AND WEB-BASED PORTAL FOR LIFELINE SERVICES
Author: Harsh Gaur, Bhavya Kapoor & Azhar Ashraf

ABSTRACT—
During emergencies, prompt access to essential ser- vices is vital to reducing loss of lives and risks. This study pro- poses an integrated emergency support system that uses Android apps and web portals to offer convenient access to lifeline services like healthcare, police response, firefighting, and disaster relief. The system provides real-time communication, tracking, and automated alerting to facilitate efficiency in response. Through the use of AI-powered analytics and cloud infrastructure, the envisioned platform will make emergency response processes efficient, eliminate delays, and enhance access. The performance of the system is analyzed in case studies and user responses to prove its feasibility for deployment in smart cities and rural towns at scale.

Index Terms—Emergency support system, Android applica- tion, Web portal, Lifeline services, Real-time communication, AI-driven analytics, Cloud-based infrastructure, Disaster man- agement, Location tracking, Smart city deployment.

Paper Title MALWARE TRAFFIC ANALYSIS USING MACHINE LEARNING AND DEEP LEARNING: A COMPARATIVE STUDY WITH LSTM, XGBOOST, AND RANDOM FOREST
Author Name Vaibhav Bajaj, Taniya Mukhija, Azhar Asroof & Harshita Dhingra
Country India
DOI https://doi.org/10.5281/zenodo.18976678
Page No. 240-247

Abstract View PDF Download Certificate
MALWARE TRAFFIC ANALYSIS USING MACHINE LEARNING AND DEEP LEARNING: A COMPARATIVE STUDY WITH LSTM, XGBOOST, AND RANDOM FOREST
Author: Vaibhav Bajaj, Taniya Mukhija, Azhar Asroof & Harshita Dhingra

ABSTRACT—
With cyber threats evolving constantly, we needed something beyond traditional rule-based detection, which struggles against polymorphic attacks. We tested machine learning models, starting with Random Forest (RF) and XGBoost on the CICIDS2017 dataset, and while they gave a solid baseline, they missed sequential attack patterns. That’s when we moved to Deep Learning (DL), specifically Long Short-Term Memory (LSTM) networks, which handle time-series network traffic way better. But then we ran into another issue—class imbalance, where rare attacks were barely represented. So, we used GANs and SMOTE to fix that, generating synthetic attack traffic to train the model better. We evaluated everything with accuracy, precision, recall, F1-score, and AUC-ROC, and the pattern was clear—LSTM outperformed RF and XGBoost, improving malware detection by capturing sequential dependencies in network traffic. Our results highlight the tradeoff between accuracy and computational cost, showing that while LSTM is powerful, hybrid approaches may work even better in balancing detection efficiency and real-time processing.

Keywords— Malware Traffic Analysis, Machine Learning, Deep Learning, LSTM, XGBoost, Random Forest, GANs, SMOTE, Network Security

Paper Title DEEPLEARNING FOR AGE AND GENDER ESTIMATION
Author Name Bharath Yalagi & Sangeetha J
Country India
DOI https://doi.org/10.5281/zenodo.18978344
Page No. 248-259

Abstract View PDF Download Certificate
DEEPLEARNING FOR AGE AND GENDER ESTIMATION
Author: Bharath Yalagi & Sangeetha J

ABSTRACT:
Automatic age and gender prediction via facial recognition is an important feature in modern applications, such as personalized marketing, surveillance, and security systems. This work focuses on applying CNNs in order to learn
and extract automatically features from face images, doing away with manually engineered features. The system predicts age within certain ranges and accurately classifies gender, even under tough environments characterized by variable illumination, facial expressions, and occlusions. Using a diverse and labelled dataset, the model generalizes to unseen data while dealing with real-world complexities. Used Techniques like transfer learning and data augmentation enhance the robustness and accuracy of system. The suggested approach not only enhances the reliability of prediction but also shows significant promise for deployment in areas such as forensic investigations, demographic studies, and human-computer interaction. This novel approach is expected to provide a scalable and efficient framework for automated demographic analysis.

Keywords: Convolutional Neural Networks, ResNet, VGGNet, deep learning, data augmentation

Paper Title SECURE COMMUNICATION IN CRITICALWIRELESS INFRASTRUCTURE NETWORK
Author Name Subhajit Paul, Azhar Ashraf, Abhay Tiwari, Abhijeet Kumar, Shubham Kumar Jha & Shreyansh Shrey
Country India
DOI https://doi.org/10.5281/zenodo.18977770
Page No. 260-266

Abstract View PDF Download Certificate
SECURE COMMUNICATION IN CRITICALWIRELESS INFRASTRUCTURE NETWORK
Author: Subhajit Paul, Azhar Ashraf, Abhay Tiwari, Abhijeet Kumar, Shubham Kumar Jha & Shreyansh Shrey

ABSTRACT
Critical infrastructure networks (CINs), such as power grids, transportation systems, and water supply networks, provide the foundation of modern society. As we continue scaling these networks, the required protection to secure communication within these networks against cyber threats, unauthorized access, and potential system failures becomes critical. This
article describes the major risks and vulnerabilities in CIN communication, covering threats like Man-in-the-Middle attacks, Denial-of-Service (DoS) attacks, and Advanced Persistent Threats (APTs). We examine current security frameworks, encryption methodologies, and authentication strategies, underlining how cryptographic protocols, blockchain, and AI-based anomaly detection can be pivotal in strengthening resilience. In addition, we introduce a multitiered security architecture and describe how incorporating real-time monitoring mechanisms, secure network
communication protocols, and a zero-trust network design paradigm can secure data transmission between elements of CINs. Future research directions: What are we going to do?

Keywords— Critical Infrastructure, Secure Communication, Cybersecurity, Cryptography, Zero-Trust Architecture, Anomaly Detection, Blockchain.

Paper Title ADVANCING CYBERSECURITY: A COMPREHENSIVE REVIEW OF FEDERATED LEARNING APPROACHES FOR DISTRIBUTED INTRUSION DETECTION SYSTEMS
Author Name Anupam Sharma, Arbaz Raza, Kunal Chauhan, Simranpreet Kaur, Udit Dagar & Digvijay Singh Shekhawat
Country India
DOI https://doi.org/10.5281/zenodo.18978263
Page No. 267-275

Abstract View PDF Download Certificate
ADVANCING CYBERSECURITY: A COMPREHENSIVE REVIEW OF FEDERATED LEARNING APPROACHES FOR DISTRIBUTED INTRUSION DETECTION SYSTEMS
Author: Anupam Sharma, Arbaz Raza, Kunal Chauhan, Simranpreet Kaur, Udit Dagar & Digvijay Singh Shekhawat

ABSTRACT—
The review paper analyzes cybersecurity through examining how federated learning works with distributed intrusion detection systems for implementation and performance effectiveness. The increasing danger from cyberattacks forces traditional intrusion detection systems to struggle in their ability to respond to present-day cybersecurity threats. Federated learning presents itself as a solution to improve distributed network detection through decentralized machine learning models. The abstract presents a thorough research on federated learning approaches together with their intrusion detection system applications that boost detection precision and operational speed. The paper explores both the advantages and difficulties implied by federated learning systems while discussing security-related issues along with privacy protection needs and network traffic management problems and model distribution mechanisms. The study uses case studies and
experimental results to illustrate the functional advantages that result from federated learning implementation across different network configurations. The paper provides essential research and practical guidance about present-day distributed intrusion detection breakthroughs to scholars and security experts and technical professionals. Based on existing research synthesis and important discoveries we intend to steer upcoming research directions for building improved cybersecurity solutions suited to distributed computing systems.

Keywords— Federated learning, cybersecurity, intrusion detection, distributed networks, machine learning, privacy preservation, model synchronization, communication overhead, network security, adaptive cybersecurity.

Paper Title REAL TIME PHISHING DETECTION USING AI IN CORPORATE NETWORKS
Author Name Azhar, Shanu Kumar, Onkar Nath & Bevan Mehra
Country India
DOI https://doi.org/10.5281/zenodo.18978852
Page No. 276-283

Abstract View PDF Download Certificate
REAL TIME PHISHING DETECTION USING AI IN CORPORATE NETWORKS
Author: Azhar, Shanu Kumar, Onkar Nath & Bevan Mehra

ABSTRACT
The phishing attacks targeting today corporate networks have fully exploited email, messaging, and collaboration platforms. Even traditional security measures like signature-based and rule-based systems have a hard time keeping up with advancing phishing strategies. In this, we delve into a real-time AI driven phishing detection system using machine learning, deep learning, and natural language processing that promises exceptionally high accuracy in detecting and responding to threats. The anomaly detection integration with AI, behavior analysis, and multi-layered automated response
mechanisms help in securing multi-channel corporate communication. The system is capable of real-time phishing detection by performing sophisticated analyses of email metadata, hyperlinks, and message content. Proactive AI-response measures such as content filtering, user alerting, etc. further improve corporate defense. Challenges such as conducted
adversarial AI attacks, detection of false positives, and compliance to data privacy regulations are notable, yet, progress in federated learning and Explainable AI provide answers to the unique problems posed. Ultimately, this research shed light on the powerful potential of AI being able to combat phishing attack in real-time.

Keyword : AI-based Phishing Detection, Real-time Cybersecurity, Machine Learning, Deep Learning, Corporate Networks.

Paper Title AI-DRIVEN REAL-TIME WEATHER ANALYTICS FOR PRECISION AGRICULTURE: ENHANCING CROP MANAGEMENT AND YIELD PREDICTION
Author Name Lavanish Chaudhary, Rishi Kumar Singh, Raushan Kumar, Abhishek Kumar, Atul & Amit Vajpayee
Country India
DOI https://doi.org/10.5281/zenodo.19015311
Page No. 284-292

Abstract View PDF Download Certificate
AI-DRIVEN REAL-TIME WEATHER ANALYTICS FOR PRECISION AGRICULTURE: ENHANCING CROP MANAGEMENT AND YIELD PREDICTION
Author: Lavanish Chaudhary, Rishi Kumar Singh, Raushan Kumar, Abhishek Kumar, Atul & Amit Vajpayee

ABSTRACT—
Climate fluctuations heavily influence farm produc- tivity, calling for sophisticated weather analytics for precision agriculture. The study suggests a real-time weather analytics system powered by artificial intelligence specifically designed for agriculture, based on machine learning algorithms and IoT- based sensor networks for monitoring and forecasting meteorological parameters. The system combines real-time weather observations, satellite imaging, and climatological history to improve farmers’ decision-making. Key characteristics involve temperature, humidity, rainfall, and wind pattern analysis, which allow for real-time interventions to maximize irrigation, pest management, and crop output. The outlined framework enhances accuracy in forecasting, reduces losses, and encourages climate- resilient agriculture. Results from experiments validate the ef- ficiency of the system in delivering actionable knowledge for climate-resilient agriculture.

Index Terms—Real-time weather analytics, precision agricul- ture, machine learning, IoT, climate prediction, crop yield optimization, smart farming, sustainable agriculture, meteorological monitoring.

Paper Title MEASURING ENERGY AND POWER EXCHANGE FOR PV-ESBS SYSTEM USING MATLAB/SIMULINK
Author Name Gurpinder Singh, Sushil Kakkar & Shweta Rani
Country India
DOI https://doi.org/10.5281/zenodo.19015371
Page No. 292-302

Abstract View PDF Download Certificate
MEASURING ENERGY AND POWER EXCHANGE FOR PV-ESBS SYSTEM USING MATLAB/SIMULINK
Author: Gurpinder Singh, Sushil Kakkar & Shweta Rani

ABSTRACT:
The transition to renewable energy, particularly solar photovoltaic (PV) systems, necessitates robust energy storage solutions. To facilitate this shift, accessible models of PV systems integrated with battery storage (ESBS) are crucial for engineers. These models enable the evaluation of technical and economic advantages during system design. This work introduces a comprehensive model that accurately represents power flows and energy exchanges within a PV-ESBS system. It offers two PV generation approaches: a Gaussian model and a meteorological data-based (MDB) model. The
MDB model is shown to be more effective for short-term analysis, while the Gaussian model aligns better with long-term measured data. The model is versatile, capable of simulating various energy management strategies, including peakshaving and maximizing self-consumption, applicable across different PV-ESBS scales. Validation is achieved by comparing simulation results with data from a real-world grid-tied PV-ESBS, demonstrating the model's accuracy and reliability.

Paper Title GREEN COMPUTING-A REVIEW
Author Name Chanpreet Kaur & Harminder Kaur
Country India
DOI https://doi.org/10.5281/zenodo.19015665
Page No. 303-310

Abstract View PDF Download Certificate
GREEN COMPUTING-A REVIEW
Author: Chanpreet Kaur & Harminder Kaur

ABSTRACT
The undertaking task of “Saving Planet Earth” has become essential to all of us for the sustainable life on the Earth. The necessity of sustainable development and urgency to save Earth stems from the increasing pressures of human activities which result in global warming and greenhouse emission. In today's world IT is playing a pivotal role in ensuring the integration of technologies and systems. Day by day there is an escalation in energy consumption by IT resources. To provide solutions and focus on this key problem, a new paradigm “Green Computing or Green IT” appeared. This
paradigm promotes the environmentally responsible use of computer resources which involves employing energy-efficient processors, servers, and peripherals, along with responsible e-waste disposal practices. The goal is to minimize the carbon footprint of IT operations worldwide. Various dimensions of environment sustainability, energy efficient economy, reusability or recyclability of used products are included in the broader way of this paradigm. These dimensions have also paved the reasons for developing this approach as it manages to save power, produces long term benefits, reduces pollution and increases performance etc. Technologies like Green Cloud Computing, Internet of Things (IOT), Green Servers, and nano computing are the key drivers in the progress of Green Computing. Furthermore, various enforcement policies by government agencies or corporate sectors effectively catalyze the implementation of Green Computing. Additionally, it is also spreading awareness that sustainable computing practices are important and how to make their usage in an ecofriendly manner.

General Terms
Green IT, Eco-friendly IT, Energy Efficiency, Environmental Pollution

Keywords: Sustainable Development, Green Computing, IOT, Green Cloud Computing, Green Servers, Nano Computing,
Bio Computing, Virtualization

Paper Title ARTIFICIAL INTELLIGENCE IN E-COMMERCE
Author Name Harshit, Er. Disha Sharma, Tanuja Dobal & Yuvraj Tyagi
Country India
DOI https://doi.org/10.5281/zenodo.19015720
Page No. 311-321

Abstract View PDF Download Certificate
ARTIFICIAL INTELLIGENCE IN E-COMMERCE
Author: Harshit, Er. Disha Sharma, Tanuja Dobal & Yuvraj Tyagi

ABSTRACT
With the rapid progress of science, technology, and our economy, we see artificial intelligence (AI) being used more and more in colorful areas. It has a significant impact on our work and life. Artificial intelligence (AI) is a leading technology of the current age of the Fourth Industrial Revolution, with the capability of incorporating mortal intelligence and intelligence into machines or systems. In the field of e-commerce, AI is astronomically applied and has shown promising results. AI has surfaced as a pivotal driving force for the growth of e-commerce. The proposed paper will exfoliate light on how AI is being applied in E-commerce assistance and the impact of AI on E commerce doors. It examines the operation of AI in areas similar to AI sidekicks, image exploration, recommendation systems, and optimized pricing. This exploration explores how AI greatly affects and benefits the development of E-commerce. Artificial Intelligence (AI) has revolutionized different businesses, and one of its critical impacts has been within commerce. This paper investigates the operation of AI strategies in upgrading different shoes of e-commerce, counting customer hassles, personalization, suggestion fabrics, highway robbery discovery, stock administration, and force chain optimization. By using AI inventions similar to machine literacy, common shoptalk running, computer vision, and visionary analytics, e-commerce businesses can streamline operations, move forward with decision-making forms, and convey substantiated hassles to guests.

Index Terms— E-Commerce, Machine Learning, Artificial intelligence, Recommendation Systems, Fraud Detection,
chatbots, Online shopping

Paper Title ADAPTIVE THREAT DETECTION: LEVERAGING MACHINE LEARNING FOR REALTIME CYBERSECURITY
Author Name Sahil Sharma, Amit Kumar, Mayank Bansal & Azhar
Country India
DOI https://doi.org/10.5281/zenodo.19015902
Page No. 322-329

Abstract View PDF Download Certificate
ADAPTIVE THREAT DETECTION: LEVERAGING MACHINE LEARNING FOR REALTIME CYBERSECURITY
Author: Sahil Sharma, Amit Kumar, Mayank Bansal & Azhar

ABSTRACT
In the dynamically changing cyber security domain, conventional mechanisms for defense often prove inadequate against advanced threats that adapt themselves to counter defenses. This paper presents a new paradigm in building cyber security with the induction of machine learning algorithms into its design for enhanced threat detection and response in real time. In essence, the system keeps learning and, therefore, analyzes network traffic, user behaviors, and system anomalies regularly to identify threats when they are emerging. Our methodology includes supervised and unsupervised learning techniques for known threats and the unveiling of new attack patterns. The proposed system will evolve with new data and
be very potent against zero-day attacks and polymorphic malware. Further, feedback in the loop will help the system in refining the models built over time for better accuracy and reducing false positives. It will validate the effectiveness of this adaptive threat detection system by testing it at large in simulated environments, where it will way outperform the traditional methods in the identification and mitigation of a wide range of cyber threats. Results show how machine learning can actually transform cybersecurity to become proactive and dynamic about modern cyber defense challenges.

Index Terms—Machine Learning, Cybersecurity, Threat Detection, Real-Time Analysis, Adaptive Systems

Paper Title AI-DRIVEN IMAGE PROCESSING FOR KIDNEY STONE INFECTION DETECTION AND MANAGEMENT
Author Name Pragya Rajput, Yaismeenpreet Kaur, Neelanshi & Ashish
Country India
DOI https://doi.org/10.5281/zenodo.19015900
Page No. 330-346

Abstract View PDF Download Certificate
AI-DRIVEN IMAGE PROCESSING FOR KIDNEY STONE INFECTION DETECTION AND MANAGEMENT
Author: Pragya Rajput, Yaismeenpreet Kaur, Neelanshi & Ashish

ABSTRACT—
Kidney infections are a serious medical condition that can also cause serious complications if not diagnosed and treated in a timely manner. Conventional diagnostic techniques including ultrasound, computed tomography, and X-rays have constraints on precision, effectiveness and availability. Recent advances in Artificial Intelligence (AI) and image technology have changed the paradigms of medical diagnostics enabling the quick, accurate and automated analysis of images. This article explores image processing techniques focused on AI for the detection and management of renal
stone infections. It deals with a variety of visualization methods, automated learning approaches, and pre-processing methods that increase image quality and support in accurate diagnosis. This study also deals with detailed learning models, including convolutional neural networks (CNNs) to classify and predict the risk of renal renal infection. Additionally, it examines AI integration in a clinical setting and highlights challenges such as data confidentiality, model modeling, and regulatory considerations. The results suggest that AI-driven imaging processing may significantly improve early detection, reduce diagnostic errors, and optimize patient management. Future research includes real-time AI use, federal training, and assistants in kidney surgery for kidney treatment.

Paper Title VIRTUAL REALITY IN THERAPY AND MENTAL HEALTH
Author Name Pragya Rajput, Laksh Kapoor, Lavanya Saini & Ramit Chaturvedi
Country India
DOI https://doi.org/10.5281/zenodo.19016533
Page No. 347-355

Abstract View PDF Download Certificate
VIRTUAL REALITY IN THERAPY AND MENTAL HEALTH
Author: Pragya Rajput, Laksh Kapoor, Lavanya Saini & Ramit Chaturvedi

ABSTRACT
With the increase in mental health disorders, alternative approaches to treatment have become essential. This paper provides an overview of how VR technology has been integrated into the treatment of a wide spectrum of mental health problems, such as OCD, anxiety disorders, PTSD, and social anxiety disorder. It demonstrates, through a small number of different empirical studies and clinical trials, how good VR supports the improvement of traditional treatment modalities such as exposure therapy and CBT. The findings suggest that VR offers a good platform for therapeutic practices, improving patient outcomes significantly.

General Terms
Virtual Reality, Mental Health, Therapy, Human-Computer Interaction, Health Informatics, Clinical Psychology, Rehabilitation

Keywords
Virtual Reality Therapy, VR in Mental Health, Virtual Reality Exposure Therapy, Chronic Pain Management, Cognitive Behavioral Therapy, Immersive Environments, Kinesio phobia, Psychobehavioral Modulation, PTSD Treatment, Anxiety Disorders, Neuropsychological Mechanisms, Ethical Issues in VR Therapy

Paper Title AI-POWERED SECURE PASSWORD MANAGEMENT SYSTEM: ENHANCING DIGITAL SECURITY THROUGH AUTOMATION AND PROACTIVE ANALYSIS
Author Name Shubham Choudhary, Mukhtiar Singh, Keshav Sharma, Aditya Shrivastav, Vickey Shaw & Anil Kumar Yadav
Country India
DOI https://doi.org/10.5281/zenodo.19016731
Page No. 356-361

Abstract View PDF Download Certificate
AI-POWERED SECURE PASSWORD MANAGEMENT SYSTEM: ENHANCING DIGITAL SECURITY THROUGH AUTOMATION AND PROACTIVE ANALYSIS
Author: Shubham Choudhary, Mukhtiar Singh, Keshav Sharma, Aditya Shrivastav, Vickey Shaw & Anil Kumar Yadav

ABSTRACT
The need of secure password management has significantly increased in the contemporary digital era due to the growing frequency of cyberthreats and data breaches. This project presents a Secure Password Management System that enhances
the security, usability, and flexibility of password management through AI-based analysis. In order to assess password strength, identify weaknesses, and make real-time improvement suggestions, the system makes use of machine learning algorithms. Features like password creation, encryption-based safe storage, and periodic security audits are all included. The AI-powered analysis module identifies trends in user behaviour to lessen threats like phishing or brute force attacks, while anomaly detection ensures the early identification of suspicious activities. The technology also teaches users how to generate and maintain passwords through intelligent feedback systems.

Keywords:
Secure Password Management, AI-Powered Security, Password Strength Analysis, Password Creation Automation, Compromised Password Detection, Password Reuse Detection, Proactive Security Measures, Human Error in Password Management, Digital Authentication, Cybersecurity Automation, Password Security Compliance.

Paper Title REAL-TIME OBJECT DETECTION AND TRACKING USING YOLO AND OPENCV: A PYTHON-BASED APPROACH
Author Name Prateek Raj Srivastav, Raiyan Ahmad, Yuvraj Anand, Anchal Chauhan & Vanshika Jain
Country India
DOI https://doi.org/10.5281/zenodo.19016796
Page No. 362-368

Abstract View PDF Download Certificate
REAL-TIME OBJECT DETECTION AND TRACKING USING YOLO AND OPENCV: A PYTHON-BASED APPROACH
Author: Prateek Raj Srivastav, Raiyan Ahmad, Yuvraj Anand, Anchal Chauhan & Vanshika Jain

ABSTRACT—
Object detection and tracking are essential com- ponents of computer vision applications, from surveillance to autonomous systems. This paper introduces a real-time ob- ject detection and tracking system based on OpenCV, Python, and the
YOLO (You Only Look Once) algorithm. The sys- tem detects multiple objects in video streams efficiently and tracks their movement with high accuracy. Combining YOLO’s deep learning-driven detection with the tracking algorithms of OpenCV guarantees strong performance in challenging environ- ments. The system’s ability to deal with occlusions, lighting changes, and multiple object interactions is shown through experimental results. This work opens up the possibility for deep learning-based real-time vision applications and offers an extensible solution for automated monitoring and
inspection.

Index Terms—Object Detection, Tracking, YOLO, OpenCV, Python, Deep Learning, Computer Vision, Real- Time Processing, Autonomous Systems, Surveillance.

Paper Title REAL-TIME OBJECT DETECTION AND TRACKING USING YOLO AND OPENCV: A PYTHON-BASED APPROACH
Author Name Prateek Raj Srivastav, Raiyan Ahmad, Yuvraj Anand, Anchal Chauhan & Vanshika Jain
Country India
DOI https://doi.org/10.5281/zenodo.19016796
Page No. 362-368

Abstract View PDF Download Certificate
REAL-TIME OBJECT DETECTION AND TRACKING USING YOLO AND OPENCV: A PYTHON-BASED APPROACH
Author: Prateek Raj Srivastav, Raiyan Ahmad, Yuvraj Anand, Anchal Chauhan & Vanshika Jain

ABSTRACT—
Object detection and tracking are essential com- ponents of computer vision applications, from surveillance to autonomous systems. This paper introduces a real-time ob- ject detection and tracking system based on OpenCV, Python, and the
YOLO (You Only Look Once) algorithm. The sys- tem detects multiple objects in video streams efficiently and tracks their movement with high accuracy. Combining YOLO’s deep learning-driven detection with the tracking algorithms of OpenCV guarantees strong performance in challenging environ- ments. The system’s ability to deal with occlusions, lighting changes, and multiple object interactions is shown through experimental results. This work opens up the possibility for deep learning-based real-time vision applications and offers an extensible solution for automated monitoring and
inspection.

Index Terms—Object Detection, Tracking, YOLO, OpenCV, Python, Deep Learning, Computer Vision, Real- Time Processing, Autonomous Systems, Surveillance.

Paper Title A COMPREHENSIVE REVIEW ON AI IN HEALTHCARE USING MENTAL HEALTH THERAPIST CHAT-BOT
Author Name V. K. Barbudhe, Vijay. M. Rakhade, Kishan Patil, Shravani Jagtap, Suyash Marathe & Ankit Patil
Country India
DOI https://doi.org/10.5281/zenodo.19017363
Page No. 369-375

Abstract View PDF Download Certificate
A COMPREHENSIVE REVIEW ON AI IN HEALTHCARE USING MENTAL HEALTH THERAPIST CHAT-BOT
Author: V. K. Barbudhe, Vijay. M. Rakhade, Kishan Patil, Shravani Jagtap, Suyash Marathe & Ankit Patil

ABSTRACT
Since 2022, chatbots with artificial intelligence have been more popular. They provide all possible outcomes for algorithms used in Natural Language Processing (NLP) and Machine Learning. It would be appreciated if the underlying capacity expansion, productivity improvement, and provision of guidance and help in colorful areas were carried out. The idea behind mortal artificial intelligence (HAI) is to facilitate the fusion of artificial and mortal intelligence. We will implement several adjustments that relate to the value of empathy and ethical consideration, which increase the efficacy of AI
chatbots, in order to solve their limits. Global health is significantly impacted by mental health, which is a global concern. AI and ML are used to link data analytics to mental health outcomes. to minimize hidden dangers and optimize their benefits. collaborative strategies and cutting-edge. In addition to reducing impulses in AI operations, educational and practical outcomes may improve responsible usage and increase the effectiveness of cognitive and computational training programs. For all providers of digital internal health, digital internal health means operating more efficiently and
inclusively.

Keywords
Artificial intelligence, Mental health chatbot, Generative-AI Chatbot, Natural language processing, Machine learning, Deep learning.

Paper Title REAL-TIME ENERGY OPTIMIZATION IN DATA CENTERS: A BIG DATADRIVEN APPROACH FOR EFFICIENT RESOURCE MANAGEMENT
Author Name Sujit Kumar Panda, Siddharth Shivam Singh, Kshitij Jain & Anupam Sharma
Country India
DOI https://doi.org/10.5281/zenodo.19017522
Page No. 376-383

Abstract View PDF Download Certificate
REAL-TIME ENERGY OPTIMIZATION IN DATA CENTERS: A BIG DATADRIVEN APPROACH FOR EFFICIENT RESOURCE MANAGEMENT
Author: Sujit Kumar Panda, Siddharth Shivam Singh, Kshitij Jain & Anupam Sharma

ABSTRACT—
The high proliferation of data centers and their energy consumption have also picked up over the years, creating an environment that demands efficient energy management. Within this context, the present study suggests a real-time energy optimization framework, applying big data analytics to enhance data center energy efficiency. It is intended to dynamically distribute workload and optimally allocate available resources, given the integration of machine learning algorithms, predictive analytics, and a monitoring system. This research uses data-driven techniques, including load balancing, thermal- aware scheduling, and predictive cooling strategies, to reduce energy wastage without sacrificing performance reliability. The incorporation of real-time monitoring and intelligent automation enables it to be adaptable to the variability of workload and environmental conditions. Results include significant reductions in power consumption, effective carbon footprint management, and sustainable operation. This proposed model may serve as a foundation for future next-generation energy-efficient data centers.

Index Terms—Real-time energy optimization, big data ana- lytics, machine learning, predictive analytics, workload manage- ment, data center efficiency, thermal-aware scheduling, intelligent automation, predictive cooling, sustainability.

Paper Title FROM DATA TO DISCOVERY: THE ROLE OF MACHINE LEARNING IN PERSONALIZED EDUCATION
Author Name Parkhi Acchreja, Adith M.R., Abhay Kejriwal, Narinder Yadav & Akarshan Jangid
Country India
DOI https://doi.org/10.5281/zenodo.19017804
Page No. 384-393

Abstract View PDF Download Certificate
FROM DATA TO DISCOVERY: THE ROLE OF MACHINE LEARNING IN PERSONALIZED EDUCATION
Author: Parkhi Acchreja, Adith M.R., Abhay Kejriwal, Narinder Yadav & Akarshan Jangid

ABSTRACT
Self-education undergoes a transformation through Machine Learning because it supports teachers to build and enhance customized educational activities which align with student-specific needs. Through analysis of student interaction data ML discovers methods which boost student commitment together with comprehension and educational success outcomes. The implementation of adaptive learning systems and predictive analytics for intervention and automated feedback and material recommendations represent some key instances of ML usage. The educational benefits of ML remain challenging by three main factors: privacy concerns along with discriminatory practices and difficulties scaling algorithmic capabilities. The responsible application of AI systems must remain a priority because improper ethical choices and irregular fair learning implementation need to be prevented. A document investigates how ML works in education by analyzing its benefits and barriers as well as potential solutions for ethical AI implementation in educational systems. This research examines how ML powers personalized education while studying its advantages and obstacles together with expected trends while stressing the requirement of ethical implementation and continuous technological advancement in education systems that leverage artificial intelligence.

General Terms
Algorithms, artificial intelligence, human factors, security, performance, design, experiment.

Keywords
Personalized learning and machine learning, adaptive education, intelligent tutoring, data privacy, AI in education, reinforcement learning, federated learning.

Paper Title ADVANCEMENTS & CHALLENGES IN MILLIMETER-WAVE OFDM-MDM ROFSO COMMUNICATION
Author Name Muskandeep Kaur, Harminder Kaur & Chahat Jain
Country India
DOI https://doi.org/10.5281/zenodo.19018029
Page No. 401-411

Abstract View PDF Download Certificate
ADVANCEMENTS & CHALLENGES IN MILLIMETER-WAVE OFDM-MDM ROFSO COMMUNICATION
Author: Muskandeep Kaur, Harminder Kaur & Chahat Jain

ABSTRACT
This review paper analyzes the combination of RoFSO technology and MMW hybrid OFDM-MDM communication system for 5G networks. The study reviews essential developments, challenges, and opportunities in the field. The performance of recent technologies, computation optimization approaches, and different weather conditions that affect transmission performance are evaluated. The review studies the importance of adaptive signal processing techniques, link reliability, and spectral efficiency. In addition, the study advocates concentrate on Multi-channel RoFSO architectures and improvements using artificial intelligence in the future.

Keywords: OFDM, MDM, RoFSO, 5G Networks, Millimeter-Wave

Paper Title FORTIFIED STREAMING (ENHANCED SECURITY AND ROBUSTNESS)
Author Name Sudhanshu Gairola, Yadwinder Singh & Anita Rani
Country India
DOI https://doi.org/10.5281/zenodo.19018071
Page No. 412-421

Abstract View PDF Download Certificate
FORTIFIED STREAMING (ENHANCED SECURITY AND ROBUSTNESS)
Author: Sudhanshu Gairola, Yadwinder Singh & Anita Rani

BSTRACT
Adaptive streaming technologies, such as HLS and DASH, have revolutionized video delivery, enabling seamless playback across diverse network conditions. However, the inherent open nature of these protocols poses significant security challenges, including
unauthorized content access, redistribution, and download. This paper presents a comprehensive security framework for adaptive streaming, integrating Digital Rights Management (DRM), signed source URLs, and video player key IDs to mitigate these
vulnerabilities. We explore the implementation of robust DRM solutions to encrypt and control content usage, ensuring only authorized playback. Furthermore, we leverage signed source URLs to restrict access to content segments, preventing unauthorized downloads and sharing. To enhance user-specific access control, we propose the utilization of video player key IDs, uniquely identifying client applications and preventing playback in unauthorized environments or third-party players. This mechanism effectively restricts content access to designated platforms, minimizing the risk of piracy. The proposed framework is evaluated through practical implementation and performance analysis, demonstrating its efficacy in securing adaptive streaming content while maintaining a seamless user experience. Our findings contribute to the advancement of secure video delivery solutions, addressing critical security concerns in the evolving landscape of online streaming.

Paper Title AI PORTFOLIO RECOMMENDATION AND ALLOCATION
Author Name Mayuri Kanik, Tushar Vaishya, Aditya Kamble, Harshdeep Gorade & Krishna Pandey
Country India
DOI https://doi.org/10.5281/zenodo.19018146
Page No. 422-431

Abstract View PDF Download Certificate
AI PORTFOLIO RECOMMENDATION AND ALLOCATION
Author: Mayuri Kanik, Tushar Vaishya, Aditya Kamble, Harshdeep Gorade & Krishna Pandey

ABSTRACT
The "AI portfolio recommendation and allocation system" is a cutting-edge technological innovation designed to revolutionize investment management by addressing the complexities of modern financial markets. This project aims to develop a dynamic system that leverages advanced machine learning techniques to optimize
portfolio allocations and provide personalized investment recommendations. By integrating diverse data sources, real-time analysis, and robust risk assessment, the system ensures improved decision-making, adaptability to market changes, and enhanced user satisfaction. It strives to democratize access to sophisticated investment strategies for both novice and seasoned investors.

Keywords AI-Driven Systems, Portfolio Management, Machine Learning, Risk Assessment, Investment Strategies.

Paper Title COMPARATIVE ANALYSIS BASED ON VARIOUS PERFORMANCES FOR OPTIMIZING QUALITY OF SERVICES IN IoMT
Author Name Dinesh Anand, Avinash Kaur & Parminder Singh
Country India
DOI https://doi.org/10.5281/zenodo.19018234
Page No. 432-443

Abstract View PDF Download Certificate
COMPARATIVE ANALYSIS BASED ON VARIOUS PERFORMANCES FOR OPTIMIZING QUALITY OF SERVICES IN IoMT
Author: Dinesh Anand, Avinash Kaur & Parminder Singh

ABSTRACT
The swift progress of IoMT and related technologies has transformed healthcare by enabling real-time data collection, monitoring, and analysis through medical sensors, wearable devices, and IoT-driven applications. However, these innovations have led to obstacles associated with data processing and transmission, particularly in traditional cloud computing models due to latency, bandwidth constraints, and security concerns. Fog computing extends cloud capabilities closer to the edge prototype, addresses these challenges by activating live data processing, reducing latency, and enhancing
security and scalability. This paper explores the Incorporation of IoMT with fog computing and evaluates various optimization techniques aimed at improving the Quality of Service (QoS) in healthcare applications. A comparative analysis of performance metrics, including reliability, latency, energy efficiency, and security, is conducted across different devices, communication protocols, and network configurations. The paper also highlights key contributions, such as the development of secure load balancing techniques, the use of Federated Learning for privacy-preserving data analysis, and the application of multipopulational genetic algorithms for adaptive QoS-aware service composition. While promising, several challenges remain in ensuring data privacy and real-time processing in critical healthcare environments. This
research provides recommendations for optimizing QoS in IoMT applications, ensuring better healthcare outcomes, and
proposes a framework for future IoMT deployment that incorporates emerging technologies like AI, edge computing, and
blockchain.
Keywords—IoMT, QoS, Fog Computing, Task Completion Time, Reliability, Energy Consumption, Response Time.

Paper Title SMART WI-FI-ENABLED TRASH BIN: REVOLUTIONIZING WASTE MANAGEMENT WITH AI-POWERED SORTING, IOT MONITORING
Author Name Abhsihek Yadav, Ashish Sharma & Rinku Sharma
Country India
DOI https://doi.org/10.5281/zenodo.19050538
Page No. 444-454

Abstract View PDF Download Certificate
SMART WI-FI-ENABLED TRASH BIN: REVOLUTIONIZING WASTE MANAGEMENT WITH AI-POWERED SORTING, IOT MONITORING
Author: Abhsihek Yadav, Ashish Sharma & Rinku Sharma

ABSTRACT
This idea is proposed as a Wi-Fi enabled smart trash bin to change the way of waste management in India especially in the areas inhabited by wildlife and high tourist traffic. The system is designed to promote the correct disposal of waste by offering free Wi-Fi connection to the users after entering a one time password (OTP) while the device is equipped with IoT sensors and AI driven waste classification (YOLOv8) as well as real time connectivity. In the wildlife zones the bins are made animal proof, the units are solar powered for off grid sustainability and the units have multilingual LED displays for tourists. The waste is sorted into recyclables and non recyclables and the fill level information is sent to the authorities through the IoT for on time collection. This solution is in conformity with the Swachh Bharat Abhiyan and incorporates digital rewards (behavioral nudges), environmental protection (reduced litter in forests) as well as smart city goals (effective waste management). The revenue model is scalable and consists of advertisement displays and government partnerships to ensure it is a low cost, tech based solution to India’s urbanization and ecological issues.

Keywords— WiFi-Trash Bin , YOLOv8 , Reward, IoT

Paper Title SECURE NETWORK ACCESS CONTROL USING BLOCKCHAIN TECHNOLOGY
Author Name Pranav Aggarwal, Azhar, Harshit Gupta & Sanjana Arora
Country India
DOI https://doi.org/10.5281/zenodo.19050696
Page No. 455-462

Abstract View PDF Download Certificate
SECURE NETWORK ACCESS CONTROL USING BLOCKCHAIN TECHNOLOGY
Author: Pranav Aggarwal, Azhar, Harshit Gupta & Sanjana Arora

I. ABSTRACT
The rapid advancement of digital technologies in many areas has made establishing secure network access control a matter of high priority, especially in decentralized systems. Traditional access control systems are likely to be plagued by problems like points of single failure, scalability, and susceptibility to cyber attacks. By using decentralization, immutability, and cryptographic techniques, blockchain technology offers an end-toend security paradigm. This paper addresses network access control with blockchain technology, with a focus on decentralized authentication, identity verification, and access control. It explains some blockchain-based models like role-based access control (RBAC), decentralized identifiers (DIDs), and smart contracts. The paper also considers relevant challenges like scalability, compliance with regulatory needs, energy efficiency, and interoperability, and suggests likely solutions. The work further suggests a novel framework for access control based on blockchain, with a mathematical model and assesses performance using simula- tion analyses.
Blockchain, Access Control, Smart Contracts, AI-driven Security, IoT Security, Decentralization, Cybersecurity, Quantum Security, Zero-Knowledge Proofs, Edge Computing.

Paper Title DETECTING DECEPTION: AN APPROACH TO DETECTING FAKE NEWS USING DISTIL-BERT
Author Name Avinash Bhat & Sangeetha J
Country India
DOI https://doi.org/10.5281/zenodo.19050823
Page No. 463-470

Abstract View PDF Download Certificate
DETECTING DECEPTION: AN APPROACH TO DETECTING FAKE NEWS USING DISTIL-BERT
Author: Avinash Bhat & Sangeetha J

ABSTRACT
The integrity of information and the public's confidence are under serious attack due to the dissemination of false news on social media. Leveraging transformer-based language models more specifically, the Distil BERTbase- uncased and RoBERTa-base models. this study provides a dependable and efficient approach for identifying fake news. The light structures of these models as well. the ability to retain important contextual information render them suitable for high-performance text classification tasks. To manage the complexity of detecting false news, training and testing were done on large datasets incorporating various types of news content, user interaction, and location information. RoBERTa achieved a competitive performance with an accuracy of 89% and an F1 score of 92%, while Distil BERT attained an accuracy of 86% and an F1 score of 91%. In terms of efficiency and computational cost, both models surpassed traditional machine learning methods. Also, the incorporation of extra social environment features which were inspired by advances in the discipline—was needed to maximize model predictions These findings contribute to the growing body of research indicating that massive pre-trained language models can be used to combat disinformation. For further enhance detection abilities on social media platforms, future studies might explore real time optimization techniques and multi-class classification situations.

Keywords— Fake News Detection, RoBERTa, Distil BERT- base-uncased, Natural Language Processing, Transformer Models, Text Classification, Social Media Misinformation, Machine Learning, F1 Score, Accuracy, Binary Classification

Paper Title A HYBRID METHOD FOR POTHOLE DEPTH ESTIMATION: COMBINING LIDAR WITH POINT CLOUD
Author Name Sparsh Verma, Shashank Kumar, Ayush Jindal & Sandeep Kumar
Country India
DOI https://doi.org/10.5281/zenodo.19063123
Page No. 471-480

Abstract View PDF Download Certificate
A HYBRID METHOD FOR POTHOLE DEPTH ESTIMATION: COMBINING LIDAR WITH POINT CLOUD
Author: Sparsh Verma, Shashank Kumar, Ayush Jindal & Sandeep Kumar

ABSTRACT
This study presents an automated approach for detecting potholes and estimating their depth using LiDAR point cloud data. The methodology involves pre-processing raw LiDAR data, segmenting the road surface, clustering pothole regions, and calculating their
dimensions. The proposed system utilizes DBSCAN clustering and convex hull techniques to accurately identify and measure potholes. The methodology involves collecting 3D point cloud data from LiDAR sensors, specifically from .las files, to ensure accurate surface reconstruction. The pre-processing stage applies voxel down sampling, statistical noise removal, and plane segmentation using RANSAC to differentiate road surfaces from potholes. Henceforth, an algorithm called DBSCAN is then employed that identifies the regions in which the potholes are present. Then an unambiguous extraction of pothole dimensions is done using the convex hull estimation. This methodology not only provides an accurate measurement of the pothole depth but also aids in real-time view of the potholes, which is important for the maintenance of roads and ensuring road safety.

General Terms
Algorithms, Measurement, Computer Vision, Data Processing, Remote Sensing

Keywords
Computer Vision, DBSCAN clustering, LiDAR, Point Cloud, Potholes, RANSAC

Paper Title AI-ENHANCED DEPRESSION DETECTION IN SOCIAL MEDIA
Author Name Pragya Rajput, Pradeep Kumar Reddy Chereddy, Vaishnavi Yampalla, Sai Sreekar Devoju, Keshav & Vinay Raparthi
Country India
DOI https://doi.org/10.5281/zenodo.19063217
Page No. 481-488

Abstract View PDF Download Certificate
AI-ENHANCED DEPRESSION DETECTION IN SOCIAL MEDIA
Author: Pragya Rajput, Pradeep Kumar Reddy Chereddy, Vaishnavi Yampalla, Sai Sreekar Devoju, Keshav & Vinay Raparthi

ABSTRACT –
The widespread use of social media platforms has provided new avenues for understanding and taking action on mental health, with a focus on depression on a person’s level of state. Over the past few years, researchers and mental health care professionals have increasingly leveraged artificial intelligence (AI) and natural language processing (NLP) techniques to build automated systems that can detect signals of depression among social media users. In this paper, we provide a detailed overview of the existing state-of-the-art methods in AI-based depression detection using a range of techniques: linguistic, sentiment analysis, and machine learning methods. We critique existing approaches with attention to their strengths and weaknesses and touch on the ethical implications of automated depression detection systems. In addition, we discuss future research directions for improving the accuracy and reliability as well as the ethical aspect of AI-based depression detection on social
media platforms with particular emphasis on privacy protection and handling algorithmic bias in AI algorithms. We research the topic to advance our understanding of the ways in which artificial intelligence(AI) may be used to support and help in mental health on the internet.

Index Terms — Depression, Social Media, Artificial Intelligence, Natural Language Processing.

Paper Title STATISTICAL METHOD TO IMPROVE PERFORMANCE PARAMETER IN PRECISION AGRICULTURE USING TRANSFER LEARNING
Author Name Raviprakash Shriwas & Alok Kumar
Country India
DOI https://doi.org/10.5281/zenodo.19063318
Page No. 489-496

Abstract View PDF Download Certificate
STATISTICAL METHOD TO IMPROVE PERFORMANCE PARAMETER IN PRECISION AGRICULTURE USING TRANSFER LEARNING
Author: Raviprakash Shriwas & Alok Kumar

ABSTRACT
Monitoring leaf diseases is one of the significant challenges to global crop production and food security, particularly early monitoring, which is vital for managing leaf diseases. In this research, we propose LeafDocNet, a thin and high-performing transfer learning-based model for leaf disease identification across different plant species with a few training samples. We employ statistical optimisation approaches to improve the
performance of two well-known deep learning architectures, DenseNet121 and MobileNetV2. Specifically, we propose an attention-based transition and global average pooling layers in DenseNet121, a further attention module, and four pooling layers after each convolutional layer in MobileNetV2. Batch normalisation, Swish activation, and dropout regularisation are also included to reduce overfitting and improve the robustness and generalisation of the model. The proposed approach is verified with cassava and wheat leaf disease datasets, outperforming existing techniques on key performance metrics such as accuracy, precision-recall, and AUC. Lastly, we use Grad-CAM++ to visualize and interpret model decisions to verify reliable and transparent
disease classification. Combining statistical techniques with transfer learning significantly improves model efficiency, making it a valuable practice for precision agriculture and plant disease monitoring.

Keywords
Leaf Disease Detection, Deep Learning, Transfer Learning, Precision Agriculture, Grad-CAM++

Paper Title BLOCKCHAIN-BASED AUDIT TRAILS FOR CLOUD STORAGE SYSTEMS
Author Name Manas Mayank, Sarthak & Munish Kumar
Country India
DOI https://doi.org/10.5281/zenodo.19063379
Page No. 497-508

Abstract View PDF Download Certificate
BLOCKCHAIN-BASED AUDIT TRAILS FOR CLOUD STORAGE SYSTEMS
Author: Manas Mayank, Sarthak & Munish Kumar

ABSTRACT—
With increasing use of cloud storage, ensuring data security, openness, and integrity has become ever more critical. Centralization, potential tampering, and lack of transparency are typical issues with conventional audit trails employed to monitor data access and changes in cloud computing environments. To enhance cloud storage security and reliability, this article explores a blockchain-based audit trail system. The proposed approach ensures tamper-proof logging of all data transactions through the immutability, cryptographic hashing, and decentralized prop- erties of blockchain technology. Additionally, smart contracts reduce third-party trust requirements through automated and verifiable auditing. We measure the scalability, performance, and architecture of the system compared to more traditional approaches to auditing. The findings indicate that, although there are some disadvantages such as scalability and cost of transac- tions, an audit trail in blockchain enhances the integrity and reliability of data within cloud storage. To make it more efficient, subsequent research will explore optimization techniques such as Layer-2 solutions and zero-knowledge proofs.

Index Terms—Distributed Ledger Technology (DLT), blockchain, cloud storage, audit trail, data integrity, smart contracts, decentralized security, cryptographic hashing, transparency, and tamper-proof logging.

Paper Title THE EVOLUTION OF DATA VISUALIZATION: STATIC REPORTS TO REAL-TIME SYSTEMS
Author Name Abhishek Roushan, Sushil Kumar Garg, Vatsala Singh, Anvi, Tanvi Kanwar & Muskan Devi
Country India
DOI https://doi.org/10.5281/zenodo.19063493
Page No. 509-521

Abstract View PDF Download Certificate
THE EVOLUTION OF DATA VISUALIZATION: STATIC REPORTS TO REAL-TIME SYSTEMS
Author: Abhishek Roushan, Sushil Kumar Garg, Vatsala Singh, Anvi, Tanvi Kanwar & Muskan Devi

ABSTRACT
Real-time data visualization dashboards are at the forefront of modern decision making since they provide dynamic and interactive visual representation of data. These dashboards allow users to monitor key indicators, identify trends, and make data-driven decisions from real-time insights. In this paper, we present the design and implementation of a successful real-time data visualization dashboard that collects data from multiple sources, processes it dynamically, and presents it in simpleto-interpret visual forms such as charts, graphs, and heatmaps. We discuss some of the technologies and frameworks used for real-time data processing, including Web Sockets, stream processing, and cloud-based analytics. In addition, we address challenges in real-time data visualization such as latency, scalability, and achieving optimal user experience. The study presents best practices for the development of dashboards that are more usable, performance-effective, and able to serve a wide range of applications ranging from business intelligence to industrial automation. Outcomes of this paper contribute towards developing robust, user-centric visualization tools that strengthen decision-making processes in real-time environments.

Keywords- Real-time visualization, Data dashboard, Interactive analytics, Streaming data, Data processing, Webbased visualization, Business intelligence, Industrial monitoring.

Paper Title DEEP LEARNING-BASED SMART WASTE MANAGEMENT SYSTEM FOR AUTOMATED PROBLEM IDENTIFICATION AND RESOLUTION
Author Name Murali D, P Mohammed Sulaiman, Y Prudhvi Raj, S Obulesu & G Lokesh
Country India
DOI https://doi.org/10.5281/zenodo.19063657
Page No. 522-528

Abstract View PDF Download Certificate
DEEP LEARNING-BASED SMART WASTE MANAGEMENT SYSTEM FOR AUTOMATED PROBLEM IDENTIFICATION AND RESOLUTION
Author: Murali D, P Mohammed Sulaiman, Y Prudhvi Raj, S Obulesu & G Lokesh

ABSTRACT —
Maintaining urban cleanliness and optimizing waste management are critical for sustainable city development. Traditional waste management systems rely on manual reporting, which often results in inefficiencies, delayed response times, and unorganized waste disposal. These limitations contribute to environmental degradation, public health risks, and ineffective resource utilization. To address these challenges, this paper presents an advanced, real- time waste management system that leverages Bootstrapped Language-Image Pre-training (BLIP) alongside modern web technologies to enhance automation in waste detection and reporting. The proposed system allows users to capture and upload images of waste accumulation in public areas. These images are processed using a fine-tuned BLIP-2 deep learning model, which automatically generates detailed textual descriptions of the waste conditions. This AI- powered description is then used to notify municipal authorities, enabling them to take timely action. Unlike traditional manual approaches, the system provides accurate and real-time waste monitoring, reducing delays in waste collection and improving urban cleanliness. To ensure seamless operation, the system incorporates live location
tracking, allowing authorities to pinpoint the exact site of waste accumulation. The web-based interface is developed using Angular for the frontend and ASP.NET for backend processing, ensuring a responsive and scalable architecture. By integrating deep learning and modern web technologies, this system introduces a structured and automated approach to waste management, improving efficiency, reducing environmental hazards, and promoting a cleaner urban environment. This paper discusses the system’s design, implementation, and impact, demonstrating its potential to revolutionize waste management strategies in smart cities.

Keywords— Machine Learning, Reverse Geocoding API, Deep Learning, BLIP-based model.

Paper Title COLLABORATIVE PROBLEM-SOLVING IN GAME DESIGN: EXPLORING EPISTEMIC STANCE, AFFECT, AND ENGAGEMENT
Author Name Seema Kharod, Himanshu Gera, Kshitij Vats, Aryan Bassi, Akashat Srivastava & Sidharth Aggarwal
Country India
DOI https://doi.org/10.5281/zenodo.19064212
Page No. 529-537

Abstract View PDF Download Certificate
COLLABORATIVE PROBLEM-SOLVING IN GAME DESIGN: EXPLORING EPISTEMIC STANCE, AFFECT, AND ENGAGEMENT
Author: Seema Kharod, Himanshu Gera, Kshitij Vats, Aryan Bassi, Akashat Srivastava & Sidharth Aggarwal

ABSTRACT
Collaborative game design consists of intricate problem- solving activities wherein participants engage with epis- temic stances, affective dynamics, and engagement strategies. The present research examines how designers collaborate to build knowledge, manage emotions, and maintain engagement in the game development process. Through a study of team interactions, design iterations, and decision-making schemes, we examine important factors that facilitate or impair effective collaboration. Our results shed light on optimizing collaborative work in game creation, creativity building, and optimizing problem-solving effectiveness. The research adds to the overall knowledge of collaborative design process practices, highlighting the influence of
cognitive and emotional involvement on creative game development outputs.

Index Terms—Collaborative game design, problem-solving, epistemic stance, affect, engagement, teamwork, creativity, game development, design iteration, cognitive engagement, emotional regulation.

Paper Title CATTLE DISEASE PREDICTION AND PREVENTION USING A DEEP LEARNING MODEL
Author Name Adarsh, Shraddha S Prabhu, Pradeesha P Suvarna, Masooda & Udaya Kiran
Country India
DOI https://doi.org/10.5281/zenodo.19064318
Page No. 538-544

Abstract View PDF Download Certificate
CATTLE DISEASE PREDICTION AND PREVENTION USING A DEEP LEARNING MODEL
Author: Adarsh, Shraddha S Prabhu, Pradeesha P Suvarna, Masooda & Udaya Kiran

ABSTRACT
Cattle diseases can significantly affect livestock health and farm productivity. To help tackle this issue, we have created an AI-powered system that uses deep learning to predict diseases from images. With a simple and userfriendly React interface, farmers and veterinarians can upload photos of cattle for analysis. Our system leverages a trained Convolutional Neural Network (CNN) to examine the images and detect potential illnesses. The predictions are processed in real-time through a Node.js backend, enabling early diagnosis and faster response. To make the solution more accessible, we provide remedies in English and regional languages, allowing farmers to understand and apply treatments easily. By reducing reliance on manual inspections, this technology improves efficiency and ensures better livestock care. In our testing, the model achieved an accuracy of 89%, demonstrating its potential to lower cattle mortality rates and enhance overall farm productivity.

Keywords
Cattle disease detection, Machine learning, Deep learning, Image-based analysis, React, Node.js

Paper Title SUPPORT THROUGH INTEGRATED ANDROID APP AND WEB PORTALS FOR LIFELINE SERVICES
Author Name Harmanpreet Singh, Sumit Bhandar, Azhar Ashraf Gadoo & Ayush Gupta
Country India
DOI https://doi.org/10.5281/zenodo.19064469
Page No. 545-554

Abstract View PDF Download Certificate
SUPPORT THROUGH INTEGRATED ANDROID APP AND WEB PORTALS FOR LIFELINE SERVICES
Author: Harmanpreet Singh, Sumit Bhandar, Azhar Ashraf Gadoo & Ayush Gupta

ABSTRACT
In the digital age, it is important to enable access to critical lifesaving services, including health care, emergency assistance, financial assistance, and government services which are essential to community wellbeing. This research looks at an integrated model utilizing an Android application, accompanied by web portals, that that behaves as a single, easy to use access point for the provision of these services. The suggested model
employs a system of cloud computing, Artificial Intelligence to make service recommendations, and real-time data syncing, as part of the streamlined experience for both the user and service provider experience. The Android application allows for a mobile first experience, enabling the user to access and order service remotely,
while the web portal extends the users experience and allows for the service provider’s administrative uses. The functions of the model include secure log-in user authentication, geolocation service recommendations, bot-assisted navigation, and multi-language support for a diverse user population. The research also considers
the technical architecture, security aspects of to ensure scalability and reliability, and usability of said application. This integrated platform aims to address the digital divide, service delivery efficiency, and engagement with users and providers of lifesaving services. The research will report on empirical analysis and case studies that present impact and effectiveness of the model. Further impact and effectiveness can be
investigated for continued critical service access in both urban and rural spreading areas.

Index Terms—Integrated Services, Android Application, Web Portals, Lifeline Services, Emergency Response, Cloud Comput- ing, Artificial Intelligence, Service Accessibility, Digital Inclusion, Real-Time Data Synchronization, Mobile Technology

Paper Title EARLY DETECTION OF PLANT DISEASES USING DEEP LEARNING AND ADVANCED IMAGING TECHNIQUES
Author Name Satyaprakash Jena, Dhruv Gandhi, Amit Kumar Jaiswal & Harsh Khatri
Country India
DOI https://doi.org/10.5281/zenodo.19064623
Page No. 555-564

Abstract View PDF Download Certificate
EARLY DETECTION OF PLANT DISEASES USING DEEP LEARNING AND ADVANCED IMAGING TECHNIQUES
Author: Satyaprakash Jena, Dhruv Gandhi, Amit Kumar Jaiswal & Harsh Khatri

ABSTRACT
Plants are at the center of where an economy is situated, the agric sector, and that of any nation's ecosystem. Look after your health to ensure it does not fall prey to many diseases caused by viruses, bacteria, and fungi. It entails due treatment, with detection of the same, and therefore must be conducted in such a manner as to put an end to irreplaceable damage to crops. Over the last few years, there has been spectacular progress in object discovery and image detection during deep network learning. Grounding on this, our research work aims to use pre-trained convolutional neural networks such as AlexNet, VGG16 and VGG19 via transfer learning for effective detection of plant disease. To facilitate improved model performance, we pre-process the images to improve the quality of the images and boost accuracy. Having trained the models, we tested them thoroughly to affirm the results. We are using the Plantvillage data set here, in which we have both a healthy leaf and a disease leaf. We split 80% of the training data and hold out 20% for the test. Along with accuracy, we also calculate accuracy, memory, and score F1 to check the models in general. The result confirmed that Alexnet achieved the outstanding test accuracy of more than 96.63%, which outperformed VGG16 (95.05%) and VGG19 (95.22%). Alexnet also achieved outstanding performance in other measurements at 92% precision, 91% memory and 91% F1 score. The above result confirms the efficiency of the AlexNet model trained to classify plant diseases with outstanding accuracy and efficiency. The aim of this work is the implementation of novel technology such as deep learning for crop protection to assist in achieving sustainable agriculture and economic development. Auto-detection of disease will help farmers act instantaneously to save crops, avoid loss and minimize the excessive use of chemical medication.

Index Terms – Deep Learning, Histogram equalization, RELU, Pooling, Fully Connected

Paper Title INTELLIGENT NANOSENSORS FOR REAL-TIME HEALTH MONITORING AND ADAPTIVE THERAPY USING AI
Author Name Shruti Sharma
Country India
DOI https://doi.org/10.5281/zenodo.19064819
Page No. 565-572

Abstract View PDF Download Certificate
INTELLIGENT NANOSENSORS FOR REAL-TIME HEALTH MONITORING AND ADAPTIVE THERAPY USING AI
Author: Shruti Sharma

ABSTRACT
The union of artificial intelligence (AI) and nan- otechnology is transforming contemporary healthcare by allowingreal-time, accurate, and individualized therapeutic interventions. AI-enhanced nanoscale sensors can track physiological parame- ters at the molecular level, offering real-time data that facilitates dynamic treatment decisions. This paper discusses the design and integration of AI-based nanosensors in medical implants and wearable systems with a focus on their application in adaptive therapeutic responses. Applications to chronic disease manage- ment, early detection, and telemedicine-based remote health monitoring are explored, in addition to challenges involving data protection, energy consumption, and regulatory environments. By utilizing machine learning, predictive analysis, and real-time feedback mechanisms, AI-enabled nanosensors have the ability to revolutionize patient care as a more anticipatory and reactive process.

Index Terms—Artificial intelligence, nanoscale sensors, medi- cal implants, real-time health monitoring, adaptive therapeutic responses, machine learning, data analytics, precision medicine, personalized care, implantable devices.

Paper Title WEB APPLICATION FOR SECURE CONTRACT MANAGEMENT USING SMART CONTRACTS
Author Name Rakshit Mahajan, Er. Seema Kharod, Ankit Kumar Malik, Shive Prakash, Bharti Attri & Parvesh Saini
Country India
DOI https://doi.org/10.5281/zenodo.19064915
Page No. 573-581

Abstract View PDF Download Certificate
WEB APPLICATION FOR SECURE CONTRACT MANAGEMENT USING SMART CONTRACTS
Author: Rakshit Mahajan, Er. Seema Kharod, Ankit Kumar Malik, Shive Prakash, Bharti Attri & Parvesh Saini

ABSTRACT
The next generation of contract management systems faces challenges related to security, transparency, andautomation. Traditional centralized contract platforms are prone to data tampering, unauthorized access, and inefficiencies in execution. By guaranteeing immutability, decentralized execution, and trust less agreements, a
blockchain-based smart contract system can get around these restrictions. A Web3-enabled contract management system that uses Ethereum/Polygon smart contracts for safe, automated, and transparent contract execution is presented in this paper. To improve security and dependability, the platform incorporates IPFS-based decentralized storage, role-based access management, and multi- factor authentication (MFA). Furthermore, an Escrow smart contract mechanism ensures secure financial transactions, releasing funds only upon contract fulfilment. To optimize user experience and efficiency, the system employs a React.js frontend with Web3 authentication and an Express.js API for blockchain interactions. Security enhancements such as Focal Loss for anomaly detection in contract activities, Enhanced IoU (EIoU) for transaction validation, and Coordinate Attention (CA) for fraud prevention are incorporated. Experimental results indicate that this decentralized contract management solution achieves higher security, transparency, and automation, outperforming traditional
centralized platforms while maintaining scalability and efficiency.

Keywords— Web3 Authentication, Escrow Mechanism, Blockchain, Ethereum, Polygon, Decentralized Execution, Role-Based Access Control (RBAC), IPFS Storage, React.js, Express.js, Multi- Factor Authentication (MFA), Anomaly Detection, Focal Loss, Enhanced IoU (EIoU).

Paper Title AI-AUGMENTED THREAT HUNTING FOR ZERO-DAY ATTACKS
Author Name Pradyumn Pratap Singh, Anant Bhardwaj, Astha Bharti, Kumar Sanu, Aisheek Mazumder & Azhar Ashraf Gadoo
Country India
DOI https://doi.org/10.5281/zenodo.19065012
Page No. 582-590

Abstract View PDF Download Certificate
AI-AUGMENTED THREAT HUNTING FOR ZERO-DAY ATTACKS
Author: Pradyumn Pratap Singh, Anant Bhardwaj, Astha Bharti, Kumar Sanu, Aisheek Mazumder & Azhar Ashraf Gadoo

ABSTRACT
Zero-day attacks pose a significant challenge to cybersecurity due to their unpredictable nature and lack of existing signatures or patches. Traditional threat-hunting methods often fall short in detecting and mitigating these attacks. This paper explores the integration of Artificial Intelligence (AI) into threat-hunting processes to
enhance the detection and response to zero-day attacks. By leveraging machine learning algorithms, anomaly detection, and behavioral analysis, AI-augmented threat hunting can proactively identify and neutralize zeroday threats. This paper discusses the methodologies, benefits, and challenges of implementing AI in threat hunting, providing a comprehensive framework for future research and practical applications. By leveraging machine learning, anomaly detection, and behavioral analysis, AI-augmented threat hunting can proactively identify and neutralize emerging threats, providing a robust defense mechanism against zero-day vulnerabilities. The integration of AI into threat hunting not only enhances the ability to detect zero-day attacks but also enables organizations to predict and prevent future threats by analyzing patterns and trends in real-time data.

Index Terms- Artificial Intelligence, Zero-Day Attacks, Threat Hunting, Cybersecurity, Machine Learning, Anomaly Detection.

Paper Title SMART VISION: ENHANCING AUTONOMOUS DRIVING WITH AI-POWERED RECOGNITION
Author Name Shaffy, Aditya Sinha, Md Shadab Alam, Syed Ubaid Ullah, Naman Kumar & Sachin Kumar Sachan
Country India
DOI https://doi.org/10.5281/zenodo.19065117
Page No. 591-601

Abstract View PDF Download Certificate
SMART VISION: ENHANCING AUTONOMOUS DRIVING WITH AI-POWERED RECOGNITION
Author: Shaffy, Aditya Sinha, Md Shadab Alam, Syed Ubaid Ullah, Naman Kumar & Sachin Kumar Sachan

ABSTRACT
With the rapid advancements in artificial intelligence (AI), autonomous vehicles have emerged as a transformative innovation in transportation. Understanding the evolution of AI- powered recognition systems and identifying emerging trends in this domain is crucial for guiding future research and development. This paper proposes a comprehensive approach to analyzing AI technologies used in autonomous vehicles, focusing on perception, decision-making, and predictive modeling. By systematically collecting data from multiple sources, we preprocess and structure it for analysis. Using advanced machine learning techniques such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and sensor fusion algorithms, we extract insights into how AI enables vehicles to recognize objects, predict behaviors, and navigate complex
environments. Visualization techniques such as heat maps, trajectory graphs, and feature importance charts will demonstrate the prominence of various AI methods over time and their impact on safety and efficiency. Our findings highlight key trends in AI-powered perception systems, including object detection, lane recognition, and predictive modeling, while also identifying challenges like handling edge cases and ensuring robustness under adverse conditions. This study not only showcases the effectiveness of AI in autonomous vehicle recognition but also provides a roadmap for leveraging these technologies to shape the future of mobility.

General Terms—Autonomous Vehicles, Artificial Intelligence, Object Recognition, Computer Vision, Sensor Fusion, Predictive Modeling, Deep Learning

Paper Title EXPLORING CHALLENGES, FEATURES AND APPLICATIONS OF WIRELESS SENSOR NETWORK
Author Name Geeta Kocher & Kuldip Kumar
Country India
DOI https://doi.org/10.5281/zenodo.19065192
Page No. 602-610

Abstract View PDF Download Certificate
EXPLORING CHALLENGES, FEATURES AND APPLICATIONS OF WIRELESS SENSOR NETWORK
Author: Geeta Kocher & Kuldip Kumar

ABSTRACT
Wireless Sensor Network is a kind of remote correlation that encompasses an enormous number of sensor center points that are good for distinguishing, activating, and transferring the gathered data, which have generated astounding sway all over. A wireless sensor network is a massive sensor local area that can only perform limited evaluation and has a limited power supply. The sensor hubs are equipped with radio points of interaction, allowing them to communicate with one another and form an organization. With the significant advancements in PC and sensor development, wireless sensor networks are used in a wide range of industries, including the military, healthcare, organic agriculture, and other commercial applications. This paper aims to
present a recent composition on various aspects of wireless sensor organization capacity and examine the benefits and challenges of remote organization over standard association. In this paper various examination problems in applications based on remote sensor networks are summarized.

Keywords
Sensor Nodes, Security, Applications of WSN, Wireless Sensor Network

Paper Title SECURE PERSONA PREDICTION AND DATA LEAKAGE PREVENTION SYSTEM
Author Name Ritik Chawla, Aayushi Sinha, Richa Dhiman, Sanya Saxena & Ruchi Thakur
Country India
DOI https://doi.org/10.5281/zenodo.19065239
Page No. 611-621

Abstract View PDF Download Certificate
SECURE PERSONA PREDICTION AND DATA LEAKAGE PREVENTION SYSTEM
Author: Ritik Chawla, Aayushi Sinha, Richa Dhiman, Sanya Saxena & Ruchi Thakur

ABSTRACT—
The Secure Persona Prediction and Data Leakage Prevention System leverages advanced predictive analytics to enhance user experience while simultaneously safeguarding sensitive information. By accurately anticipating user requirements and behavioral patterns, this innovative system significantly diminishes the risk of data
breaches. As a result, it ensures robust protection of critical data across a diverse array of applications, providing users with a seamless and secure interaction environment. This dual focus on user satisfaction and data security positions the system as a vital tool in today’s data-driven landscape.

Keywords—User experience, Data protection, data breach prevention, Behavioral analysis, Risk mitigation

Paper Title LEVERAGING VOTING TECHNIQUES TO PREDICT MENTAL STRESS: EXPLORING THE EFFICACY OF HARD AND SOFT VOTING MODELS
Author Name Priyanka Gupta & Anil Pandit
Country India
DOI https://doi.org/10.5281/zenodo.19090443
Page No. 622-628

Abstract View PDF Download Certificate
LEVERAGING VOTING TECHNIQUES TO PREDICT MENTAL STRESS: EXPLORING THE EFFICACY OF HARD AND SOFT VOTING MODELS
Author: Priyanka Gupta & Anil Pandit

ABSTRACT:
Student stress is a significant concern affecting academic performance, mental well-being, and overall health. This study examines the use of ensemble learning methods, particularly hard voting and soft voting classifiers, on a dataset that includes several academic, social, physiological, psychological, and environmental elements that affect students' stress levels. A range of machine learning models, including Decision Trees, Support Vector Machines, and Logistic Regression, are used in ensemble frameworks. Performance indicators including accuracy, precision, recall, and F1-score are used to
assess the efficacy of hard versus soft voting techniques. The results demonstrate the advantages of soft voting in handling
complex, multi-dimensional data in student stress prediction.Furthermore, we analyse the feature importance and the impact of individual predictors on stress levels, which provides deeper insights into the contributing factors. This research highlights the importance of ensemble learning in psychological and academic research, offering improved stress prediction and early intervention possibilities

KEYWORDS: Ensemble Learning, Hard Voting, Soft Voting, Student Stress Prediction, Machine Learning, Psychological Factors, Physiological Factors , Academic Performance

Paper Title MACHINE TRANSLATION OF ENGLISH NEWS TO INDIAN SIGN LANGUAGE (ISL) USING SYNTHETIC ANIMATION FOR DEAF COMMUNITY
Author Name Annu Rani, Sukhdeep kaur, Sandeep kaur & Vikas Atri
Country India
DOI https://doi.org/10.5281/zenodo.19107000
Page No. 629-639

Abstract View PDF Download Certificate
MACHINE TRANSLATION OF ENGLISH NEWS TO INDIAN SIGN LANGUAGE (ISL) USING SYNTHETIC ANIMATION FOR DEAF COMMUNITY
Author: Annu Rani, Sukhdeep kaur, Sandeep kaur & Vikas Atri

ABSTRACT
Communication of ideas, concepts, and knowledge to others depends heavily on language. A language known as sign language is used by hearing-impaired persons to comprehend our thoughts. Our created system in this study uses a rulebased methodology. Our method uses synthetic animations based on Indian Sign Language's grammatical rules to translate English news into ISL. Following identification, 141 grammatical rules that transform complex, compound sentences into simple ones are used. Lemmatization is used to transform the words into the lemma form because inflections of words are not used in ISL. The bilingual dictionary includes total 4497 gestures in the form of synthetic animation. Animated virtual avatars are used to convert the HamNoSys notations into synthetic animations. The survey was done in Patiala's "Deaf and Blind School of Patiala" to assess the created system. The performance of the system has been assessed using qualitative and quantitative metrics on a total of 1112 news phrases. It is demonstrated that the created English News
Telecast System for Deaf is normally 79.94% accurate. The ISL lexicon and recorded ISL videos are compared to every signed word's output. This research contributes to the domain of sign language translation by merging established linguistic principles within new animation techniques. It represents a main step towards bridging the gap for ISL users, enhances their access to education, media and border societal participation.
General Terms

Keywords
BART, ISL, Deaf community, Synthetic Animation, HamNoSys code and SiGML Player

Paper Title CLASSIFICATION OF TEXT DATA USING A DEEP LEARNING LONG SHORTTERM MEMORY NETWORK
Author Name Peerzada Moien Ahmad, Amreen Kaur & Yadwinder singh
Country India
DOI https://doi.org/10.5281/zenodo.19107216
Page No. 640-644

Abstract View PDF Download Certificate
CLASSIFICATION OF TEXT DATA USING A DEEP LEARNING LONG SHORTTERM MEMORY NETWORK
Author: Peerzada Moien Ahmad, Amreen Kaur & Yadwinder singh

ABSTRACT
The presented study explores various signal classification techniques, systematically categorizing them into statistical and machine learning (ML) approaches. While statistical methods operate on predefined mathematical foundations requiring minimal algorithmic support, ML techniques were developed to address automation demands in signal processing. ML-based classification is further sub-divided into supervised,
unsupervised, and semi-supervised learning models, each characterized by unique methodologies and challenges. Supervised learning, though effective, is resource-intensive due to its reliance on labeled data. Unsupervised techniques leverage clustering and self-organizing maps to overcome labeling constraints. Semisupervised approaches combine the strengths of both, significantly enhancing classifier accuracy with minimal labeling costs. In this work, a Long Short-Term Memory (LSTM) neural network is proposed for text classification tasks, employing word embedding layers to capture semantic relationships. The developed LSTM model demonstrates 100% accuracy in classifying testing data, highlighting its efficacy for high-dimensional
signal classification problems.

Keyword: Signal Classification Techniques, Machine Learning Approaches, Statistical Methods, Long ShortTerm Memory (LSTM), Supervised and Unsupervised Learning

Paper Title SMART PARKING SYSTEMS: LEVERAGING MACHINE LEARNING AND IOT FOR EFFICIENT SPACE MANAGEMENT
Author Name Ritik Soni, Supriya Kumari & Bhawana Goyal
Country India
DOI https://doi.org/10.5281/zenodo.19107309
Page No. 645-653

Abstract View PDF Download Certificate
SMART PARKING SYSTEMS: LEVERAGING MACHINE LEARNING AND IOT FOR EFFICIENT SPACE MANAGEMENT
Author: Ritik Soni, Supriya Kumari & Bhawana Goyal

ABSTRACT
Rapid urbanization coupled with a rapidly growing vehicle population has led to a great concern in the management of cities’ parking structures, which have become congested leading to increased emissions and wasted time. This research will discuss the development of a Smart Parking System (SPS), integrating algorithms of Machine Learning (ML) and Internet of Things (IoT) technologies to help optimize the
management of urban parking spaces. The proposed system used IoT sensors to capture real-time data on the availability of parking spaces, vehicle occupancy, and user demand patterns. Through ML techniques such as predictive analytics and reinforcement learning, the SPS will improve decision-making processes for the
driver and the parking administrator. Case studies and sim- ulations are analyzed based on performance regarding reduced search times, utilization of spaces, and higher satisfaction for users for testing the efficacy of the system. It also talks about the integration with the existing urban infrastructure and is associated with sustainable urban mobility. Findings from the study indicated that SPS not only improved parking
efficiency but also reduced traffic congestion coupled with carbon footprints in urban areas. This study further brings forth the revolutionary capabilities of integrating ML and IoT, when merged together, to reimagine the management of parking and create smarter cities as well as more efficient ones.

Index Terms- Smart Parking System, Machine Learning, In- ternet of Things, Space Management, Urban Mobility, Predictive Analytics, Traffic Congestion, Sustainability, Real-Time Data, Vehicle Occupancy, Smart Cities, IoT Sensors.

Paper Title DETECTING ALZHEIMER'S DISEASE IN ITS EARLY STAGES: DEEP LEARNING APPROACHES TO MRI ANALYSIS
Author Name Rajni Devi, Anzah Bashir & Khalid Hafiz Mir
Country India
DOI https://doi.org/10.5281/zenodo.19107440
Page No. 654-661

Abstract View PDF Download Certificate
DETECTING ALZHEIMER'S DISEASE IN ITS EARLY STAGES: DEEP LEARNING APPROACHES TO MRI ANALYSIS
Author: Rajni Devi, Anzah Bashir & Khalid Hafiz Mir

ABSTRACT
Alzheimer’s disease is a progressive neurodegenerative disease that has severe impact on cognitive abnormalities and life span. Ideally the diagnosis should be made early enough so that one can control the symptoms and slow down progression of the disease but conventional diagnostic techniques seldom help in diagnosing AD right at their onset. As for this research, the approach of using deep learning algorithms in the MRI outcomes is introduced in the aspect of the early screening of Alzheimer’s disease. To this concern, we propose and evaluate the proposed CNN and transfer learning to
identify subtle structural changes in the early phase of AD. With the MRI scan dataset that we have gotten for the diagnosed patients and control group, the developed models to different test criteria and control have been trained for the test. Studying results of the experimental comparison of the various applied models makes it possible to outline features for achieving high sensitivity as well as specificity at the biomarker discovery time concerning early Alzheimer’s due to the results of the present study. This work could open up the way for the application of deep learning to enhance the efficiency and efficacy of screening for AD so that early detection could be a possibility.

Keywords—Alzheimer's disease, early detection, deep learning, MRI analysis, convolution neural networks, transfer learning, neurodegenerative disorders, biomarkers, medical imaging, artificial intelligence.

Paper Title PHISHING SIMULATION PLATFORM FOR ENHANCING CYBERSECURITY AWARENESS AND TRAINING
Author Name Abhishek Tiwari, Ayush Awasthi, Mukhtiar Singh & Nikhil Tripathi
Country India
DOI https://doi.org/10.5281/zenodo.19107549
Page No. 662-670

Abstract View PDF Download Certificate
PHISHING SIMULATION PLATFORM FOR ENHANCING CYBERSECURITY AWARENESS AND TRAINING
Author: Abhishek Tiwari, Ayush Awasthi, Mukhtiar Singh & Nikhil Tripathi

ABSTRACT
Phishing attacks remain one of the most prevalent and damaging threats in the cybersecurity landscape. Educating users about phishing risks is crucial to mitigating these threats. This paper presents a phishing simulation platform designed to
enhance cybersecurity awareness and train individuals in recognizing phishing tactics. The platform simulates realistic phishing scenarios by sending deceptive emails that redirect users to a phishing site, where credential entry is monitored. It comprises three core components: an email-sending module, a login page, and a real-time credential logging dashboard. The backend of the platform is developed using Flask, while the frontend is built with HTML, CSS, and JavaScript to ensure a responsive and interactive user experience. The system is deployed on Render, providing a scalable and accessible
environment for real-time phishing simulations. By analyzing user interactions with simulated phishing attempts, the platform assesses users‟ ability to detect phishing threats. The results demonstrate its effectiveness in improving awareness and highlight its potential as a training tool for cybersecurity education. This study provides a foundation for future advancements in phishing awareness training and the development of more sophisticated educational tools to combat social engineering attacks.

Keywords: Phishing simulation, cybersecurity awareness, phishing attacks, email phishing, credential logging, phishing prevention, phishing education, cybersecurity tools, user behavior, real-time monitoring.

Paper Title AUTONOMOUS INTELLIGENCE: ADVANCEMENTS AND CHALLENGES IN INTEGRATING AI FOR SELF-DRIVING CARS
Author Name Aarti Hans & Namrata Vij
Country India
DOI https://doi.org/10.5281/zenodo.19107823
Page No. 671-683

Abstract View PDF Download Certificate
AUTONOMOUS INTELLIGENCE: ADVANCEMENTS AND CHALLENGES IN INTEGRATING AI FOR SELF-DRIVING CARS
Author: Aarti Hans & Namrata Vij

ABSTRACT—
A lot of countries around the world are very concerned about road safety. Traffic risk is being reduced by using innovative technology. Innovative features of intelligent transportation infrastructure include autonomous vehicles (AVs). As a type of safety device, they are active. The unsolved issues are how to make self-driving cars safe enough for drivers and other road users, and most importantly, how much safety would be put in. In addition to reducing transportation costs (including fuel, vehicles, and infrastructure) by 40% and improving livability and walkability, these five urban transportation revolutions might remove traffic congestion by 30% with 30% fewer automobiles on the road by 2050. Make parking spaces available for community centers, parks, and schools, among other uses. Cut global urban CO2 emissions by 80%. Design and implementation of a battery and photovoltaic-powered self-driving automobile are the goals of this project. With the use of appropriate sensors and actuators, artificial intelligence principles have been implemented. An AI is stands
as a contemporary subfield in computer science, a relatively nascent area extensively employed in innovation management within organizational frameworks. Drawing on actual enterprises such as Tesla, this research investigates the process of converting autonomous driving technology into a novel product that gains societal acceptance, exploring its influence on organizational innovation.

Index Terms—Machine Learning, Self-driving Cars, Au- tonomous Cars, Tesla, Road Safety ,Safety Algorithm, AI Pro- cessors.

Paper Title AUTONOMOUS INTELLIGENCE: ADVANCEMENTS AND CHALLENGES IN INTEGRATING AI FOR SELF-DRIVING CARS
Author Name Aarti Hans & Namrata Vij
Country India
DOI https://doi.org/10.5281/zenodo.19107823
Page No. 671-683

Abstract View PDF Download Certificate
AUTONOMOUS INTELLIGENCE: ADVANCEMENTS AND CHALLENGES IN INTEGRATING AI FOR SELF-DRIVING CARS
Author: Aarti Hans & Namrata Vij

ABSTRACT—
A lot of countries around the world are very concerned about road safety. Traffic risk is being reduced by using innovative technology. Innovative features of intelligent transportation infrastructure include autonomous vehicles (AVs). As a type of safety device, they are active. The unsolved issues are how to make self-driving cars safe enough for drivers and other road users, and most importantly, how much safety would be put in. In addition to reducing transportation costs (including fuel, vehicles, and infrastructure) by 40% and improving livability and walkability, these five urban transportation revolutions might remove traffic congestion by 30% with 30% fewer automobiles on the road by 2050. Make parking spaces available for community centers, parks, and schools, among other uses. Cut global urban CO2 emissions by 80%. Design and implementation of a battery and photovoltaic-powered self-driving automobile are the goals of this project. With the use of appropriate sensors and actuators, artificial intelligence principles have been implemented. An AI is stands
as a contemporary subfield in computer science, a relatively nascent area extensively employed in innovation management within organizational frameworks. Drawing on actual enterprises such as Tesla, this research investigates the process of converting autonomous driving technology into a novel product that gains societal acceptance, exploring its influence on organizational innovation.

Index Terms—Machine Learning, Self-driving Cars, Au- tonomous Cars, Tesla, Road Safety ,Safety Algorithm, AI Pro- cessors.

Paper Title CLASSIFICATION OF TEXT DATA USING A DEEP LEARNING LONG SHORTTERM MEMORY NETWORK
Author Name Peerzada Moien Ahmad, Amreen Kaur & Yadwinder singh
Country India
DOI https://doi.org/10.5281/zenodo.19107216
Page No. 640-644

Abstract View PDF Download Certificate
CLASSIFICATION OF TEXT DATA USING A DEEP LEARNING LONG SHORTTERM MEMORY NETWORK
Author: Peerzada Moien Ahmad, Amreen Kaur & Yadwinder singh

ABSTRACT
The presented study explores various signal classification techniques, systematically categorizing them into statistical and machine learning (ML) approaches. While statistical methods operate on predefined mathematical foundations requiring minimal algorithmic support, ML techniques were developed to address automation demands in signal processing. ML-based classification is further sub-divided into supervised,
unsupervised, and semi-supervised learning models, each characterized by unique methodologies and challenges. Supervised learning, though effective, is resource-intensive due to its reliance on labeled data. Unsupervised techniques leverage clustering and self-organizing maps to overcome labeling constraints. Semisupervised approaches combine the strengths of both, significantly enhancing classifier accuracy with minimal labeling costs. In this work, a Long Short-Term Memory (LSTM) neural network is proposed for text classification tasks, employing word embedding layers to capture semantic relationships. The developed LSTM model demonstrates 100% accuracy in classifying testing data, highlighting its efficacy for high-dimensional
signal classification problems.

Keyword: Signal Classification Techniques, Machine Learning Approaches, Statistical Methods, Long ShortTerm Memory (LSTM), Supervised and Unsupervised Learning

Paper Title BIO-INSPIRED OPTIMIZATION: THE INTEGRATION OF PSO AND ACO FOR ENHANCED ENERGY EFFICIENCY
Author Name Amanpreet Kaur & Sandeep Singh Kang
Country India
DOI https://doi.org/10.5281/zenodo.19107963
Page No. 684-694

Abstract View PDF Download Certificate
BIO-INSPIRED OPTIMIZATION: THE INTEGRATION OF PSO AND ACO FOR ENHANCED ENERGY EFFICIENCY
Author: Amanpreet Kaur & Sandeep Singh Kang

ABSTRACT—
Powerful bio-mediated approaches have demon- strated their ability to solve various complex optimization prob- lems in multiple sectors. The research investigates how merging two major bio-inspired methods Particle Swarm Optimization and Ant Colony Optimization improves energy efficiency of computational and engineering systems. Particle Swarm Optimization utilizes bird flocking social behaviors to attain excellent global exploration but Ant Colony Optimization achieves its local exploitation efficiency by utilizing ant foraging behaviors. Through the proposed hybrid framework both
methods com- plement each other to overcome PSO’s premature convergent behavior as well as reduce ACO’s complex computation. The PSO-ACO hybrid approach produces an advanced solution for energy optimization by incorporating the exploration capabilities of PSO with the optimization efficiency of ACO. The framework achieves its intended outcomes according to simulation evalua- tions and practical case assessments through proving its effec- tiveness in energy reduction, resource optimization and system operational enhancement. The newly developed hybrid strategy offers both accelerated convergence performance together with superior solution quality in addition to superior adaptability in dynamic environmental conditions when compared to con- ventional approaches. The studied research shows that hybrid
bio-inspired algorithms demonstrate effectiveness by supplying scalable sustainable solutions to energy management tasks. The proposed framework develops a strategic optimization solution which helps advance current knowledge about efficient power system development. The research created foundations to advance bio-inspired techniques through future investigations of their utilization with multiple objectives and real-time systems and industrial implementations for global energy management.

Index Terms—Bio-Inspired Algorithms, Particle Swarm Opti- mization (PSO), Ant Colony Optimization (ACO), Computational Optimization, Swarm Intelligence.

Paper Title ANALYZING DATA WITH COGNITIVE ALGORITHMS: UNLOCKING THE POTENTIAL OF AI AND CHATGPT
Author Name Er. Priyanka Devi, Er. Shivam Sharma & Mukhtiar Singh
Country India
DOI https://doi.org/10.5281/zenodo.19108880
Page No. 695-704

Abstract View PDF Download Certificate
ANALYZING DATA WITH COGNITIVE ALGORITHMS: UNLOCKING THE POTENTIAL OF AI AND CHATGPT
Author: Er. Priyanka Devi, Er. Shivam Sharma & Mukhtiar Singh

ABSTRACT—
Artificial intelligence has seen a revolution thanks to large language models, which are employed in many different contexts. Chat Generative Pre-trained Transformer is one of these models. is a particularly effective and extensively used tool. Personalized suggestions, chatbots, language translation, content creation and even medical diagnosis and treatment have all benefited from the successful application of ChatGPT. The reason behind its effectiveness in these applications is its capacity to produce replies that resemble those of a human, comprehend natural language, and adjust to
various settings. Because of its accuracy and versatility, it is a useful tool for NLP, But ChatGPT has drawbacks as well, namely the potential to reinforce negative language patterns and its propensity to generate biased replies. A thorough explanation of ChatGPT’s uses, benefits, and drawbacks is given in this article. Data analysis may be greatly improved by integrating cognitive algorithms and AI, especially with models like ChatGPT. Through preprocessing, insights production, and decision support, these technologies provide a comprehensive method for maximizing data’s potential for a range of uses. Nonetheless, it’s critical to keep privacy, security, and ethical issues in mind at every stage of the data analysis procedure. The study also stresses how crucial ethical issues are to take into account when applying this powerful tool in practical settings. Finally, by shedding light on quick engineering strategies, this study adds to the continuing conversations about artificial intelligence and how it affects the disciplines of vision and natural language processing.

Index Terms—Artificial intelligence, NLP , ChatGPT, Cognitive Algorithms, Generative models.

Paper Title NEXT-GEN AI DECISION SUPPORT IN SOFTWARE ENGINEERING: LEVERAGING COMPLEXITY WITH QUANTUM COMPUTING, DEVOPS AUTOMATION, AND RESPONSIBLE MACHINE LEARNING
Author Name Simran, Sonu Kumar & Er Priyanka Devi
Country India
DOI https://doi.org/10.5281/zenodo.19109050
Page No. 705-713

Abstract View PDF Download Certificate
NEXT-GEN AI DECISION SUPPORT IN SOFTWARE ENGINEERING: LEVERAGING COMPLEXITY WITH QUANTUM COMPUTING, DEVOPS AUTOMATION, AND RESPONSIBLE MACHINE LEARNING
Author: Simran, Sonu Kumar & Er Priyanka Devi

ABSTRACT—
Utilizing next-generation AI decision support systems driven by quantum computing, DevOps automation, and responsible machine learning is the way of the future as software engineering struggles with increasing complexity. Current computational boundaries are broken by quantum computing, which makes it possible to solve complex algorithms and large amounts of data quickly. DevOps automation integrates AI to remove bottlenecks and increase efficiency while orchestrating smooth cooperation. Fundamentally, responsible machine learning acts as the moral compass, guaranteeing that decisions made by AI are open, accountable, and consistent with social norms. When these three ideas come together, software development and management undergo a radical change. They handle the complexities of contemporary software while improving speed and dependability by streamlining decision- making. This study presents a framework for Next Generation AI Decision Support in Software Engineering, resulting in an AI- driven "software engineer" capable of managing the difficulties of modern development. This intelligent system uses quantum computing to solve complicated software design difficulties with its improved processing capabilities. Integrating DevOps automation to speed up continuous integration, delivery, and deployment ensures agile, real-time responsiveness to changing needs. The
incorporation of responsible machine learning concepts, which address concerns of bias and interpretability while maintaining privacy, enables ethical and transparent decision-making. Through case studies and performance evaluations, this AI-driven software engineer has proven to optimize resources, reduce development timelines, and improve software quality, laying the groundwork for future autonomous engineering systems that support complex decision-making and operational efficacy.

Index Terms—Ethical AI, Quantum Computing, DevOps Au- tomation, Decision Support Systems, Autonomous engineering systems, Predictive Analytics, Automated Workflows

Paper Title THE GREEN CODE: SUSTAINABLE PRACTICES IN COMPUTING
Author Name Gurnoor Kaur, Gurpuneet S. Hunjan & Chahat Jain
Country India
DOI https://doi.org/10.5281/zenodo.19109254
Page No. 714-722

Abstract View PDF Download Certificate
THE GREEN CODE: SUSTAINABLE PRACTICES IN COMPUTING
Author: Gurnoor Kaur, Gurpuneet S. Hunjan & Chahat Jain

ABSTRACT
Green computing, or sustainable computing, comprises the development and optimization of computer hardware, systems, networks, and software aimed at enhancing efficiency by maximizing energy utilization while minimizing adverse
environmental impacts. The term "green computing" comprises methodologies and practices designed to reduce technology's environmental impact. It also encompasses the reduction of electronic waste disposal. With advancements in upcoming technology, too much of devices, mechanisms, and software tools have emerged, prompting extensive research focused on optimizing their green computing capabilities. This review examines and synthesizes literature surrounding green computing. It provides a detailed explanation about what the top leading tech- companies are doing to achieve maximum performance while remaining efficient. Some of the famous industry leaders are NVIDIA, IBM, Apple, Asus, Intel, and Samsung. It highlights current research trajectories, assessment methodologies employed, and the architectural
strategies of various technologies facilitating green computing and sustainable development. The insights offered herein will be valuable for organizations, researchers, and institutions engaging in green computing initiatives.

Keywords: Green Computing, E-waste Management, Sustainable Hardware, Circular Economy, Sustainable IT

Paper Title QUANTUM COMPUTING MEETS CLOUD: INTEGRATING AND ENHANCING HIGHPERFORMANCE COMPUTING APPLICATIONS
Author Name Sonali Banyal & Rishabh Sharma
Country India
DOI https://doi.org/10.5281/zenodo.19109353
Page No. 723-733

Abstract View PDF Download Certificate
QUANTUM COMPUTING MEETS CLOUD: INTEGRATING AND ENHANCING HIGHPERFORMANCE COMPUTING APPLICATIONS
Author: Sonali Banyal & Rishabh Sharma

ABSTRACT
A revolutionary change in the world of computation- ally intensive applications is represented by the mainstreaming of quantum computers into services provided by the cloud. This paper explores the synergy between quantum computing and cloud infrastructures, emphasizing how their convergence can address the computational demands of modern industries. We present an in-depth analysis of existing frameworks, ar- chitectures, and methodologies enabling this fusion, pointing up important issues such data transmission latencies, error correction, and limitations of quantum technology. Furthermore, we provide a brand-new hybrid integration model that max- imizes task distribution among cloud-based conventional and quantum resources, guaranteeing smooth operation and lower overhead. Quantum computing, or QC, has enormous potential to further scientific research in fields including neural networks, optimization, as quantum chemical science. The external noise present in the current noisy intermediate-scale quantum (NISQ) era, however, continues to pose serious problems to QC. The integration of QC as a computational accelerator in traditional
high-performance computing (HPC) systems is examined in this work. Using a variety of simulators and quantum hardware, we provide a hardware-neutral framework to use QC to improve the abilities for conventional HPC. Using the Department of Energy’s (DOE) lifetime management skills plus leveraging Oak Ridge National Laboratory’s (ORNL) HPC expertise, our strategy focuses on strategically integrating QC acceleration into current HPC processes. For the DOE and the Office of Naval Research missions, this entails thorough assessments, benchmarking, and code optimization. The framework creates a unified environment that facilitates research on both quantum and conventional computing by integrating hardware, software, processes, and user interfaces. By bridging QC and HPC, this paper aims to open new
computational opportunities, driving scientific innovation and enabling groundbreaking advancements across various
research domains.
Index Terms—Quantum-Cloud Integration, Quantum Algo- rithms, Cloud Infrastructure, Hybrid Computing Models, Scalable Computing.

Paper Title ENERGY-EFFICIENT ROUTING PROTOCOLS FOR WIRELESS BODY AREA NETWORKS: A REVIEW
Author Name Surender Singh, Amreen Kaur & Jaspreet Kaur
Country India
DOI https://doi.org/10.5281/zenodo.19109444
Page No. 734-739

Abstract View PDF Download Certificate
ENERGY-EFFICIENT ROUTING PROTOCOLS FOR WIRELESS BODY AREA NETWORKS: A REVIEW
Author: Surender Singh, Amreen Kaur & Jaspreet Kaur

ABSTRACT
Wireless Body Area Networks (WBANs) have emerged as a crucial technology for healthcare monitoring, enabling realtime patient monitoring with minimal human intervention. These networks consist of sensor nodes that continuously track
vital physiological parameters and wirelessly transmit data to remote medical servers. However, energy efficiency remains a critical challenge due to the limited power resources of sensor nodes, affecting the longevity and reliability of WBAN deployments. Efficient routing protocols play a key role in managing power consumption, reducing communication overhead, and enhancing network lifetime while ensuring quality of service (QoS) parameters such as reliability, latency, and security. This paper provides a comprehensive review of various energy-efficient routing protocols designed for
WBANs, analyzing their mechanisms, strengths, and limitations. The classification of these protocols into cluster-based, temperature-aware, QoS-aware, and cross-layer approaches offers a structured comparison of their effectiveness in different medical scenarios. Additionally, we present a detailed comparative analysis based on key performance metrics such as energy consumption, network lifetime, and reliability. Furthermore, we discuss existing challenges in WBAN energy efficiency, including security concerns, real-time data transmission constraints, and scalability issues. Lastly, we explore potential research directions, emphasizing the integration of energy harvesting techniques and blockchain-based security frameworks to enhance the sustainability and robustness of WBANs. This review aims to provide insights into
future advancements in energy-efficient WBAN routing protocols, supporting optimized healthcare applications and remote patient monitoring systems.

Paper Title BUSTING DARK PATTERNS USING PACKET CAPTURING
Author Name Richa Dhiman, Rishabh Katiyar, Muskan Rawat, Abhiroop Singh, Vansh Rawat & Anirudh Singh
Country India
DOI https://doi.org/10.5281/zenodo.19109649
Page No. 740-749

Abstract View PDF Download Certificate
BUSTING DARK PATTERNS USING PACKET CAPTURING
Author: Richa Dhiman, Rishabh Katiyar, Muskan Rawat, Abhiroop Singh, Vansh Rawat & Anirudh Singh

ABSTRACT—
Dark patterns include a set of design signals coming from a website or an application, which control the consumer’s choices in a waythat the consumer is not aware of or did not consent to the manipulation. [1] Some of these tactics have been seen to capitalize on people’s feelings and thoughts to make them perform undesired actions for instance making unnecessary purchases, signing up for unnecessary services or putting out personal details. Packet Capturing: This technique pays out well in the identification of ways that there is intercepting of the networkpackets and their analysis. Sneaking a peek through the internet’s packetsof data would make one realize the use of
dark patterns [2]. Following is a discussion on the utilization, as an identification and solution technique, of packet capturing as a means of identifying dark patterns. This research will discuss type of dark patterns out there, what a victim potentially stands to suffer from. This study will present a suggested solution in relation to packet capture approaches that will address the need to educate the user alongside the use of machine learning and dataanalysis.

Keywords—Prognostication, Multivariate time series, price salecorrelation, parameterized prognosticator.

Paper Title ADVANCES IN DISPERSION COMPENSATION TECHNIQUES FOR FIBER-OPTIC COMMUNICATION SYSTEMS: A REVIEW
Author Name Jaspreet Kaur, Rakesh Goyal & Gagandeep Kaur
Country India
DOI https://doi.org/10.5281/zenodo.19109747
Page No. 750-757

Abstract View PDF Download Certificate
ADVANCES IN DISPERSION COMPENSATION TECHNIQUES FOR FIBER-OPTIC COMMUNICATION SYSTEMS: A REVIEW
Author: Jaspreet Kaur, Rakesh Goyal & Gagandeep Kaur

ABSTRACT
This review synthesizes advancements in dispersion compensation techniques for WDM and passive optical network (PON) systems. It covers various compensation schemes including pre‐, post‐, symmetric, and dual techniques and examines the roles of fiber Bragg gratings (FBGs), dispersion compensating fibers (DCFs), and hybrid configurations. Mathematical models underlying dispersion effects and performance metrics are presented alongside schematic figures to illustrate system architecture and simulation results.

Keywords: Rare-earth-doped hybrid optical amplifier, Fiber Bragg gratings, chromatic dispersion, nonlinear effects, WDM systems

Paper Title TEXTLESS NLP FOR LOW-RESOURCE SPEECH TRANSLATION
Author Name Priyanka Jangra, Prince Kumar, Adeeb Alam, Kriti kant, Nirbhay Mishra & Vikas Babu
Country India
DOI https://doi.org/10.5281/zenodo.19109829
Page No. 758-768

Abstract View PDF Download Certificate
TEXTLESS NLP FOR LOW-RESOURCE SPEECH TRANSLATION
Author: Priyanka Jangra, Prince Kumar, Adeeb Alam, Kriti kant, Nirbhay Mishra & Vikas Babu

ABSTRACT—
The increasing demand for multilingual communication across the globe highlights the need for effective translation systems, particularly for low-resource languages with scarce or non-existent text data. Conventional speech translation pipelines rely heavily on intermediate text representations, which are impractical for languages with limited written corpora or complex oral traditions. This paper proposes a Textless NLP framework tailored for low-resource speech translation, directly translating speech from source to target languages without the need for text transcription. Leveraging advancements in self-supervised speech representations, speech-only embeddings, and sequence-to-sequence speech mapping, the system captures semantic content from the target language and produces vocal output in the source language. The proposed system is evaluated on simulated low-resource datasets, demonstrating its efficacy in preserving meaning and achieving intelligible translations even in the absence of textual data. This research contributes to the development of inclusive speech technology, particularly for endangered languages, oral dialects, and linguistically marginalized communities. Results indicate that textless speech translation can achieve competitive performance with reduced reliance on annotated parallel corpora, making it a viable solution for real-world deployment in low-resource contexts.

Keywords: Textless NLP, Low-resource languages, Speech translation, Self-supervised learning, Speech-to-speech translation, Endangered languages, Zero-shot translation, Low-resource NLP

Paper Title FIBER LENGTH IMPACT ON STIMULATED RAMAN SCATTERING (SRS) IN WDM SYSTEMS
Author Name Jaspreet Kaur, Rakesh Goyal & Gagandeep Kaur
Country India
DOI https://doi.org/10.5281/zenodo.19110011
Page No. 769-778

Abstract View PDF Download Certificate
FIBER LENGTH IMPACT ON STIMULATED RAMAN SCATTERING (SRS) IN WDM SYSTEMS
Author: Jaspreet Kaur, Rakesh Goyal & Gagandeep Kaur

ABSTRACT
This study systematically investigates the interplay between fiber length and Stimulated Raman Scattering (SRS)-induced spectral distortions in Wavelength Division Multiplexing (WDM) systems. Using a 50 km nonlinear optical fiber and highresolution optical spectrum analysis, we quantify the evolution of Raman tilt a power imbalance between short and longwavelength channels under controlled conditions (bit rate: , sample rate: , channel spacing: 58.30 GHz). Our experiments reveal a nonlinear relationship between fiber length and tilt magnitude, with tilt increasing from
to . The results highlight the critical role of cumulative SRS effects in degrading
channel uniformity and optical signal-to-noise ratio (OSNR) in long-haul systems. This work provides actionable insights for mitigating nonlinear impairments in next-generation optical networks, emphasizing strategies such as unequal channel
spacing and hybrid amplification.

Keywords
Stimulated Raman Scattering (SRS), Wavelength Division Multiplexing (WDM), nonlinear fiber optics, Raman tilt, spectral distortion, noise accumulation

Editorial Policy About Peer Reviewed Journal Publication Ethics & Practices Plagiarism Policy Open Access, Licencing & Copyright Disclaimer Policy Privacy Policy FAQ Special Issue About The Journal

Latest Announcements

  • CALL FOR PAPERS 2025 (January-June)

    01-01-2025
    SUBMIT PAPERS IN OUR RESEARCH JOURNAL! 2025
    National Research Journal of Information Technology and Information Science  contributes in the growth and application of Research & Technology, by delivering the latest information contained in research papers, which enables them to enhance understanding for advancements in research activities. We intends to Disseminate and promote the research works of research scholars, Academia.

  • Subscribe This Journal

    01-01-2025
    We Request to Subscribe our Journals for the Noble Cause to Spread Knowledge, Wisdom and also to Protect Intellectual Property Rights of Scholars Across the World.

    Subscription Price: 3500/- (Bi-Annual)

    CALL NOW!
    +91-9888934889, 7986925354

Publish
Conference
Or Seminar
papers in our journal

Read More

National Research Journal of Information Technology & Information Science

+91-9888934889

editornrjitis@gmail.com

Useful Links

  • Home
  • About The Publisher
  • Submit Paper Online
  • Call for Papers
  • Publication Ethics
  • Join Our Editorial Board
  • Journal Subscription
  • Contact Us

Explore Other Journals

  • NRJ of Human Resource Mgt.
  • National Research Journal of Business Economics
  • Sales and Marketing Management
  • Banking and Finance Management
  • Academe: Journal of Education and Psychology
  • Research and Reviews in Biotechnology and Biosciences
  • Journal of Literary Aesthetics
  • Social Science Journal

Downloads

  • Copyright Form
  • Paper Template
  • Manuscript Guidelines
  • e-Certificate
  • Sitemap
© 2026 National Research Journal of Information Technology & Information Science. All Rights Reserved.
Published By: National Press Associates www.npajournals.org