Deep Learning -Based Suicidal Thought Detecion From Social Media With IOT-Enabled Alert System
Authors: J. Jenitta, Amulya N, Keerthi Kandakur, Nithin N, Shashank G
Abstract: As the online socialization process advances, more and more individuals are reporting their emotional conditions online and in many instances showing symptoms of misery and suicidal tendencies, which present significant obstacles to monitoring mental health. Conventional techniques of detecting such content are often untimely and ineffective and it is based on this need that automated and real time detection is important. In this paper, the author suggests a deep learning-based suicide risk prediction system based on linguistic data obtained on social media. The model achieves a high degree of accuracy in differentiating between texts that are suicidal and those that are not by learning the contextual semantics using bidirectional long short-term memory (Bi-LSTM) networks. The system is coupled with an IoT-based alert system to make sure that timely intervention is applied to prevent suicidal intent by sending alarms to caregivers or other interested parties whenever any suicidal intent is identified. The results of the testing show that the proposed method performs better in comparison to the traditional machine learning classifiers that are measured in terms of precision, recall, and F1-score. This combination related to the higher-order NLP techniques and the use of IoT-driven indicators offers a scalable and productive approach to stopping destructive online behavior. This article highlights the role of artificial intelligence and IoT in the improvement of digital mental health support systems.
DOI: http://doi.org/10.5281/zenodo.17590356
Automatic Cruise Control System for Car
Authors: Dr. S. P. Munot, Pratiksha Gudade, Rutuja Ikhe, Vaibhavi Kandare
Abstract: The Automatic Cruise Control (ACC) System using Raspberry Pi 4 is a smart, cost-effective prototype designed to enhance vehicle safety and comfort through intelligent automation. Powered by Raspberry Pi 4, it integrates multiple sensors—ultrasonic for obstacle detection, gyroscope for stability, GPS and GSM for tracking and communication, and a camera with face recognition for secure vehicle access. The system automatically maintains and adjusts vehicle speed using an L298 motor driver and DC motor based on real- time sensor data, while an OLED display and buzzer provide instant feedback and alerts. This project effectively demonstrates how embedded technology can simulate adaptive cruise control, offering a scalable and efficient step toward future autonomous driving system.
A Study On The Procurement Strategies Adopted By The Hospitals In Kolkata: An Analysis By Using AI Based Tolls
Authors: Dr. Pramit Das, Mr. Prasmit Das, Ms. Subhasree Ray
Abstract: Healthcare procurement in India encompasses a complex interplay between cost containment, transparency, and quality improvement. This research examines procurement mechanisms in public and private hospitals, highlighting the transition from price-based purchasing toward value-based, sustainable, and technology-driven strategies. This paper analyses purchase and revenue data from 2022 to 2025 in the healthcare sector, with special attention to implants and consumables. Analytical methods employed include descriptive statistics, variance analysis, correlation studies, and regression modelling. The findings highlight notable growth in purchases and revenue, identify leading product categories, and examine the interplay between inflation and purchase behaviour.
Smart Attendance System Using Location
Authors: Swarupa Chavare, Madhuri Dhole, Sneha Bankar, Prajakta Dhaygude, Harshda Bhongale, I.T.Mukerjee
Abstract: Attendance for the organization is important in both academic and professional institutions, to keep discipline and track performance. Conventional practices such as manual roll calls or use of biometric scanners are highly time-consuming, error pro and susceptible to proxy attendance through multiple means. This paper proposes a Smart Attendance system with the help of GPS technology as well as the geofencing concept which does marking attendance automatically. As student’s smart phone entered pre-defined classroom region, system recorded the attendance of the student. The students are supported by a mobile app while attendance data is stored and processed in a cloud based backend. It also has a Defaulter List Module which computes percent attendance automatically and lists the respective students who does not attend by given cut-off (i.e. less than 75%). It enhances accuracy and transparency, minimizes manual labor, while enhancing rigour. Practical realization demonstrates that the system is capable of effectively avoiding proxy attendance and realizing real-time attendance management with reliability.
Buddy: A Python-Based Mood-Aware Chatbot For Personalized Movie, Music, And Motivation Recommendations”
Authors: Aditya Kamble, ,Jayash Chavan, Siddharth Gaikwad, Vaishnavi Dardige, Professor I.T. Mukharjee
Abstract: In recent years, conversational artificial intelligence (AI) has transitioned from simple command-based systems to emotionally responsive digital companions capable of contextual understanding and human-like interaction. However, most available chatbot architectures depend on large-scale machine learning models and cloud-based computation, making them complex, data-intensive, and inaccessible for lightweight or educational applications. To address these challenges, this research presents Buddy, a modular, Python-based conversational chatbot designed to deliver personalized entertainment and motivational support using emotion cues and real-time API integrations. The proposed framework emphasizes simplicity, scalability, and emotional adaptability without requiring extensive natural language processing infrastructure. Buddy functions as a context-aware conversational assistant capable of recognizing user moods and providing tailored responses in the form of movie, music, weather, and motivational recommendations. The system integrates multiple public APIs — including TMDb for film suggestions, Spotify for mood-aligned music, ZenQuotes for motivational content, and OpenWeatherMap for contextual awareness — enabling multi-domain interaction. A rule-based mood detection engine identifies user sentiment from keywords such as “sad,” “happy,” or “bored,” while modular functions handle data fetching and formatting. This architecture creates a seamless conversational loop where Buddy adapts to user feedback, learns preferences in real time, and maintains an empathetic conversational tone. Experimental evaluation demonstrates that Buddy achieves an average response latency of 1.25 seconds, with a keyword detection accuracy of 95% across varied moods and network conditions. The framework exhibits low computational overhead (<100 MB memory usage) and functions efficiently on standard hardware without GPU support. Furthermore, its modular structure allows integration with advanced AI components such as sentiment classifiers or edge-deployed models in future versions. Compared to existing AI chatbots, Buddy provides a balance between human-like engagement, data privacy, and system transparency, highlighting how modular API-driven design can democratize access to emotionally intelligent AI systems. This study establishes Buddy as a sustainable, privacy-preserving, and adaptable conversational framework that bridges the gap between rule-based logic and emotionally aware digital companionship — paving the way for next-generation lightweight AI assistants suitable for education, mental wellness, and personalized entertainment ecosystems.
CENT-Advancing Banking System Using Face Recognition
Authors: Harshvardhan Patil, Dhruv Agrawal, SuryaPratap Singh Solanki, Parth Patel
Abstract: This research paper explores the development of a next-generation banking system that integrates biometric authentication, specifically facial recognition, to ensure robust security and a seamless user experience. The project, titled CENT (Centralized Enhanced Neural- banking Technology), combines machine learning models, backend services, frontend design, and database integration to simulate a secure and scalable financial application. Built using technologies like OpenCV and TensorFlow, the system features a comprehensive pipeline including face detection, user registration, account management, and transaction processing, all accessible through a modern web interface. This paper elaborates on the project's architecture, system requirements, design methodology, implementation details, and real-world applications, providing a comprehensive overview of the CENT system.
DOI: http://doi.org/10.5281/zenodo.17597420
Smartfolio ( AI-based Portfolio Management System )
Authors: Cheenepalli Gowthami Priya, Shreya Itkapalle, Priya Prasad, Saginala Arifulla, Rishabh Tripathi, Dr. Nithya
Abstract: SmartFolio is a portfolio management software aimed to assist users in creation, management and. present individual portfolios effectively. The platform serves differ- ent professionals who include By offering lively customization of the portfolio, intel- ligent, investors, designers and freelancers. user experience, and content suggestions. Constructed on the basis of the latest web technologies. SmartFolio uses AI-based analytics to streamline the portfolio material, propose better options, and. enhance user engagement. The system incorporates the mechanisms of automated portfolio generation, reactive design templates, live-time data analytics, and safe cloud stor- age. Additionally, it enables multimedia support, interactive user in- terfaces and rich search capabilities into guarantee an enjoyable and uninterrupted experience. The project will seek to close the divide that exists between static. portfolio websites and intelligent automation through delivering a smart, adaptable and user- friendly. platform. It will use machine learning algorithms, real- time data processing, and cloud-based. architecture, SmartFolio allows professionals to sustain an effective and relevant digital. presence with little work. In this paper, the architecture, the pro- cess of development and the major points will be discussed. capabilities, and possible future improvements of SmartFolio, with a focus on how it can change. AI-based portfolio manage- ment. Keywords:Portfolio management system, Intelligent portfo- lio generation,Machine learning,Professional portfolio showcase, Interactive UX/UI de- sign,Freelancer portfolio,Investor portfo- lio,Designer portfolio.
Design And Implementation Of A Modern Expense Tracker Web Application Using MERN Stack
Authors: Marella Jaya Sri, Mounika Sai Sowjanya Kodi, Koppula Vasundhara, Gunji Sai Sasank
Abstract: Personal financial management has become in- creasingly crucial in today’s fast-paced world where individuals struggle to track their expenses manually. This research paper presents the design, development, and implementation of a comprehensive Expense Tracker web application built using the MERN (MongoDB, Express.js, React, Node.js) stack. The application provides users with an intuitive platform to monitor income and expenses, categorize transactions, set monthly budgets, and analyze spending patterns through interactive visualizations. Key features include JWT-based authentication, dynamic transaction filtering, category management, budget tracking with proactive alerts, and data visualization. The paper discusses the technology selection rationale, system architec- ture, implementation challenges, and performance evaluation. The application demonstrates how modern web technologies can be leveraged to create effective financial management tools that empower users to make informed financial decisions. Expense Tracker, MERN Stack, Financial Management, Budget Tracking, React, Node.js, MongoDB, Web Applica- tion
Ai Based Student Feedback Analysis System
Authors: Prajwal Sunil Saste, Om Santhosh Dhage, Aditya Arun Tathe, Prof. Rahane.D.A
Abstract: The swift advancement of AI in education has paved the way for more customized and flexible educational settings. This study introduces a student feedback analysis system powered by AI, which offers immediate, smart feedback to boost learning results. The system uses sentiment analysis to determine the emotional aspectof student communications and uses machine learning methods like decision trees, support vector machines (SVM), and deep learning models to assess participation, success, and emotional conditions. By merging cognitive and emotional understandings,the suggested system offers tailored, relevant feedback to help students conquer learning obstacles. Testing outcomes reveal enhanced student involvement, contentment, and general academic success, emphasizing the ability of AI to revolutionize contemporary education
Ai Based Student Feedback Analysis System
Authors: Prajwal Sunil Saste, Om Santhosh Dhage, Aditya Arun Tathe, Prof. Rahane.D.A
Abstract: The swift advancement of AI in education has paved the way for more customized and flexible educational settings. This study introduces a student feedback analysis system powered by AI, which offers immediate, smart feedback to boost learning results. The system uses sentiment analysis to determine the emotional aspectof student communications and uses machine learning methods like decision trees, support vector machines (SVM), and deep learning models to assess participation, success, and emotional conditions. By merging cognitive and emotional understandings,the suggested system offers tailored, relevant feedback to help students conquer learning obstacles. Testing outcomes reveal enhanced student involvement, contentment, and general academic success, emphasizing the ability of AI to revolutionize contemporary education
E-Library Management System
Authors: B.Parthiban, R.Sripadma
Abstract: Libraries have come a long way from the traditional manual processes to the modern digital solutions that we now have, changing forever how information is handled and accessed. This paper presents the design, construction and application of a Library Management System (LMS) integrated with various advanced capabilities like Chat Bot, Voice Recognition and GUI. This LMS is intended to automate library operations, help improve user experience as well as optimize resource management. The paper describes the problem definition, project aims, approach taken, and system level architecture along with future work directions.
AI-Powered Forensic Image Suite For Authenticity Verification
Authors: Professor Shivani Karhale, Mr. Rohit Pawar, Ms. Sanskruti Marawade, Ms. Nandini Jadhav, Ms. Vaishnavi Pawaskar
Abstract: The rapid advancement of artificial intelligence, image editing tools, and generative models has made visual manipulation easier than ever. Altered images can influence legal investigations, journalism, social media, and political narratives, creating a critical need for automated authenticity verification systems. This research introduces an AI-Powered Forensic Image Suite integrating shadow analysis, image consistency detection, and metadata verification to identify tampered digital images. The system preprocesses images through resizing, normalization, and noise reduction, followed by shadow recognition using gradient-based and geometric estimation techniques. Image consistency is evaluated using structural similarity, lighting coherence, and texture uniformity checks. Metadata analysis extracts EXIF information to verify timestamps, camera signatures, and editing traces. Experiments conducted on a dataset of 500 real and manipulated images demonstrate high accuracy, with shadow detection (94%), consistency check (92%), and metadata validation (98%). The suite serves as a reliable tool for investigators, journalists, and forensic professionals, and provides a scalable foundation for advanced features such as deepfake detection, reverse image search, and error-level analysis.
College Event Management: A Survey of Analytics and Personalization
Authors: P. Shiva Sanakara Pandian, K. Sai varsha
Abstract: College Event Management System represents a comprehensive software solution designed to optimize and streamline the planning, organization, and management of events within college. This research project addresses the challenges encountered by academic institutions in coordinating and executing a diverse range of events, including conferences, seminars, cultural festivals, and sports tournaments, with a primary focus on enhancing efficiency, communication, and collaboration. The objective of this study is to explore the development and implementation of the College Event Management System, underscoring its potential to transform event management within educational institutions. By combining user insights, case studies, and in- depth analysis. The findings underscore the importance of modernized event management tools in promoting student engagement, fostering effective communication, and facilitating the successful execution of events within the college environment. Ultimately, this research project aims to provide valuable insights for academic institutions seeking to optimize their event management processes, thereby enhancing the overall campus experience.
Environmental Influence On Chicken Raised In Refused Dumpsites In The Zaria Metropolis
Authors: Umudi Ese Queen, Erienu Obruche Kennedy, Apuyor Kingsley Efe, Apuyor Stanley Ejohwomu, Onwugbuta Godpower Chukwuemeka, Eresanya Olanrewaju Isola, Ikechukwu Sampson Chikwe
Abstract: The research looked into how dumpsites affect the areas around them. They collected and tested the dust and heavy metals found in chickens raised near these waste sites during both dry and wet seasons. For three months, young chickens were fed solid waste and leachates from these sites, and then they were sacrificed for analysis. A standard method for testing dust and heavy metals was followed, as recommended by the World Health Organization (WHO). They used Atomic Adsorption Spectroscopy to find out how much heavy metal was present. The levels of Zn, Cd, Cu, Pb, and Hg in the dust varied by season, ranging from 1.40 (JK) to 210.60 (SA), BDL (CTR) to 3.74 (RA), 0.241 (KU) to 390.0 (JK), 2.26 (CTR) to 78.260 (SH), and BDL (CTR) to 25.69 (AJ). For the chicken samples, the heavy metal levels ranged from BDL (CTR) to 8.844 (JK), BDL (CTR) to 2.850 (BG), BDL (CTR) to 0.099 (BG), BDL (CTR) to 128.017 (NTC), and BDL (CTR) to 83.122 mg/kg (DD) for Zn, Pb, Cd, Cu, and Hg across different sites and seasons. Most of the metal levels in the chicken samples were below safe limits, but a few were not, indicating that people living near these dumpsites are affected. The Kaduna State Environmental Agency (KEPA) needs to work on reducing hazardous waste and provide better waste disposal options.
DOI: http://doi.org/10.5281/zenodo.17637261
Traffic Sign Recognition Using Multi-Task Deep Learning For Self-Driving Vehicles
Authors: Atharva Rajesh Gosavi
Abstract: raffic sign recognition (TSR) is a critical component of autonomous driving systems, enabling vehicles to understand and respond to road regulations in real time. Traditional TSR approaches typically separate classification and localization tasks, resulting in increased computational cost and reduced robustness in complex driving environments. This paper proposes a multi-task deep learning framework that performs simultaneous traffic sign detection, classification, and attribute prediction using a shared feature-extraction backbone. The model leverages multi-task learning to exploit interrelated features across tasks, improving overall accuracy while reducing inference time—an essential requirement for self-driving applications. Extensive experiments conducted on benchmark datasets such as GTSRB and GTSDB demonstrate that the proposed approach outperforms single-task baselines, achieving higher precision in both recognition and localization. The results show that multi-task learning enhances generalization under challenging conditions, including occlusion, varying illumination, and high-speed motion. This work highlights the potential of unified deep learning architectures to deliver efficient and reliable traffic sign recognition for next-generation autonomous vehicles.
Pseudo Irregular Fuzzy Soft Graphs
Authors: L.Subhalakshmi, Dr. N.R.Santhi Maheswari
Abstract: This paper deals with pseudo irregular fuzzy soft graphs. The definition of pseudo irregular graphs is introduced with some properties. The pseudo edge irregular fuzzy soft graphs are illustrated with examples. The properties of the defined graphs are studied. Highly, neighbourly, strongly pseudo irregular graphs are explained with examples. Also some pseudo edge irregular fuzzy soft graphs are illustrated. The relation between strongly pseudo irregular fuzzy soft graphs with highly and neighbourly pseudo irregular FSG is given. Results on total pseudo irregular FSG and total pseudo edge irregular FSG is examined.
Fuzzy PDE Models For Sustainable Resource Dynamics: An A-Cut And Robust Optimization Framework
Authors: Siddalingaswamy R, Yogeesh N, Rajathagiri D T, M. S. Sunitha, Jagadeesha K C
Abstract: This study develops a practical modeling pipeline to treat epistemic uncertainty in sustainability-focused partial differential equations governing environmental and urban systems. We represent imprecise forcings and parameters with fuzzy numbers (triangular/trapezoidal membership functions) and propagate uncertainty via α-level analysis: for each α, parameters are mapped to compact intervals and a deterministic diffusion–reaction problem is solved to yield envelopes of feasible states. The workflow integrates (i) fuzzy parameterization and α-cut computation, (ii) numerically stable parabolic solvers (implicit/Crank–Nicolson discretizations with Dirichlet boundaries), and (iii) a stylized robust multi-objective design that visualizes trade-offs between expected performance and sustainability risk. Two representative applications illustrate relevance: groundwater-style storage under uncertain recharge–demand balance and urban heat mitigation with uncertain material/forcing properties. Results include interpretable membership curves and α-cut bounds, α-dependent terminal profiles, time-evolution bands that communicate worst-plausible excursions, and Pareto fronts clarifying yield–risk compromise under policy intensity. A grid-refinement study indicates indicative second-order spatial convergence in the smooth-solution regime, supporting numerical consistency. Beyond these cases, the framework is modular and extensible to nonlinear physics, higher dimensions, and hybrid fuzzy–stochastic formulations, while remaining transparent for expert elicitation and decision support. Overall, the approach preserves uncertainty structure without imposing unwarranted probability models, providing decision-makers with conservative, policy-ready indicators for risk-aware planning in data-sparse contexts
DOI: http://doi.org/10.5281/zenodo.17617766
Leveraging Artificial Intelligence (AI) And Machine Learning (ML) In Women’s Access To Healthcare In Rural India
Authors: Hridayjyoti Deka, Dikshita Medhi
Abstract: Women's healthcare necessitates comprehensive approaches to address unique and ubiquitous health related issues of women, which include nutritional, reproductive, mental, and chronic diseases. On the other hand, rural healthcare must overcome tangible and intangible barriers, including geographic isolation, inadequate physical and digital infrastructure, sociocultural resistance, a shortage of healthcare professionals, and policy paralysis. Artificial Intelligence and Machine Learning have revolutionized the healthcare paradigm through developments such as deep learning enabled medical imaging and diagnostics, predictive analytics, drug discovery, real time monitoring of disease surveillance, precision and personalised medicines, robotic surgery, robotic neurorehabilitation, etc. However, the benefits of these breakthroughs are mostly being received by the advanced societies; the greater rural masses still expect miracles of the trickle down effect. The healthcare issues and challenges pertaining to women are peculiar and need special focus from researchers, particularly in low resource settings like rural India. Nevertheless, the researchers have long started exploring Artificial Intelligence and Machine Learning based solutions for problems related to women’s healthcare and rural healthcare. In this article, focusing on the challenges and approaches, we review the state of the art of Artificial Intelligence and Machine Learning in women’s healthcare that carries significant potential for implementation in the rural healthcare system in India
DOI: http://doi.org/10.5281/zenodo.17617845
Enhancement Of Energy Efficiency For Decarbonization In The Indian Manufacturing Sector: A Review
Authors: D. Damodara Reddy, Soma Vivekananda, Vennam Gopala Krishna
Abstract: Primary energy consumption doubled since the 2000s, between 440 and 880 million TOE. It is projected to double within the next 20 years, reaching approximately 1,900 million TOE, and to reach 1,500 million TOE by 2030. It is anticipated to double over the next 20 years to around 1,900 million TOE, and by 2030, it will reach 1,500 million TOE. The manufacturing sector in India uses the most energy. Energy use in the global industrial sector accounts for one-third of total consumption, according to a review of energy analysis. So that effort has been made to improve the energy efficiency (EE) of the industry to enhance performance. Energy efficiency means using less energy to do an identical task while lowering energy costs and emissions. A key component of the all-encompassing plan to decarbonize industrial operations is energy efficiency. This research intends to investigate the most current systematic literature evaluations on energy efficiency in the industrial sector that were published between 2017 and 2023, taking into account this vast amount of information. The current study creates and establishes six distinct groups that reflect the state of the field's research after conducting qualitative and topical evaluation: Energy Conservation and Innovation, Energy Diagnostics, Energy Monitoring, and Energy Optimization. It consists of the automated and comprehensive formulation of measures for energy efficiency utilizing energy efficiency analysis, broad and flexible modeling of consumption of energy at various production stages to determine technological efficiency possibilities, and the comprehensive evaluation and sorting method taking into account the relationships among methods.
DOI: http://doi.org/10.5281/zenodo.17618019
Social Media Monetization (Modern Advertising System)
Authors: Aaditya Deo, Shah Saurabh, Anurag Tiwari, Ishordev Chaudhary, Dr. Sneha Soni
Abstract: Traditional digital marketing frequently encounter high costs, authenticity gaps, and declining consumer trust. Simultaneously regular customers and small creators who organically promote products seldom receive benefits. This paper present a concise research version of the project “Social Media Monetization: A Modern Advertising System” which enable customers to earn cashback by promoting purchased product from partnered brands on Instagram. The system leverage user generated con- tent to provide brands with authentic, cost effective promotion while offering customers a transparent reward mechanism. We summarize the problem context, objectives, system methodology, modules, expected outcomes, and future directions strictly based on the original project report, and reserve space for illustrative figures aligning with the submitted work. Customer Based Advertising, Cashback Reward, Digital Marketing, Social Media Promotion, Instagram Marketing, Authenticity, Secure Payment Integration, Marketing Ana- lytics, User Engagement Tracking, AI Based Advertisement Optimization, Scalable Marketing Model.
Adoptly: A Cross-Platform Application For Streamlined Pet Adoption
Authors: Akshat Parekh, Jemit Patel, Deep Upadhyay, Jay Shah
Abstract: The increasing number of abandoned animals underlines the necessity of reliable and transparent adoption systems. Existing adoption practices often rely on scattered sources such as social media, which lack consistency, verification, and accountability. This paper presents Adoptly, a mobile-first application designed to streamline pet adoption by ensur- ing secure authentication, verified listings, and seamless communication between adopters and shelters. Built using React Native (Expo) for cross- platform compatibility, Clerk for user authentication, and Firebase for real-time storage and database services, Adoptly integrates features such as verified pet profiles, favorites, adoption requests, story sharing, and an in-app chat system. Developed under an agile methodology, the system reduces misinformation, enhances trust, and improves adoption efficiency compared to unstructured methods. Early testing demonstrates reliabil- ity in authentication, smooth navigation, and real-time synchronization. The findings highlight the potential of mobile-first systems to revolu- tionize adoption processes by bridging gaps of communication, trust, and scalability.
DeepLeaf: AI-Powered Plant Disease Detection And Prediction With Multilingual Support And PDF Report Generation_783
Authors: G Vishal, G K Sharath Kumar, Karthik N Ganiga,, Sanjay Kumar
Abstract: An important factor in a nation's economic development is the agricultural sector. In particular, it provides millions of people in rural India with a vital source of income. One of the major issues influencing the agriculture industry is plant disease. Diseases can infect plants for a variety of reasons, such as synthetic fertilizers, outdated methods, environmental factors, etc., which affect farm productivity and thereby hurt the economy. Researchers have looked into a variety of AI and machine learning-based applications to identify plant diseases in order to address this problem.
Deep Leaf: AI-Powered Plant Disease Detection and Prediction with Multilingual Support and PDF Report Generation
Authors: G Vishal, G K Sharath Kumar, Karthik N Ganiga,, Sanjay Kumar, Prof. Merlin B
Abstract: An important factor in a nation's economic development is the agricultural sector. In particular, it provides millions of people in rural India with a vital source of income. One of the major issues influencing the agriculture industry is plant disease. Diseases can infect plants for a variety of reasons, such as synthetic fertilizers, outdated methods, environmental factors, etc., which affect farm productivity and thereby hurt the economy. Researchers have looked into a variety of AI and machine learning-based applications to identify plant diseases in order to address this problem.
Energy-Efficient Data Center Optimization using AI Control
Authors: Logeshwaran V, Bhuvaneswari B
Abstract: In recent years, the exponential growth of dataintensive applications and cloud-based services has drastically increased energy consumption in data centers worldwide. This surge poses significant challenges, including high operational costs, carbon emissions, and sustainability concerns. To address these issues, this paper proposes a comprehensive AI-based framework for energyefficient data center optimization. The approach integrates intelligent control algorithms, predictive analytics, and adaptive resource allocation mechanisms that dynamically manage workloads, cooling systems, and server utilization. Using techniques such as machine learning (ML), reinforcement learning (RL), and neural network-based control, the proposed model achieves significant energy savings while maintaining service-level agreements (SLAs). The research demonstrates how AI- driven systems can autonomously predict server loads, optimize cooling parameters, and minimize idle energy consumption. The findings contribute to the design of sustainable, selfoptimizing data centers for the next generation of green computing infrastructure.
A Comprehensive Review On Canine Health And Welfare: Trends, Challenges, And Technological Advancements
Authors: Isha V Solanki, Preet Darji, Jainil Parmar, Manush Desai, Prof. Garima Sharma
Abstract: The paper addresses an in-depth review of over 60 peer-reviewed studies that deal with canine health and welfare and their proponents and cons on both conventional and emerging strategies. The review encompasses topics of behavioral assessment, vaccination, dental hygiene, population management, diagnosis of allergies and the introduction of artificial intelligence into veterinary medicine, aligning clinical science and technology and ethics. It is worth noting that it determines the vital areas of investigation of behavioral and dental diagnostics, issues of population affected by stray populations, and lack of standardiza- tion in the implementation of preventive care despite its evident usefulness. In contrast to the previous reviews, the given study is rather multi-dimensional, as it links welfare and innovation to each other. The paper can be reproducible because it adheres to PRISMA standards on the selection of studies. Conclusions will target both the veterinarians, the pet owners, researchers, and policymakers by promoting evidence-based models of care. In the perspective, the paper highlights the necessity of standard behaviors and tools, available AI-aided diagnosing, and more significant public education so as to drive international levels of canine well-being.
Desktop Voice Assistant
Authors: Anish Mukhiya, Raushan Kumar Ram, Anuraj Chaudhary, Omkar Mahto
Abstract: Background: Personal Desktop Voice Assistants (PDVAs) represent a significant advancement in human-computer interaction, offering intuitive voice-based control of desktop environments. Meth- ods: This study employed Python programming language with integrated speech recognition, natural language processing, and text-to-speech technologies to develop an accessible PDVA. The system archi- tecture incorporates wake word detection, intent recognition, and task execution modules. Results: The developed PDVA successfully executes diverse commands including web searching, media control, system management, and information retrieval. The system demonstrates particular effectiveness for visually impaired users, providing multimodal feedback through synthesized speech and on-screen text. Conclu- sion: The research confirms that Python-based PDVAs can significantly enhance desktop accessibility while highlighting the importance of addressing privacy concerns and interaction limitations in future developments.
Study Report On Swift Kiosk
Authors: Arpita Sahu, Dr. Waris Patel
Abstract: The rapid digital transformation in the food and beverage industry has created a demand for efficient, customizable, and user-friendly ordering solutions. Tra- ditional restaurant operations often face challenges such as order inaccuracies, long wait times, dependency on labor, and inefficient payment systems. To ad- dress these issues, we propose Swift Kiosk, a digital kiosk application designed specifically for caf´es and restaurants. Built using the MEARN stack (MongoDB, Express.js, Angular, React, and Node.js), Swift Kiosk enhances the food ordering experience by allowing customers to customize their meals, process cashless trans- actions, and reduce dependency on manual labor. This innovation streamlines restaurant operations while delivering a seamless and engaging customer experi- ence. One of the core functionalities of Swift Kiosk is food customization, allowing users to personalize their meals and beverages with ease. Customers can select portion sizes, ingredients, dietary preferences (vegan, gluten-free, keto, etc.), and cooking methods, ensuring a tailor-made dining experience. The application pro- vides a real-time preview of the customized meal, ensuring accuracy before order placement. Swift Kiosk leverages MongoDB as the database to efficiently store and manage user preferences, order details, and restaurant menu configurations. With Node.js and Express.js powering the backend, the system ensures fast and scalable pro- cessing of customer orders, reducing wait times and improving order accuracy. To enhance user interaction, the application is designed using React.js for the frontend, offering a responsive and visually appealing interface. For businesses, an Angular-based admin panel allows restaurant owners to manage menus, track sales, and analyze customer behavior in real time. This combination of technolo- gies ensures a smooth and dynamic user experience. Swift Kiosk automates the order-taking process, reducing the reliance on hu- man staff and increasing efficiency. Customers can place their orders directly through the kiosk interface, which sends requests instantly to the restaurant’s kitchen system. The application supports multiple payment options, including UPI, digital wallets, credit/debit cards, and QR-based transactions, ensuring se- cure and hassle-free payments. By integrating Express.js and MongoDB, transaction data is stored securely, and real-time payment confirmations ensure a frictionless checkout process. This automated system eliminates long queues, minimizes order miscommunication, and enhances customer satisfaction. By digitizing order placement and payment, Swift Kiosk reduces labor depen- dency, allowing restaurant staff to focus more on food preparation and service rather than manual order management. The application also provides data ana- lytics using MongoDB’s aggregation framework, helping restaurant owners analyze customer preferences, order trends, and peak business hours. These insights assist in optimizing menu offerings, pricing strategies, and targeted promotions, enhanc- ing overall profitability. Swift Kiosk, powered by the MEARN stack, presents a modern, scalable, and efficient solution for caf´es and restaurants. By allowing customers to customize their food, automating the ordering and payment process, and reducing opera- tional inefficiencies, Swift Kiosk transforms traditional restaurant operations into a tech-driven, customer-centric model. As the food service industry continues to embrace digital transformation, Swift Kiosk stands as a pioneering step towards enhancing efficiency, reducing operational costs, and improving the overall dining experience.
DOI: http://doi.org/10.5281/zenodo.17637230
Healthsync: Smartcare Companion
Authors: Krishna Wable, Bhumika Raut, Radhika Ware, Achal Patil, Prof.Vrushali Channe
Abstract: Maintaining a healthy lifestyle often becomes diffi- cult due to generic advice and delayed health insights. Health- Sync: SmartCare Companion is an AI-driven system designed to offer personalized, adaptive, and culturally relevant healthcare support. It integrates BioMistral-7B for medical text understand- ing and ResNet for food and symptom image recognition. Using fuzzy logic with TOPSIS/AHP, the system estimates personalized daily nutrient and calorie needs, supported by an ontology-based food graph linking Indian dishes, nutrients, and diseases. With time-series tracking and reinforcement learning, HealthSync continuously refines recommendations based on user progress. Trained on Indian food and lifestyle datasets, it delivers accurate, real-time, and inclusive wellness guidance—transforming preven- tive healthcare into a smarter, more user-focused experience.
Developing an End-to-End Secure Chat Application
Authors: S. Surendar Raj, K. Sai varsha
Abstract: Chat applications have emerged as indispensable tools on smartphones, offering users the ability to exchange text messages, images, and files at no cost. However, ensuring the security of these communications is paramount. This paper proposes a secure chat application that implements End-to-End encryption, safeguarding private information exchanged between users and providing robust data protection. The application also addresses storage security concerns. By outlining a set of requirements for a secure chat application, this paper informs the design process. The proposed application is evaluated against these requirements and compared with existing popular alternatives to assess its security features. Furthermore, the application under goes rigorous.
Abusive and Hate Speech Detection in Social Media using Natural Language Processing
Authors: Praveen B, Sripadma R
Abstract: Social media platforms such as Facebook, Twitter, Instagram, and WhatsApp have emerged as primary channels for public communication, information sharing, and social interaction. However, the same platforms also serve as spaces where abusive expressions, offensive remarks, and hate speech are increasingly common. Hate speech may target individuals or groups based on factors such as religion, nationality, gender, ethnicity, or other identity characteristics, and can result in psychological harm, discrimination, and real-world conflict. Manual moderation of such continuously increasing online content is challenging, inconsistent, and time-consuming. Therefore, automated detection systems are needed to analyze and classify harmful language. This research proposes a Natural Language Processing based system that preprocesses text, extracts features using TF-IDF, and classifies content using Support Vector Machine (SVM). The results show that this approach effectively distinguishes between normal, abusive, and hate speech, making it suitable for real-time moderation in social media platforms.
Facial Expression Recognition For Mental Health
Authors: Dr. Radha Shirbhate, Zaidkhan Pathan, Aditya Gude, Vishal Joshi
Abstract: Mental health plays a vital role in determining overall well-being, productivity, and social interaction [1], [2]. However, diagnosing mental disorders like depression and anx- iety often relies on self-reporting and therapist observation, which may introduce subjectivity and delay treatment. This paper presents an AI-based facial expression recognition (FER) framework that analyzes human emotions from visual cues to assist early mental health assessment [3], [4]. The proposed system uses Convolutional Neural Networks (CNNs) trained on the FER-2013 dataset, combined with MediaPipe for real-time facial landmark extraction and OpenCV for image preprocessing. The model recognizes seven basic emotions: happy, sad, fear, anger, disgust, surprise, and neutral. Real-time video streams are processed, and the detected emotional states are visualized on a dashboard that can track emotion trends over time [5]. The system demonstrates promising performance with accuracy above 92% on validation data and real-time latency under 40 ms/frame [6]. The integration of FER technology into mental health analysis offers an innovative, non-invasive, and continuous monitoring tool that complements traditional clinical methods.
Ai in Cybersecurity: Threat Intelligence and Prediction
Authors: Mohammad Usman M, Bhuvaneswari B
Abstract: The rapid digitization of global infrastructure has led to an exponential increase in cyber threats. Traditional security mechanisms are proving inadequate against evolving, intelligent, and large-scale cyberattacks. Artificial Intelligence (AI) has emerged as a transformative tool in cybersecurity, enabling automated detection, proactive threat prediction, and adaptive defense mechanisms. This paper explores how AI enhances threat intelligence through predictive analytics, machine learning, and deep learning techniques. It also examines challenges related to data privacy, model interpretability, and adversarial attacks. The study concludes that AI-driven threat intelligence has immense potential in transforming cyber defense, provided that human oversight and ethical frameworks are maintained.
Enhancing Restaurant Efficiency with Swift Kiosk: An Electron.js based Interactive Ordering Platform
Authors: Warish Patel, Nana Yaw Duodu, Arpita Sahu, Raksha Choudhary, Sakshi Sharma, Achala Karn
Abstract: The food and beverage sector is undergoing rapid digital transformation, which has in- creased the need for flexible, efficient, and user-friendly ordering platforms. Conventional restaurant systems often struggle with problems like order mismatches, extended waiting times, heavy dependence on staff, and outdated payment methods. To overcome these challenges, we introduce Swift Kiosk, a digital kiosk solution tailored for caf´es and restaurants. Developed using Electron.js, Swift Kiosk en- hances the dining experience by offering customizable ordering, seamless UPI-based payments, and reduced reliance on manual operations. A key highlight of Swift Kiosk is its meal customization feature, where customers can choose portion sizes, ingredients, dietary options (such as vegan, keto, or gluten- free), and preferred cooking styles. The system displays a real-time preview of the customized dish, ensuring precision before order confirmation. Orders are then sent directly to the kitchen system, which minimizes delays and reduces the chance of human error. Additionally, secure UPI integration enables quick, cashless transactions for a smoother checkout process. By streamlining order-taking, payment, and analytics, Swift Kiosk helps restaurants lower labor re- querulents while delivering higher customer satisfaction. This technology-driven approach modernizes traditional restaurant operations, cutting costs, improving efficiency, and creating a customer-focused dining environment. As the industry continues to adopt digital innovations, Swift Kiosk stands out as a scalable, sustainable, and future-ready solution for restaurant management.
Selecting an Effective Microservices Decomposition Approach: A Decision Framework
Authors: Md. Abdul Momin, M.M. Musharaf Hussain, Md. Ezharul Islam
Abstract: This research presents a comprehensive exploration of diverse microservices decomposition techniques. This research identifies the sequential steps integral to each decomposition method through a meticulous study and analysis of multiple techniques. Moreover, the paper integrates insights gleaned from a select group of experts. These experts offer valuable perspectives on software characteristics and elucidate the types of example software ideally suited for distinct decomposition types. They also validate the time and cost implications associated with each decomposition technique. Drawing from these multifaceted insights, the paper culminates in creating an algorithm. This algorithm is intricately designed based on collective knowledge and discussions surrounding software traits, such as suitability, time, and cost considerations linked to various decomposition techniques. This algorithm helps developers choose the most effective decomposition approach for microservices.
DOI: https://doi.org/10.5281/zenodo.17645806
The Role of Artificial Intelligence in Indian Education: A Survey-Based Study
Authors: Kartavy Gupta
Abstract: Artificial Intelligence (AI) is rapidly transforming the Indian education system, offering personalized learning, improved accessibility, and efficient administration. This paper examines the role of AI in Indian education, combining secondary research with a small-scale student survey. The survey, conducted among 50 senior secondary students from urban and semi-urban schools in India, explored awareness, usage, and perceptions of AI in learning. Results indicate that while 82% of students use AI-powered tools for study support, only 38% receive any formal school-based AI education. The findings highlight both enthusiasm for AI and the need for structured training, equitable access, and ethical guidelines. The study concludes that AI can revolutionize Indian education if implemented inclusively and responsibly.
Blockchain For Secure Electronic Medical Records: A Review
Authors: Suraj Yadav, Girdhari Lal
Abstract: Electronic Medical Records contain extremely private medical data, electronic medical records are frequently shared between authorized parties. Maintaining the integrity and security of that procedure is still very difficult. Blockchain technology provides a promising basis for creating and systems that are resistant to tampering with EMR data management and sharing. The blockchain-driven strategy for safe EMR sharing between healthcare organizations and research institutes is covered in this paper. We offer a framework created in collaboration with Stony Brook University Hospital to support data exchange for cancer patient care scenarios. A The implementation of the prototype confirms that the suggested system improves data availability, increases privacy, and permits precise, role-based access control.
The Penetration Power Of Water Towards Stones: A New Approach
Authors: Dr. Rishu Agarwal
Abstract: Penetration power of water is a different quality that makes universal solvent much more useful. There are various factors affecting penetration of water including pressure, velocity, temperature, present minerals in water. It also depends on the surface of stone on which water is thrown. Present study is focused on study of various factors affecting penetration power of water.
Smart Shared Container Space Management Platform with AI-Based Container Matching and Real-Time Booking System
Authors: Sharayu Anap, Divyanshu Rajhans, Atharva Naik, Srividhya Achanta, Vedant Jadhav
Abstract: The global logistics and transportation industry faces persistent challenges related to inefficient container utilization, manual space booking, and communication delays among stakeholders. The proposed system, Smart Shared Container Space Management Platform with AI-Based Container Matching and Real-Time Booking System, addresses these issues through an integrated, cloud-enabled digital platform that connects Container Providers and Traders in a shared, intelligent ecosystem. The platform leverages Artificial Intelligence (AI) for smart container- space recommendations, enabling efficient matchmaking based on trader requirements such as size, cost, duration, and proximity. The system ensures seamless, real-time operations through automated booking workflows, live availability tracking, and AI-assisted approvals—monitored via a centralized Admin Dashboard. Developed using a modern web technology stack, the system employs Next.js / React for an interactive frontend, Supabase for structured data storage, and Firebase for authentication and real-time synchronization. The AI chatbot is powered by the OpenAI API (or a custom GPT endpoint), providing users with intelligent assistance for queries and bookings. Tailwind CSS and ShadCN UI deliver a clean, responsive, and modern interface, while payment modules such as Stripe or Razorpay enable secure transaction processing. By integrating AI intelligence, automation, and real-time cloud connectivity, the proposed platform significantly enhances container space utilization, reduces idle storage time, and improves coordination between traders and providers. This system sets the foundation for a next-generation logistics management ecosystem that is scalable, data-driven, and powered by intelligent automation.
“Teacher-AI Trust Dynamics: Understanding the Psychological Barriers Adoption of Artificial Intelligence (AI) in Education”
Authors: prof. Dharmaraj s kumbar
Abstract: Artificial Intelligence (AI) has definitely revolutionised the world of science and technological era. Specifically, the introduction of AI has taken place in a revolutionary shift in the field of education. AI's capabilities are transforming education in the future, from automated assessment systems to personalised learning experiences. But even with this technological development, there is still an important issue with teachers and AI not working together. One of the greatest obstacles to fully deploying AI is this coordination gap. The complex interactions that result from integrating AI into the educational system are examined in this study report. It mostly concentrates on the difficulties in attaining harmony between educators, learners, and educational institutions. While AI has the ability to offer data-driven insights in the area of education, it currently falls short of meeting expectations of human interaction and educator's experience-based judgements. Additionally, this study explores the different impacts of applying AI on teacher performance. AI has the ability, on the one hand, to expand educational chances, lessen administrative tasks, and enhance educational standards. It can improve productivity for educators. However, there are questions about how AI will impact educator classroom management and professional ability. This study looks at how AI is transforming the job of educators and how it affects student-teacher engagement. Finding a balance between artificial and human intelligence is essential for the future of education. In order to make full use of AI in education, this study examines strategies for strengthening collaboration between educators and technology.
MoleculAR: An Autonomous Agentic Framework for Novel Molecule Discovery via Stability Analysis and ChEMBL Cross-Referencing
Authors: Rajeshkumar S. A, Vishrut Nath Jha
Abstract: The rapid evolution of artificial intelligence in chem- istry has enabled autonomous systems capable of exploring vast chemical spaces and identifying novel compounds with potential pharmacological value. We introduce MoleculAR, an autonomous agentic framework that integrates molecular relationship discov- ery, quantum-level stability analysis, and cheminformatics-based novelty verification. Given a set of input molecules, MoleculAR predicts potential co-functional partners using hybrid structural and functional similarity analysis, followed by energetic and stability evaluation through quantum chemical computations. Subsequently, the system performs compound novelty verification via cross-referencing with the ChEMBL database. Molecules that are predicted to be both chemically stable and absent from ChEMBL are shortlisted for further investigation. By combin- ing agentic reasoning, computational chemistry, and database- driven validation, MoleculAR establishes a closed-loop discovery pipeline that enhances efficiency in de novo compound identifica- tion. Experimental evaluations demonstrate MoleculAR’s ability to autonomously identify stable and novel molecular candidates across diverse chemical classes.
Web-Based Strategic Performance Management System For President Ramon Magsaysay State University
Authors: Carl Angelo S. Pamplona, Menchie A. Dela Cruz
Abstract: The web-based strategic performance management system for President Ramon Magsaysay State University (PRMSU) was developed to provide a more streamlined and centralized way of handling performance management–related tasks. The main purpose of the study was to evaluate the developed system in terms of software quality (using ISO/IEC 25010:2011 metrics), level of acceptability, and level of readiness of PRMSU. The study also identified significant differences between the evaluations of PRMSU staff and supervisors on (a) software quality of the system, (b) acceptability of functionality and performance, and (c) readiness for implementation in terms of information system facility and technical personnel. Based on the respondents’ evaluation, the developed system’s software quality was “Excellent,” its level of acceptability was “Highly Acceptable,” and its readiness for implementation was “Very Ready.” There was no significant difference between staff and supervisor evaluations on software quality or on any of the measured domains (Functional Suitability, Performance Efficiency, Compatibility, Usability, Reliability, Security, Maintainability, and Portability). Finally, the researcher provided recommendations including full implementation of the system, periodic re-evaluation and maintenance, user training, and ongoing studies to align with evolving trends such as implementation of data analytics and artificial intelligence functionalities
DOI: http://doi.org/10.5281/zenodo.17657287
AI-Powered Trip Planner Using Retrieval-Augmented Generation (RAG) Models
Authors: Yash Sharma, Mr. Ritesh Kumar Chandel
Abstract: Travel planning requires synthesizing large and diverse datasets including destinations, transportation, budgets, accommodations, user preferences, and seasonal variations. Traditional tools depend on static rules and manual inputs, making them inefficient for personalized planning. This research introduces an AI-powered RAG-based trip planner that integrates vector retrieval with generative reasoning. The system mitigates hallucinations, enhances real-world grounding, and produces optimized, personalized itineraries.
Enhanced Thesis: RAG-Based Intelligent Expense Tracker
Authors: Saransh Khanna, Mr. Ritesh Kumar Chandel
Abstract: This research investigates the development of an intelligent expense tracking system powered by Retrieval-Augmented Generation (RAG). Traditional expense tracking tools rely on structured inputs and static categorizations, creating friction for users who log expenses in natural language. The proposed system uses a hybrid architecture of vector retrieval and generative reasoning to extract accurate financial insights from unstructured text, improving reliability while reducing hallucinations commonly seen in standalone LLMs.
“UNI Verse: A Unified Digital Platform for Student–Faculty Interaction and Academic Coordination”
Authors: Reeva Rawat, Ronit Roy, Vivek Sharma, Soham Andhyal, Dr. Ravi Rai Chaudhari
Abstract: The UNI Verse platform is designed to create a more intelligent, engaged campus and digital learning environment. It provides a single platform for all organizational, informational, and engagement needs of students and faculty to facilitate their learning and academic experience. It gives students a centralized location to learn about their academic engagement, course schedule, office hours of professors, assignment due dates, and upcoming campus activities. UNI Verse will even offer reminders, to help keep students informed about deadlines & updates on campus. In addition to the academic purpose, UNI Verse allows students and faculty to have more substantive communications with the real-time direct messaging and meeting scheduling options. It even provides tools to navigate campus or even journal or share notes digitally, all to foster collaboration with classmates and engage as a learning community outside and inside of the classroom. Ultimately, UNI verse is a hub and usable system for productive, engaged, interactive, and organized campus life.
DOI: https://doi.org/10.5281/zenodo.17657734
A Review On The Ethics Of AI In Facial Recognition Technology
Authors: Kashish Aggarwal, Mr.Vikas kumar
Abstract: One of the most powerful and ethically debatable technologies of the 21 st century are Facial Recognition Tech- nology (FRT), which is also driven by Artificial Intelligence (AI). FRT can be used to automate the identification and verification of individual persons under different conditions, such as law enforcement, border control, and digital authentication, by relying on machine learning and deep neural networks. Even though the technology has a positive impact on reducing safety and efficiency, it poses significant ethical issues concerning privacy, data protection, bias, consent, and responsibility. The paper is a thorough overview of the ethical aspects of AI-driven facial recognition, the benefits that it has, and the vulnerabilities of this technology. It studies the problem of algorithmic bias, data governance, and ethical dimensions of surveillance-based applications. Global regulatory reactions to the subject, including the European Union General Data Protection Regulation (GDPR), the suggested AI Act, and other upcoming data protection regulations in the United States and India are discussed to point out differences in regulation. In addition, the paper explains mitigation measures such as fairness-conscious algorithms, transparency, and privacy- sensitive methods to encourage the responsible use of AI. This research highlights the importance of balancing between innova- tion and accountability as a means of seeking to fulfill societal needs without infringing on human rights by critically analyzing and conducting case-based reviews that conclude that facial recognition can be used to the benefit of society without taking away the rights of the people.
Optimizing Hospital Resource Utilization Through Edge AI
Authors: Sagar Gupta, Vikas kumar
Abstract: Hospitals often face immense challenges related to resource utilization and managing these resources efficiently in light of increasing demands from patients and the volume of data. The use of traditional centralized healthcare computing systems introduces latency and inefficiencies related to real-time decision-making. This chapter reviews how Edge AI can transform hospital resource utilization. By processing data closer to its source using edge devices, Edge AI allows for real-time analytics, proactive resource allocation, and responsiveness of operations. This chapter details the current challenges in hospital resource management, the architecture of an Edge AI-driven resource management system, and also discusses the case studies for their implementation. Quantitative evaluation regarding improved performances such as reduced wait time for patients and improvement in the bed occupancy rate is discussed. Integration of Edge AI with IoT and other emerging technologies such as 5G and federated learning is also considered as future work. Our analysis further shows that Edge AI increases not only hospital efficiency but also better patient outcomes through intelligent and timely interventions.
Color Tuning In Eu2+ Doped Barium Silicate Nanophosphor: A Facile Combustion Synthesis For Display Device Applications
Authors: M. Venkataravanappa, K.N. Venkatachalaiah
Abstract: Combustion synthesis method was used to prepare Europium doped Barium silicate nanophosphors. The crystalline structure from PXRD profiles showed that the fabricated sample have orthorhombic phase [JCPDS Card No. 78-1371] with a face group Pb nm- 62, with no variation in the diffraction profiles because of the inclusion of the Eu2+ions. The images are regular and irregular shapes with smooth surface were observed from SEM. The photometric spectra were studied for optimized nanophosphor displays green emission at ~ 505 nm due to the presence of Eu2+ ions corresponds to 5D07F2 transition. The CIE arrangement was green spread, which are basically near to the standard characteristics and Correlated Color Temperature (CCT) was acquired 12236K. These outcomes showed that the fabricated NPs can be viably utilized as green color part in the fabrication of white light emitting diodes.
Monitoring Of Bio Medical Devices Based On Electronics
Authors: Professor Kavita Singh
Abstract: The electronic monitoring of biomedical devices has revolutionized healthcare delivery by enabling real-time diagnostics, continuous physiological tracking, and rapid response mechanisms. This study reviews the technological advances underpinning electronic biomedical monitoring systems, describes key classes of devices, and discusses engineering challenges and prospects for future developments
EduHelm – Educationally Helping Mentor
Authors: Dhyanesh M, Dharshini S, Deepak P, Aisha Amna A, Mr. S. Dhinakaran
Abstract: EduHelm is an intelligent AI-driven career and learning platform designed to personalize and optimize student growth through dynamic learning paths, adaptive projects, and real-time skill tracking. The system leverages machine learning and large language models to recommend personalized roadmaps, micro-projects, and certification-based goals aligned with each user’s academic profile and aspirations. EduHelm integrates AI mentorship, progress analytics, and gamified challenges to foster continuous improvement and engagement. It also enables students to upload learning journals and research patterns, automatically analyzing them for feedback and improvement suggestions. Developed using a React frontend, Flask backend, and PostgreSQL database, with AI modules powered by OpenAI and Hugging Face, EduHelm delivers a seamless and intelligent experience that empowers learners to take control of their career growth in the digital age.
Traffic Control with Ambulance Sign and ANPR
Authors: Mr. Karthiban R, Tharun S, Naveen B, Yuvaraj S, Pragathiswaran G
Abstract: Urban site visitors congestion has come to be one of the most critical challenges confronted via cutting-edge towns. Emergency automobiles, wi-fi ambulances, enjoy frequent delays due to traffic wireless indicators and roadblocks, which may be deadly in lifestyles-threatening conditions. This paper proposes a smart visitors control device that mixes automatic wide variety Plate recognition (ANPR) and ambulance signal detection to make sure actual-time prioritization of ambulances. The proposed system makes use of digicam-primarily based vehicle identity, an IoT-enabled site visitors manage network, and adaptive sign timing to create a “inexperienced corridor” for emergency automobiles. Experimental simulations imply that the device can reduce ambulance waiting time at intersections via extra than 60%, improving the wi-fi of emergency reaction services. the combination of ANPR era permits automatic detection of ambulances without counting on guide systems or wireless tags, making it scalable and price-effective for clever city deployment.
Topic:Human–Robot Interaction: Current Trends and Applications
Authors: Sameer Agarwal, Vaibhav Kalukar
Abstract: Human–Robot Interaction (HRI) is an interdisciplinary field that examines how humans communicate, collaborate, and coexist with robotic systems. With major advancements in artificial intelligence, sensor technologies, and automation, robots are increasingly becoming interactive partners in healthcare, manufacturing, education, and personal assistance. This research investigates current trends in HRI, emphasizing the shift from traditional command-based systems to socially aware, adaptive, and collaborative robots. A qualitative review methodology is used to analyze studies published between 2015 and 2024, focusing on social robots, industrial cobots, healthcare and assistive robotics, and service-oriented systems. Findings reveal rapid growth in socially interactive robots, widespread adoption of collaborative robots in industry, and enhanced communication through AI-driven speech, gesture, and emotion recognition. Despite challenges such as limited emotional intelligence, ethical concerns, and high costs, the increasing integration of robots into human environments highlights significant potential for future development. The study concludes that HRI will play a crucial role in shaping intelligent, human-centric robotic systems, requiring continued research in transparency, trust, and ethical design.
Data Journalism Practices In Indian News Media: Opportunities And Challenges
Authors: Mr. Mayank Arora, Nupur
Abstract: The rapid expansion of digital technologies has transformed the landscape of contemporary journalism, bringing data-driven reporting to the forefront of news production. In India, the rise of data journalism—an approach that integrates statistical analysis, visualization tools, and storytelling—has opened new possibilities for accuracy, depth, and transparency in media reporting. Yet, the adoption of data journalism remains uneven, complicated by structural issues within Indian newsrooms, limited technological expertise, and the pressures of fast-paced news cycles. This paper investigates how Indian news organizations understand, adopt, and implement data journalism practices. It explores the professional, infrastructural, and ethical challenges that constrain data-driven reporting, while also identifying opportunities created by digital literacy, open-data movements, and audience demand for evidence-based journalism. Through a review of scholarly literature, industry reports, and comparative perspectives, the study highlights how data journalism in India stands at a critical intersection of innovation and limitation. The paper argues that although data journalism has the potential to strengthen public discourse and democratic accountability, its growth depends on sustained investment in training, technological resources, and editorial vision. Ultimately, the study positions data journalism as an evolving journalistic paradigm that can contribute significantly to India’s media ecosystem if supported by a culture of transparency, collaboration, and professional development.
Modeling Human Emotion Dynamics Using Chaos Theory
Authors: Manisha Rai, Vishal Rai
Abstract: Human emotions exhibit complex, nonlinear behaviors that traditional linear psychological models fail to capture adequately. This paper proposes a comprehensive framework for understanding emotional dynamics through the lens of chaos theory and nonlinear dynamical systems. We examine how concepts such as strange attractors, bifurcations, Lyapunov exponents, and phase space representations can illuminate the intricate patterns underlying affective processes. Empirical evidence from heart rate variability studies, electroencephalographic analyses, and longitudinal mood assessments supports the view that healthy emotional functioning corresponds to a bounded chaotic regime characterized by optimal complexity and adaptability. We further explore how deviations from this regime—manifesting as either excessive rigidity or instability—may underlie various mood disorders including depression, anxiety, and bipolar disorder. The paper presents mathematical formulations for emotional phase space dynamics, discusses computational approaches for reconstructing emotional attractor landscapes from empirical data, and outlines applications in clinical psychology, affective computing, and personalized mental health interventions. Understanding emotions as emergent properties of complex dynamical systems offers profound implications for diagnosis, treatment, and the development of emotionally intelligent technologies.
AI Enable GPS Based Employee Attendance And Live Monitoring System With Real Time Alerts
Authors: Himanshu Kumar Rai, Harsh Goyal, Dr. Anshu Gupta
Abstract: This research proposes a Geo‑AI based smart attendance monitoring system that will integrate Artificial Intelligence (AI) with Global Positioning System (GPS) geofencing to provide accurate, contactless, and secure attendance tracking. The proposed system will address persistent challenges such as proxy attendance, location spoofing via mock‑GPS tools, and manual recording errors by combining AI‑based facial recognition (with liveness analysis) and geolocation verification. A mobile front end will enable frictionless check‑ins, while a cloud back end will ensure secure storage, auditability, and real‑time analytics. We detail the proposed architecture, algorithms, and implementation plan that will use a React Native application, Node.js/Express services, MongoDB storage, and Python micro‑services for inference and anomaly detection. If successfully implemented, in a controlled deployment across two office sites the system is expected to achieve 98% attendance‑marking accuracy, is projected to reduce administrative overhead by approximately 60%, and is anticipated to deliver alert latencies below five seconds. We will compare our approach with RFID, fingerprint biometrics, and GPS‑only mobile apps, and we will report an ablation analysis to quantify the benefits of liveness checks and geofence validation.’
DOI: http://doi.org/10.5281/zenodo.17679353
Smartguard: Emergency Response System for Portable Device
Authors: Sabitha.K, Mohan Sundar.M, Santhosh. A. S, Sri Raghav. B. V, Supriya.A
Abstract: The Vehicle Accident Detection and Notification App is a mobile safety tool designed to identify vehicle accidents and automatically notify emergency services and family members. Utilizing the smartphone's accelerometer and gyroscope sensors, the app tracks sudden impacts, sharp turns, or rapid stops that suggest a potential collision. Upon detecting unusual movement, the GPS feature activates to pinpoint the exact location, ensuring that emergency responders can get to the scene quickly, even if the user is unconscious. The app automatically sends a comprehensive alert message that includes the user's information, timestamp, and precise coordinates to registered contacts. To minimize false alarms, it incorporates a brief confirmation timer that enables the user to cancel the alert. Additional functionalities such as a manual SOS button, cloud-based data storage, and automated calling improve reliability. Overall, the app provides an efficient, affordable way to enhance road safety and decrease fatalities.
Gesture Mouse controller
Authors: Dr.P.Guhan, Mr.C.Barath
Abstract: Gesture-controlled computers and laptops have recently become increasingly popular, with Leap Motion technology leading this innovation. This technique enables users to control certain system functions simply by moving their hands in front of a camera. Compared to traditional slides or overhead projectors, computer-based presentations offer greater interactivity through audio, video, and programmable elements, though they can be more complex to use. As technology continues to evolve, finding new and affordable ways to interact with computers has become essential, especially since touchscreens are not feasible for all applications. To address this, a virtual mouse system based on object tracking and hand gestures is proposed as an alternative to physical mice and touch interfaces. The system employs computer vision techniques using Python and OpenCV, with a webcam detecting hand movements through HSV color segmentation. Users can wear colored caps or tapes on their fingers to move the cursor and perform actions like left-click, right-click, and double-click. The camera feed is processed in real time and displayed on the screen, allowing smooth, contactless interaction.
Real Time Object Detection using YOLOv8
Authors: Mr.S. Sathish, Ms. A. Sangeetha
Abstract: Object detection is a key area in computer vision with wide-ranging applications such as autonomous driving, surveillance, and augmented reality. YOLOv8, an advanced version of the YOLO series, stands out for its high accuracy and real-time performance. This study focuses on the analysis and implementation of YOLOv8 for real-time object detection, emphasizing its architecture that employs a deep neural network to perform a single forward pass for predicting bounding boxes and class probabilities simultaneously. The model’s main components—backbone network, detection layers, and anchor boxes—work together to achieve fast and efficient detection. Practical aspects such as model optimization, GPU acceleration, and post-processing are also explored to enhance speed and accuracy. Experiments conducted on benchmark datasets and real-world data demonstrate YOLOv8’s effectiveness, proving it to be a robust and adaptable solution for real-time object detection tasks. This research contributes to the advancement of computer vision and provides practical insights for deploying YOLOv8-based detection systems across multiple domains.
A Novel Transformer Model With Multiple Instances Learning For Diabetic Retinopathy Classification
Authors: Mr. S. Kaushik Raj, Mrs. B. Shyamala Devi
Abstract: Diabetic retinopathy (DR) is one of the major causes of vision loss worldwide, making early and reliable detection extremely important. This work presents an advanced transformer-driven framework combined with a Multiple Instance Learning (MIL) strategy to classify DR using retinal fundus images. The transformer model effectively learns long-range relationships and contextual patterns, while the MIL approach analyzes image patches to highlight clinically significant areas. Together, this hybrid system delivers strong feature representation and stable classification performance, even with variations in image quality and resolution. Trained on a large and diverse dataset, the proposed model achieves higher sensitivity and specificity than many existing deep learning techniques. The system is designed to assist eye-care professionals by enabling accurate, timely assessments and providing a scalable solution suitable for extensive DR screening initiatives.
Smart LV Conductor Protection System
Authors: Priyanka K, Sasiprabha V, Shobaa P, Shreelinganaathan M, Srimukhi TG
Abstract: Low‑voltage distribution lines are widely used in residential and semi‑urban areas, where accidental conductor breakage or unintended grounding can pose severe safety hazards, result in prolonged power outages, and damage equipment. Current detection methods rely heavily on manual handling or high‑cost protection systems, resulting in delayed responses and increased operational risks. To address these gaps, this work proposes a cost‑effective Smart LV Fault Detection System capable of identifying conductor breakage and earth faults in real time. The system integrates voltage and current sensing units with an ESP32 controller that continuously analyses line behaviour, recognises abnormalities, and triggers immediate alerts. Visual and audio warnings are activated on-spot, while remote fault notifications are delivered via GSM‑based communication. A solar‑powered backup ensures uninterrupted operation during power failures. Experimental tests show more than 95% detection accuracy with a response time under one second. The proposed solution is lightweight, scalable, and suitable for both rural and urban power networks, providing improved safety, reduced downtime, and faster maintenance response.
Deployment Of Quantum Computing For Optimized Disaster Response Planning
Authors: V.Gomathi priya
Abstract: Disaster management has transformed from a reactive emergency-centred practice to a proactive, technology-driven discipline focused on minimizing the impact of both natural and human-induced hazards. This research highlights the rising frequency and severity of disasters such as earthquakes, floods, and cyclones, emphasizing the demand for integrated, systematic, and multi-sectoral strategies. The study examines how contemporary frameworks now prioritize preparedness through scenario planning, prevention, and capacity-building, supplemented by robust early-warning systems and risk reduction measures. The role of advanced technology—including decision support systems powered by artificial intelligence, geographic information systems, and, more recently, quantum computing—is analysed for its effectiveness in rapid data processing, predictive modelling, and optimized resource allocation. The research also reviews key disaster events from the past five years to illustrate ongoing challenges and responses, demonstrating the need for resilient infrastructure and coordinated recovery operations. Findings suggest that modern disaster management not only saves lives and reduces economic loss during crises but also promotes societal resilience and sustainable development through continuous innovation, capacity enhancement, and collaborative governance. This evolution ensures that disaster management remains a critical element for safeguarding communities in an era of mounting environmental and technological risk.
Explainable Artificial Intelligence Based Early-Stage Detection of Liver Cancer
Authors: Rohit.N, Dr.R. Kannadasan
Abstract: In human anatomy, the liver has a special feature called regeneration, and this feature helps the liver to grow back even after a large part of its organ is removed. Like regeneration, it helps maintain bile salts, protein synthesis, and detoxification. Irregular eating habits, sleep, and alcohol consumption increase liver function and cause various diseases such as fatty liver and other liver problems. Hepatocellular carcinoma is one of the liver diseases, and it is caused by the abnormal growth of cells in the liver. In such cases, liver regeneration is possible if the disease is identified at an early stage. To support this early identification, several research works have been carried out using both artificial intelligence and deep learning techniques. Therefore, this paper proposed an automated approach to identify liver cancer at an early stage through a segmentation and classification using deep learning techniques. The early-stage identification becomes possible with the dual stage of segmentation using U-NET and XAI. The U-NET helps to segment the image through its various texture properties of the image. Then, the XAI is used to analyze the individual regions of the image. This special feature of this approach is that it uses descriptive AI for classification, and this helps in identifying critical regions through heat maps and saliency maps. This technique was tested on a computed tomography dataset of liver images and its performance was evaluated in terms of precision, accuracy, recall and F1-score.
Contrast Enhancement Method For MRI And X-ray Images Based On A Modified Entropy Curve
Authors: Shashikant, Vinay Saxena
Abstract: MRI and X-ray images are widely used for detecting various prevalent diseases, and accurate diagnosis heavily depends on image quality. Often, images suffer from low contrast due to factors such as uneven or insufficient illumination, mo- tion of the subject or imaging device, and device-related imperfections, some- times accompanied by noise or artifacts. In such cases, an effective contrast enhancement algorithm that improves visibility without amplifying noise or ar- tifacts becomes crucial. In this work, we propose a simple yet efficient contrast enhancement method for medical images, based on dividing a modified entropy curve into two sub-entropy curves and combining it with homomorphic filtering. The proposed approach enhances image contrast while preserving important details and minimizing noise amplification. The effectiveness of the method is demonstrated through comprehensive qualitative and quantitative evaluations, highlighting its potential for improving medical image analysis.
DOI: http://doi.org/10.5281/zenodo.17697301
Moving Object Detected System
Authors: Ms. Haripriya, Vishva P, Varunkumar V.
Abstract: The Moving Object Detection System is a project that is based on vision and is aimed at the real-time identification and tracking of moving objects by applying the processing of images. The system can either analyze live video streams or recorded footage in order to detect the motion by the method of comparing the differences between two consecutive frames. The system that is executed on Python together with the OpenCV library performs background subtraction, frame differencing, and contour detection to find and draw the moving objects accurately. The technology has great potential in fields like surveillance, traffic management, and automation of security systems. The system is capable of detecting motion with high efficiency, requiring very little computational resources, and at the same time it is very easy to integrate with IoT and alert systems for added functionality. The system in question represents an efficient solution that can be applied in various contexts not only for motion detection but also for its cost-effectiveness and versatility. Moreover, the proposed system can handle indoor and outdoor setup variations like light changes and background noises through the use of filtering and thresholding techniques. Thus, it can already be a low-budget, real-time, and powerful solution for motion tracking in smart surveillance and safety applications. Further improvements can introduce the application of deep learning for the classification of detected objects and the provision of cloud-based alert systems that would further extend its range of use across various domains.
‘A Study Of Conflict Management Techniques In Large Organizational Settings’
Authors: Ms. Pooja Jagatnarayan Dixit
Abstract: Conflict is an unavoidable component of organizational life, particularly in large organizational settings characterized by interdependence, complex hierarchies, and resource competition. Effective conflict management is essential for sustaining productivity, fostering collaboration, and promoting positive workplace relationships. This study examines conflict management techniques used in large organizations, with a specific focus on how the choice of technique influences employee satisfaction and organizational performance outcomes. A mixed-methods approach involving literature synthesis and analysis of a representative dataset was used. Findings highlight that collaborative and compromising approaches tend to correlate most strongly with improved employee satisfaction and performance outcomes, while avoidance and competitive approaches exhibit weaker or inconsistent effects. The study provides implications for managers and organizational leaders regarding selecting appropriate conflict management strategies, and suggests future directions for organizational research on adaptive conflict intervention models.
Assessment Of Land Encroachment In Kwara State Polytechnic Permanent Site Using A Geographic Information Approach
Authors: Fashagba, I, Asonibare, R. O, Babatunde, K, Ajadi, B. S
Abstract: Land encroachment has become a major challenge affecting land administration and institutional expansion in Nigeria, particularly in peri-urban areas. This study assesses the pattern, extent, and progression of land encroachment on the permanent site of Kwara State Polytechnic, Ilorin, from 2004 to 2024 using aerial drone imagery and GIS techniques. The objectives were to: (i) identify areas encroached upon by surrounding settlements, (ii) determine the proportion of land currently occupied by the institution, and (iii) visualize encroachment trends through maps and imagery. Primary data were collected using a DJI Phantom 4 Pro drone, and the imagery obtained was processed into digital, detailed, topographic, and perimeter maps. Results show rapid and continuous expansion of settlements such as Ara, Ajia, Magaji, Budo-Oba, Yerima, Dangiwa, Akuo, and others, with several fusing into larger settlement clusters. Encroachment is most severe along the southern and eastern axes of the Polytechnic. Less than one-third of the acquired institutional land remains undeveloped, creating opportunities for illegal occupation. The study recommends the construction of a perimeter fence, government-led relocation of encroaching settlements, and the provision of institutional accommodation through public-private partnerships.
Role of AI in Autonomous Vehicle Decision Making
Authors: Mayuri R. Tone, Mohammad Abdul Razzaq, Syed Abdur Rasheed, Saud Ahamed
Abstract: Artificial Intelligence (AI) has become the cornerstone of autonomous vehicle (AV) technology, enabling self-driving systems to make complex, real-time decisions with minimal human intervention. By integrating machine learning, deep neural networks, computer vision, and sensor fusion, AI allows vehicles to interpret their surroundings, predict potential hazards, and plan safe and efficient routes. Decision-making in AVs relies on continuous data analysis from LiDAR, radar, cameras, and GPS to assess dynamic traffic conditions and respond adaptively to unpredictable environments. AI algorithms learn from vast datasets to improve accuracy, reliability, and safety, ensuring context-aware and ethical decision processes. This paper explores the pivotal role of AI in enhancing the perception, reasoning, and decision-making capabilities of autonomous vehicles, highlighting current advancements, challenges, and the potential impact of intelligent systems on the future of transportation.
Machine Learning Based System For Optimal Crop Recommendation
Authors: Yash Pratap Singh, Tanya Dwivedi
Abstract: Agriculture plays a major role in the economy and livelihood of many people, especially in developing countries. Farmers often face difficulties in choosing the correct crop because soil nutrients, weather conditions, and rainfall vary from place to place. Choosing the wrong crop can reduce yield and lead to financial loss. To solve this problem, a machine learning based crop recommendation system can be used. This system analyzes soil features such as Nitrogen (N), Phosphorus (P), Potassium (K), pH value, and environmental factors like temperature, rainfall, and humidity. Based on these inputs, the system suggests the most suitable crop for cultivation. In this research, different machine learning algorithms are studied, and Random Forest is selected theoretically because it provides high accuracy and stable performance. The main aim of this study is to support farmers in making better decisions, reduce risk, and improve productivity. The proposed approach is simple, understandable, and can be further developed into a mobile or web application for real-world use.
DOI: http://doi.org/10.5281/zenodo.17708787
Optimizing Energy Efficiency In Data Centers Through Nuclear Power Integration
Authors: Girish Kishor Ingavale
Abstract: The substantial expansion of hyperscale data centers, driven by exponential growth in cloud computing, artificial intelligence, and distributed computing architectures, has created a critical energy crisis characterized by unsustainable power consumption patterns and substantial carbon emissions. Conventional energy infrastructure, encompassing fossil fuel generation and intermittent renewable sources, demonstrates fundamental inadequacies in satisfying the stringent requirements for continuous baseload power, grid stability, and cost predictability demanded by contemporary data center operations. These deficiencies manifest through supply volatility, carbon intensity concerns, escalating transmission costs, and the inherent inability of renewable portfolios to guarantee uninterrupted power delivery without extensive energy storage systems. Nuclear energy presents a strategically viable solution, characterized by exceptional capacity factors exceeding 90%, negligible greenhouse gas emissions during operation, and energy density several orders of magnitude superior to alternative generation technologies. This article provides a rigorous examination of nuclear power integration strategies for data center infrastructure optimization, emphasizing quantitative improvements in energy efficiency metrics, decarbonization outcomes, and operational resilience. Through systematic comparative analysis employing established performance indicators and lifecycle assessment methodologies, this investigation substantiates the transformative potential of nuclear power adoption in enterprise-scale computing facilities. Principal findings demonstrate that nuclear-powered data centers achieve carbon emission reductions of 92-98% relative to coal-fired generation and 85-90% compared to natural gas combined-cycle plants. Economic analysis reveals levelized cost of energy (LCOE) reductions of 25-40% over 30-year operational horizons, accounting for capital expenditure amortization, fuel costs, and decommissioning provisions. Operational metrics indicate sustained power availability factors of 99.97%, representing a 15-20% improvement over grid-dependent configurations subject to transmission constraints and generation intermittency. Integration of nuclear baseload capacity with advanced power distribution architectures yields Power Usage Effectiveness (PUE) improvements of 35-45%, attributable to elimination of redundant uninterruptible power supply (UPS) systems and optimization of thermal management infrastructure. Small Modular Reactor (SMR) technologies and fourth-generation microreactor designs demonstrate applicability to distributed data center architectures, offering scalable deployment models ranging from 1 MWe to 300 MWe capacity with enhanced passive safety systems and reduced physical footprints. The substantial capital requirements for nuclear infrastructure development, estimated at $5,000-$8,000 per installed kilowatt for SMR deployments, are economically justified through comprehensive total cost of ownership (TCO) analysis incorporating energy price stability, carbon compliance costs, and operational expenditure reductions over multi-decade asset lifecycles. Regulatory frameworks governing nuclear facility licensing, operational oversight, and decommissioning obligations are examined within the context of data center deployment scenarios, identifying pathways for streamlined approval processes and public-private partnership structures. This research advances the academic discourse on sustainable computing infrastructure by providing evidence supporting nuclear power adoption as an essential component of decarbonization strategies for the information technology sector.
DOI: http://doi.org/10.5281/zenodo.17711318
Legal Aid Chatbot
Authors: Indu Shinde, Sarvada Anvekar, Purva Nargide, Shravni Shikhre, Shantu Pujari, Professor P.S.Pandhre
Abstract: Access to legal information and assistance remains a major challenge for many individuals due to high costs, lack of awareness, and geographical barriers. With the rapid growth of Artificial Intelligence (AI) and Natural Language Processing (NLP), chatbots have become an effective tool for improving access to information and services. This research paper presents the design, development, and evaluation of a Legal Aid Chatbot that provides preliminary legal guidance to users in a simple and accessible manner. The system uses NLP techniques, machine learning models, and a structured legal knowledge base to understand user queries and generate meaningful responses.
A Novel Performance-Optimized Chaotic Mapping Technique for Secure and Compressed Image Transmission
Authors: Dr. Latha H R
Abstract: Secure communication and computing is the vital requirement of the day as global networks and information systems are expanding like the big bang theory of the universe. People have started treating information as an asset. The information asset needs to be secured from attacks. Everything in the world is being upgraded to electronic communication and this requires protection against data fraud. Information has chosen different media like text, image, audio, video and multimedia for its existence. Cryptography is the science which provides techniques for securing information over network. Network security is the process of taking physical and software measures to protect underlying infrastructure. This paper introduces cryptography, chaotic cryptography, its computational power in image security. It proposes new sealion algorithm to increase the computational power of cryptographic algorithms. It also verifies the efficiency of proposed algorithm against benchmarks set for the security of images over network.
DOI: http://doi.org/10.5281/zenodo.17720340
Productivity And Carbon Footprint Analysis Of Organic Vs. Conventional Agroforestry Systems
Authors: Chidanandamurthy G
Abstract: This study compares productivity and carbon performance of organic agroforestry (ORG-AF) and conventional agroforestry (CON-AF) using paired plots under similar soil and climatic conditions. Six pairs of 0.25 ha plots were monitored for three years. System productivity was calculated as the sum of all marketable crop and tree products per hectare, while carbon stocks were derived from tree and crop biomass and soil organic carbon (0-30" " cm). Life cycle inventories of all inputs and field operations were compiled to estimate greenhouse gas emissions and carbon footprints per hectare and per kilogram of product. CON-AF achieved higher system yields (mean 5,808" " kgha^(-1)) than ORG-AF (mean 5,017 kgha^(-1)), a difference of about 16%. In contrast, tree biomass increment was greater in organic plots (3.55tha^(-1) yr^(-1)) than in conventional plots ( 2.55tha^(-1) yr^(-1)), and soil carbon increased faster in ORG-AF (0.43tCha-1yr^(-1)) than in CON-AF (0.16tCha^(-1) yr^(-1)). Total annual carbon stock change averaged 2.09tCha^(-1) yr^(-1) in ORG-AF and 1.36tCha^(-1) yr^(-1) in CON-AF. Area-based carbon footprints were 2,950 and 4,150" " kgCO_2-eq ha^(-1) yr^(-1) for organic and conventional systems, respectively, while product-based footprints were 0.59 and 0.71" " kgCO_2-eq kg^(-1). Both systems acted as net carbon sinks, but net carbon balance was much higher in ORG-AF (4.7vs.0.8tCO_2-eq ha^(-1) yr^(-1)). The results show that organic agroforestry can maintain high productivity while substantially improving carbon efficiency and climate mitigation potential.
DOI: http://doi.org/10.5281/zenodo.17720645
Interpreting The Urban Black Box: A Spatio – Temporal XAI Framework For Causal Feature Attribution In Smart City Prediction Models
Authors: Husna Sultana, Irfan Ahmed, Shivani
Abstract: Interpreting the Urban Black Box, the proliferation of sensors and Internet of Things (IoT) infrastructure in Smart Cities has enabled the development of highly accurate Spatio-Temporal Data Mining models, often relying on deep learning architectures like Graph Neural Networks (GNNs), for tasks such as traffic prediction, crime forecasting, and resource management. Despite their high predictive performance, these models remain "black boxes," hindering their adoption by urban planners and emergency services who require transparency and justification for critical operational decisions. This lack of interpretability poses significant challenges to accountability, auditability, and public trust. This paper addresses the critical need for Explainable AI (XAI) in the urban domain by proposing a novel Spatio-Temporal XAI (ST-XAI) Framework designed for Causal Feature Attribution. Our framework leverages a modified version of SHapley Additive exPlanations (SHAP) combined with the inherent spatial and temporal structure of the data to provide granular, instance-based explanations. The proposed methodology focuses on Temporal Attribution: Quantifying the specific influence of various look-back time windows (e.g., data from the last hour vs. data from 24 hours ago) on the current prediction. Spatial Attribution: Identifying and weighting the contributing influence of specific geographic nodes, links, or neighboring zones within the network structure. Causal Inference: Moving beyond mere correlation by prioritizing features that exhibit a strong, temporally preceding impact, providing a more actionable justification for the prediction. We demonstrate the ST-XAI Framework on a smart traffic prediction model, showing how it successfully translates opaque deep learning outputs into clear, human-understandable narratives. The results illustrate that our framework not only validates model efficacy but also acts as a vital debugging tool for city engineers, transforming black-box predictions into accountable and actionable urban intelligence.
DOI: http://doi.org/10.5281/zenodo.17720787
AI-Based Career Advisor
Authors: Radhika Kulkarni, Tejal Mungase
Abstract: The current job market introduces major difficulties in effectively connecting skilled candidates with suitable employment opportunities. This paper proposes an AI-powered career advisory system using Natural Language Processing (NLP), Machine Learning (ML), and Large Language Models (LLMs) to automate career guidance. The proposed system unites four core modules: semantic-based resume parsing using transformer models, intelligent job matching using BERT embeddings, complete skill gap analysis with customized learning recommendations, and AI-driven resume optimization for Applicant Tracking System (ATS) compatibility. The system implements a three-tier architecture with React.js frontend, FastAPI backend, and a hybrid database layer. This Stage 1 paper presents problem identification, literature survey, system architecture, and methodology. The framework addresses critical gaps in career advisory services through conceptual understanding, customized guidance, intelligent automation, and access to professional career counseling.
SENTIMENT 360
Authors: Srujan Gatla, Teja, Surya, Shashi Kumar
Abstract: Sentiment analysis on social media is a natural language processing technique used to extract subjective information and opinions from user-generated content on various social media platforms, such as Twitter, Facebook, and Instagram. The goal of this project is to perform sentiment analysis on social media data related to a particular topic or brand, such as a product launch or a social issue. Social media data will be collected using relevant APIs or web scraping tools and preprocessed by cleaning and filtering out irrelevant or spammy content. A sentiment analysis model, such as a lexicon-based or machine learning model, will be applied to classify the sentiment of the content as positive, negative, or neutral. Results will be visualized and analysed using various techniques and tools, such as word clouds, bar charts, and time series analysis, to gain insights and make data-driven decisions based on public opinion. Challenges in social media sentiment analysis include the use of slang, emojis, and hashtags, as well as the need to handle multilingual con tent. Sentiment analysis on social media can be a powerful tool for understanding public opinion, customer satisfaction, and brand reputation, and making data-driven deci- sions in various domains, such as marketing, politics, and social sciences.
Advanced Cooling Systems for Nuclear-Powered Data Centers
Authors: Girish Kishor Ingavale
Abstract: The demand for computational power in nuclear-powered data centers requires effective thermal management. Traditional cooling methods are inadequate for the heat generated in these environments. This article examines advanced cooling systems for nuclear-powered data centers, focusing on energy efficiency, safety, and performance. Analyzed technologies include liquid cooling, immersion cooling, free cooling, and hybrid systems. Findings show these systems reduce energy consumption by up to 50%, improve PUE by 20-35%, and enhance computational performance by 15-20%. They also reduce server failure rates and improve reliability. Initial investment is offset by long-term energy cost savings and reduced maintenance. This article highlights the importance of advanced cooling systems for sustainable and efficient operation of nuclear-powered data centers.
Invest Wise – Ai Driven Investment Portfolio Recommendation System Based On Risk Profiling And Market Analytics
Authors: Ayush Sadanand Bhuyar, Bhakti Kiran Kumar Yete, Jayendrasin Rathod, Jayendrasin Rathod, Mr. Yatin Shukla
Abstract: The growth of retail participation in financial markets has created a strong need for intelligent, transparent and easy-to-use investment advisory tools. Beginner investors in particular often struggle to understand their own risk-bearing capacity and to select a suitable mix of equity, bonds and cash instruments. This paper presents INVESTWISE, an AI‑driven investment portfolio recommendation system that models user risk profiles using questionnaire responses and combines them with live market fundamentals such as P/E ratio, beta, dividend yield and sector information. The backend is designed using a hybrid MongoDB and relational database approach, while the frontend delivers a modern web dashboard that visualises allocations, recommended stocks and market movers. Experimental evaluation on simulated user profiles and live NSE data demonstrates that the system can generate consistent, risk-aligned portfolios with low response time, making it suitable for real‑time decision support.
Smart Gaming Supervision System
Authors: Goutami Bankapure, Rakshita Giri, Nandini Khadakhade, Sneha Teli, Aishwarya shengar, pallavi pandhare
Abstract: The rapid growth of digital gaming has led to increasingly complex behavioral challenges, particularly among adolescents and young adults. Excessive gameplay, exposure to toxic communication, and unhealthy engagement patterns continue to raise concerns regarding digital well-being. Existing monitoring tools typically offer only partial solutions, such as parental controls or time-restriction features, and lack the ability to analyze user behavior holistically. To address these gaps, this research presents the Smart Gaming Supervision System, an integrated AI-driven framework designed to promote healthier gaming habits while reducing abusive interactions. The system combines real-time gameplay duration monitoring, multilingual text toxicity detection, voice-based abusive speech recognition, motivational prompt generation, and behavior-based reward mechanisms. Leveraging state-of-the-art technologies such as XLM-R transformer models for text analysis, Whisper-based speech-to-text pipelines, and a rule-based behavioral engine supported by SQLite storage, the system continuously evaluates player behavior across multiple channels. Real-time alerts, warnings, and positive reinforcement are generated to encourage self-regulation and promote responsible gaming. Experimental evaluation demonstrates that the system achieves high accuracy in toxicity detection, effective time-limit enforcement, and improved user engagement through positive reinforcement techniques. The proposed solution highlights the potential of combining machine learning, psychology-driven reward systems, and digital wellness principles to create a comprehensive, scalable, and user-centric gaming supervision platform. This work contributes a novel and practical approach toward fostering safe, balanced, and respectful digital gaming environments.
AI in Everyday Life: How Artificial Intelligence Shapes Modern Applications
Authors: Ishaan Iyer, Abhijeet Anand Aiwale
Abstract: From voice assistants and recommendation systems to navigation tools and personalized learning, AI shapes how people live, work, and interact with technology. This rapidly growing area of research has transformed AI from a concept of the future to a technology that permeates almost every aspect of human life. This paper will discuss the integration of AI into everyday applications, identify common areas where students interact with AI unknowingly, and examine its positive impacts and potential ethical concerns. This study is based on a survey among first-year engineering students and a review of secondary literature. The results show that while AI enhances convenience and efficiency, the awareness of its mechanisms and ethical issues remains limited.
A Review Of XGBoost And Supervised Learning Approaches For Crop Recommendation Using Soil Composition Data
Authors: Harshal Patel, Jitendra Shrivastav, Kamlesh Patidar
Abstract: The integration of machine learning into agriculture has shown great promise in improving decision-making, particularly in crop recommendation systems. This review focuses on XGBoost and supervised learning approaches for crop recommendation based on soil composition analysis. Soil properties such as pH, nutrient levels, moisture, and texture play a crucial role in determining crop suitability and yield. However, many existing models fail to adequately capture the complex interactions among these variables or account for regional soil variability. By examining current supervised learning methods and the growing application of XGBoost, this paper highlights their strengths, limitations, and potential for enhancing prediction accuracy. Furthermore, it identifies key research gaps, including the scarcity of diverse soil–crop datasets and the need for models that can adapt across geographical regions and climates. The review concludes that integrating advanced supervised learning with robust soil data can significantly optimize crop recommendations, promoting sustainable and precise agricultural practices.
Comparative Analysis Of Deep Learning Models For Brain Tumor Detection With Superior Performance Of InceptionResNetV2
Authors: Pratik Pandey, Nagendra Patel
Abstract: Brain tumor detection through magnetic resonance imaging (MRI) plays a crucial role in early diagnosis and treatment planning. This study presents a comparative analysis of five deep learning models—CNN, ResNet50, U-Net, YOLOv7, and InceptionResNetV2 for accurate classification of brain tumors. The dataset was preprocessed with cleaning, augmentation, and normalization before training and evaluation. Performance was measured using accuracy, precision, recall, and F1-score. Results demonstrate that all models achieved strong outcomes, but InceptionResNetV2 significantly outperformed others, reaching nearly 100% across all metrics. This superior performance highlights its effectiveness in minimizing false positives and false negatives, thereby offering a robust tool for clinical applications. The findings emphasize the importance of advanced deep learning architectures in medical imaging for reliable tumor detection.
Trip Crafters-Crafting Experience For Travelers
Authors: Harsh Manvani, Niraj Shrimali, Sahil Ahir, Ved Patel
Abstract: The tourism sector is changing quickly as digital tools be- come more common, but many travelers still struggle to plan trips that are both convenient and affordable. A major problem is the absence of a single platform that can offer clear, reliable, and budget-focused itineraries. Although there is plenty of information available on travel websites and search engines, it is scattered and often difficult to com- pare, which makes the planning process tiring and confusing.Another issue appears once tourists reach their destination. Local transport frequently becomes a challenge, especially for first-time visitors who may end up paying high prices or relying only on taxis and ride-hailing services. This also reduces their chances of exploring places more freely and experiencing the local culture. In many tourist locations, two-wheeler rentals are actually a more convenient and enjoyable way to move around, yet they are not well integrated into existing travel systems.To overcome these problems, this study proposes an AI-based platform that combines personalized trip planning with a peer-to-peer bike rental service. The system uses machine learning to create tailored itineraries by collecting and organizing travel data from multiple sources. At the same time, it offers a safe and easy-to-use marketplace where travelers can rent two-wheelers from local owners. By bringing together artificial intelligence and community-driven mobility options, the platform aims to make travel more accessible, reduce instances of overcharging, and improve the overall experience for tourists.
DOI: http://doi.org/10.5281/zenodo.17746212
World Trip Deal
Authors: Radhika Marathe, Jagruti Patil, Vraj Patel, Nakka Narendar
Abstract: The travel and tourism industry is rapidly transi- tioning toward digital ecosystems that provide seamless user ex- periences. However, most travel applications remain fragmented, requiring customers to access different platforms for hotels, packages, transfers, and visa services. World Trip Deal resolves this by offering an integrated web platform that centralizes all essential travel-related modules. The system is built using Angular, Node.js, Express, Firebase, and MongoDB, ensuring scalability, responsiveness, and security. This paper presents the system architecture, methodology, workflow, implementation details, and performance evaluation of the platform.
Beyond Quiet Quitting: Naked Resignation in The Digital Workforce Of Pune’s IT Industry
Authors: Dr. Prabodhini B Wakhare, Bhagyashree S. Borhade, Professor Dr. Shivaji Borhade
Abstract: This study investigates the emerging trend of naked resignation among the digital workforce with a focus on IT professionals in Pune (India). Naked resignation refers to employees leaving abruptly without prior communication, gradual disengagement or attempts at negotiation. Utilising a mixed-methods approach the research gathered responses from IT employees and HR professionals to examine how factors such as techno-stress, burnout, emotional fatigue, workplace relationships and organisational trust influence resignation intentions. The findings reveal that emotional fatigue is the most significant factor followed by burnout and techno-stress. Participants noted a diminished trust in leadership and a sense of organisational disconnect as contributing factors to sudden resignations. Qualitative responses indicate that employees view naked resignation not as an impulsive decision but as a necessary reaction to psychological strain and declining workplace well-being. The study concludes that resignation is increasingly seen as a means of setting boundaries rather than a response to isolated incidents. The results underscore the need for improved communication channels, mental health resources and employee-centered leadership practices. This research sheds light on the evolving behaviours in the post-pandemic workforce and adds to the literature on employee retention, digital work culture and mental well-being in technology-driven organisations.
AI-Driven Smart Farming System
Authors: Smita Tanvade, Jyoti Sathe, Niha Kudchikar, Samruddhi Patil, Mrs. P.D Nasalapure
Abstract: Smart farming integrates advanced technologies such as the Internet of Things (IoT), artificial intelligence (AI), and data analytics to improve the efficiency, productivity, and sustainability of agricultural processes. This paper presents an AI-driven smart farming system that uses real-time soil data to help farmers make accurate and effective decisions. The system collects essential soil parameters such as moisture, pH, temperature, electrical conductivity, and nutrient levels through IoT sensors and analyzes them using machine learning algorithms. Based on this analysis, the system predicts the most suitable crop for the existing soil condition and also recommends the appropriate fertilizers needed to improve soil health and support optimal crop growth. By reducing manual guesswork, minimizing resource wastage, and offering clear data-based guidance, the proposed system helps farmers increase productivity, reduce costs, and adopt sustainable farming practices. Cloud integration and an easy-to-use interface ensure that the solution remains accessible, scalable, and suitable for different types of farms. Overall, this AI-driven system provides a practical and efficient approach to modern agriculture, enabling higher yield, better soil management, and smarter decision-making.
Appraisal of Groundwater Quality, A Case study of Panruti Block, Cuddalore District.
Authors: P. Ramamoorthy
Abstract: The study area Panruti Block has chosen to assess the groundwater quality. There are 15 groundwater samples were collected and analyzed for various physical and chemical parameters such as pH, TDS, EC, Ca, Mg, Na, K, Cl, NO3,SO4,Fl, etc. The groundwater samples are compared with the WHO standards. The quality of ground water in the study area is fresh to Brackish, slightly basic in nature, Salinity nature.
Simulation And Analysis Of A Cascaded 4-bit Digital Comparator Architecture Extended To 16-bit Using MATLAB/Simulink
Authors: Mr Sandeep Tandon
Abstract: Digital comparators are fundamental building blocks in arithmetic and control processing units, forming an essential component of ALUs, microprocessors, DSP modules, and embedded logic devices. Traditional 4-bit comparators offer a limited operational range, and real-time digital systems require scalable multi-bit comparison architectures. This paper presents a modular, cascaded comparator design methodology that extends a basic 4-bit comparator to 8-bit and 16-bit architectures using MATLAB/Simulink. The work proposes a structured cascading mechanism using hierarchical decision logic (GT, EQ, LT propagation) and evaluates performance through extensive simulation-based analysis. Functional verification, simulation timing behavior, switching activity estimation, and scalability evaluation are conducted. Results demonstrate that the proposed comparator architecture maintains accuracy, modularity, and linear scalability, making it suitable for integration into FPGA, ASIC, and real-time embedded systems.
Design And Implementation Of An Intelligent Career Guidance Ecosystem With ATS Optimization And Personality-Based Recommendation Engine
Authors: Ankit Verma, Anmol Soni, Arnav Singh, Adnan Khan, Ahtesham Farooqi
Abstract: This paper presents AI Career Navigator, a com- prehensive AI-driven career guidance platform integrating ten essential modules: career recommendation, resume analysis, job search aggregation, interview preparation, cover letter genera- tion, skill gap analysis, career trend analytics, learning resources, conversational AI chatbot, and LinkedIn profile optimization. The system employs a hybrid methodology combining NLP- based resume intelligence, psychometric profiling using the Big Five Personality Model, supervised machine learning for career prediction, and ATS-based scoring mechanisms. The frontend ar- chitecture leverages React with TypeScript, enhanced by Tailwind CSS, ShadCN UI, and Framer Motion, while the backend imple- ments advanced AI/NLP/ML algorithms for semantic analysis, personality classification, and intelligent career-profile matching. The modular architecture incorporates domain-skill mapping, career-interest correlation, and real-time trend analytics with adaptive feedback loops to generate context-aware recommenda- tions. Comparative evaluation demonstrates that AI Career Navi- gator significantly outperforms conventional systems by providing data-driven insights, holistic skill assessment, and personalized recommendations, thereby enhancing graduate employability and reducing career mismatch rates observed in traditional models.
DOI: http://doi.org/10.5281/zenodo.17761603
Identifying and Analyzing the Barriers to Adopting Green Concepts in The Sri Lankan Construction Industry
Authors: G S P Gunasekara
Abstract: In The Sri Lankan construction industry has a central position in the national development, instead of being one of the worst agents of environmental destruction due to energy consumption and production of waste and carbon dioxide. As response, strategies to reduce the environmental impact of building operations have come into the limelight in the form of green concepts and sustainable building practices in the world. Although sustainability programs have been increased and structures have been designed like the GREENSL Rating System, there is still little uptake of green practices in Sri Lanka. This paper will seek to establish and discuss the challenges to the adoption of green construction concepts in the Sri Lankan context. Based on a qualitative content analysis of twenty academic and institutional sources on local repositories, such as the University of Moratuwa, General Sir John Kotelawala Defence University, and the Green Building Council of Sri Lanka, the research synthesizes research results on the economic, institutional, technical, and cultural levels. Findings indicate that the initial high costs, lax regulatory implementation, low technical capacity and deep-rooted behavioural resistance are all complex and interdependent webs of constraints. The lack of financial incentives, poor awareness and disjointed policy frameworks are the forces that reinforce these barriers. The paper suggests a conceptual framework that demonstrates the relationship between these barriers and provides policy, industry, and research solutions to promote integrated solutions. It concludes that a rational system of national policy, coupled with specific capacity building and financial solutions, is essential in achieving mainstreaming of sustainable construction and long-term environmental resilience in Sri Lanka.
Integrated Risk Model Combining Financial, OSH, and ESG Factors for Modern Corporations
Authors: Dr. Priyanka
Abstract: Corporations today operate in environments marked by financial volatility, sustainability pressures, rising workplace safety expectations, and increased scrutiny from regulators and stakeholders. Traditional risk-management frameworks—which focus mainly on financial indicators—are no longer sufficient. This study proposes a comprehensive Integrated Risk Model (IRM) that merges Financial Risk, Occupational Safety & Health (OSH) Risk, and Environmental, Social & Governance (ESG) Risk into a single evaluative structure. Using comparative analysis, survey data, secondary financial records, and regression modelling, the paper examines how OSH and ESG performance influence financial resilience and overall corporate stability. Findings suggest that firms with strong OSH and ESG systems consistently experience fewer disruptions, lower costs, enhanced productivity, and significantly higher financial resilience scores. The research demonstrates that integrating OSH and ESG risk indicators into financial risk management leads to more accurate predictions of long-term corporate performance.
DOI: https://doi.org/10.5281/zenodo.17775670
The Impact Of Artificial Intelligence On Human Resource Efficiency: Enhancing Teachers’ Performance In Educational Institutions_819
Authors: Mohamad Siraj
Abstract: This study examines the impact of artificial intelligence (AI) on human resource efficiency among secondary teachers in international schools. While AI is increasingly promoted as a means to reduce teacher workload and enhance productivity, empirical evidence from school settings—particularly international schools—remains limited. The research focuses on how AI is used in teachers’ work, how it affects perceived workload and efficiency, and how organisational conditions shape these effects. A quantitative, cross-sectional survey design was employed. Data were collected from 150 secondary teachers working in 18 international schools, using a structured online questionnaire. The instrument captured AI usage patterns, perceptions of AI (perceived usefulness, perceived ease of use, AI anxiety, autonomy), HR-efficiency outcomes (perceived administrative workload, instructional efficiency, overall efficiency, job satisfaction) and organisational factors (leadership support, training and infrastructure). Descriptive statistics, reliability and factor analyses, correlations and multiple regression models were used to analyse the data. Findings indicate that AI is widely used for lesson planning, resource creation and assessment, but less so for administrative work and rarely for pastoral care or live classroom interaction. Teachers generally perceive AI as useful and moderately easy to use, yet administrative workload remains high. Perceived usefulness and actual AI usage are strong positive predictors of instructional and overall efficiency, and are associated with somewhat lower perceived administrative workload. AI anxiety is linked to higher workload and lower efficiency. Organisational support—through leadership, training and clear policies—consistently amplifies positive outcomes and reduces anxiety. The study concludes that AI currently offers incremental rather than transformative efficiency gains. Its contribution to human resource efficiency and teacher well-being depends on strategic, task-focused implementation and supportive organisational conditions, rather than on technology alone. Recommendations are offered for school leaders, HR practitioners and teachers, alongside directions for future research on AI, workload and sustainability in international education.
DOI: http://doi.org/10.5281/zenodo.17785987
Development of a Low Cost 3D Printed Myoelectric Hand using EMG and ECG Signal Fusion
Authors: Ayush Kumar, Abhendra Pratap Singh, Uma Gautam, Nandini Sharma
Abstract: For amputees in underdeveloped nations, the high expenses and complexity of commercial upper-limb prosthetics continue to be major obstacle to accessibility. The design, development, and testing of an affordable, 3D printed bionic hand with a dual-sensor interface is presented in this study. This system incorporates Electrocardiography(ECG) as a secondary control modality for improved stability and mode switching, in the contrast to standard myoelectric systems that only use Electromyography (EMG) and are vulnerable to motion artifacts and false triggers. Autodesk Fusion 360 was used to design the mechanical structure, which was then made of polylactic acid (PLA) and has a tendon-driven actuation mechanism controlled by SG90 servo motors. Band-pass filtering and threshold-based algorithms are used by the control logic, which is implemented on an Arduino Uno, to handle biosignals in real time. The ECG signal successfully serves as a safety interlock, and experimental results show a system latency of about 190ms and a strong object grabbing capacity. The combination of multimodal biosignals with additive manufacturing can produce a dependable, accessible, and useful prosthetic solution, as evidence by the fact that the entire fabrication cost was kept under 10000 INR.
DOI: https://doi.org/10.5281/zenodo.17786605
Parental Control Time Lock App_569
Authors: Hitanshu Bodana, Ronak Singh, Krish Patel
Abstract: The increasing immersion of children in digital ecosystems—mobile applications, virtual environments, and gamified digital spaces—has amplified concerns around excessive screen time, addictive applications, and exposure to harmful content. Traditional parental control systems rely on rigid blocking mechanisms, often creating resistance among children and lacking nuanced, interactive behaviour regulation. This paper presents a Parental Control Time Lock App, a collaborative digital parenting framework integrating real-time monitoring, application-level time budgeting, and OTP-based conditional unlocking. Developed using Kotlin (Android) and a Spring Boot backend, the system enforces usage limits and enables parents to remotely authorize temporary access by providing a secure one-time password. The application incorporates behavioural design elements to promote healthy usage rather than punitive restriction. Testing conducted across 20 families demonstrated a 32% reduction in unregulated screen time and high parental satisfaction. The study contributes to the domains of digital wellbeing, child safety, and human–computer interaction by proposing a hybrid control model that balances autonomy, security, and trust.
Predictive Analytics In Big Data
Authors: Dr. C.K. Gomathy, Swaminathan S, Rohith Reddy S, Monishkumar V
Abstract: The exponential growth of data generated from social media, IoT devices, enterprise systems, online transactions, and cloud platforms has transformed big data analytics into a critical domain for modern organizations. Predictive analytics, a major branch of data analytics, leverages statistical models, machine learning algorithms, and AI-driven techniques to forecast future events and uncover hidden patterns within large-scale datasets. Traditional analytical approaches are increasingly inadequate for handling the velocity, variety, and volume of modern data environments. With advancements in distributed computing frameworks such as Hadoop, Spark, and cloud-native analytics systems, predictive analytics has become a powerful enabler for data-driven decision-making. This paper explores the principles of predictive analytics in big data environments, examining its methodologies, architectures, machine learning techniques, and industry applications. A detailed literature survey highlights developments from 2015–2025, focusing on model optimization, scalable processing, and domain-specific predictive frameworks. The methodology outlines an end-to-end predictive analytics pipeline, including data ingestion, preprocessing, model training, evaluation, and deployment. Implementation details demonstrate how predictive models can be integrated into distributed systems using containerized microservices and scalable cloud architectures. Experimental results confirm the effectiveness of the model in supporting real-time predictions, trend analysis, and intelligent automation. The findings emphasize predictive analytics as a foundational tool across sectors such as finance, healthcare, retail, manufacturing, and cybersecurity.
DOI: http://doi.org/10.5281/zenodo.17798573
Federated Learning In Cloud–Edge Environments For Privacy-Preserving Cognitive Computing
Authors: Swaminathan S, Rohith Reddy S, Dr. R. Prema, Assistant Professor
Abstract: Federated learning (FL) enables collaborative machine learning without transferring raw data to a central server, thereby ensuring privacy and security. When integrated with cloud–edge environments, FL enhances cognitive computing by enabling real-time, decentralized intelligence. This paper explores the architecture, opportunities, applications, and challenges of federated learning for privacy-preserving cognitive systems. It highlights how cloud–edge collaboration improves data security, latency, scalability, and model performance while addressing integration barriers, communication overhead, and ethical concerns.
Evaluation of Green Plant Extracts as Corrosion Inhibitors for Mild Steel in Acidic Medium
Authors: Dr. P.Gowsalya, M.Revathi, K.Palanisamy, S.Saranya
Abstract: The corrosion inhibition efficiency of Aster chinensis extract on mild steel in 1 M HCl was examined using weight loss and electrochemical techniques. The extract significantly reduced the corrosion rate, and inhibition performance increased with increasing inhibitor concentration. Polarization studies confirmed a mixed- type inhibition behaviour, while EIS results showed higher charge transfer resistance, indicating strong adsorption of phytochemical constituents on the steel surface. Adsorption obeyed the Langmuir isotherm, suggesting monolayer formation. Surface characterization by FT-IR and SEM supported the formation of a protective film on the metal surface. The extract also facilitated the reduction of Ag⁺ to Ag⁰ nanoparticles, confirming its dual function as a green corrosion inhibitor and an effective reducing agent. Overall, Aster chinensis demonstrates excellent potential as an eco-friendly and sustainable corrosion inhibitor.
Advancing Human–Computer Interaction Through Cognitive Computing And Natural Language Processing
Authors: VD Sasank, Vishnuvel Ragavan K E C, Dr. R. Prema
Abstract: Human–Computer Interaction (HCI) is rapidly transitioning from conventional interfaces to intelligent, context-sensitive systems driven by Cognitive Computing and Natural Language Processing (NLP). Traditional input–output interactions lack the capability to understand user intent, emotions, and behavioural patterns. Cognitive computing enables machines to simulate human mental processes such as perception, reasoning, and learning, while NLP supports natural communication through speech and text. This paper presents an integrated cognitive–NLP architecture for adaptive and human-centred interaction. A detailed literature review highlights existing HCI limitations, including lack of emotional understanding, multilingual constraints, system bias, and poor contextual reasoning. A proposed hybrid model is introduced, combining behavioural sensing, cognitive modelling, semantic processing, sentiment analysis, and feedback-driven learning. Applications in healthcare, accessibility, virtual assistants, smart environments, and education are examined. The paper concludes with challenges in ethics, privacy, and data bias, followed by future advancements such as emotion-aware agents, multilingual cognition, and real-time brain–computer interfaces.
Implementing Blue-Green Infrastructure In GIS For Climate Impact: A Case Study Of Chennai, Tamil Nadu, India.
Authors: Raegan Alex. A, Jyothi Gupta
Abstract: Aim: This paper reviews urban expansion through space and time in Chennai city (a megapolis of India) based on GIS technology etc, and investigates ways to integrate blue-green infrastructure, i.e., wetlands, riverscapes, greenscapes into the development for climate adaptation, resilient cities & sustainable growth. Research Question: What can GIS show us about Chennai’s ancient land use changes and urban expansion? What are the possibilities of climate-proofing resilience and promoting sustainable urban development with blue-green infrastructure? Methodology: Ten research papers were analyzed, and core concepts were determined as well as gaps identified. The Shapefile/GIS data was obtained and studied to observe the pattern of city growth. For identifying potential areas for BGI and urban resilience interventions, the land use/land cover changes were mapped. Results: GIS based analysis identified speedy urbanization in and around OMR and GST Road at the cost of wetlands, agricultural land, and open spaces. Map of vegetation, water bodies showed areas to reclaim for restoration. The rivers, sewers, sumps and metro lines became avenues for blue-green infrastructure projects. Zones for planning interventions were determined using highway networks and administrative boundaries. A mapping of priority areas for flooding, urban cooling and sustainable development was conducted. Conclusion and Limitation: Urbanization of Chennai has shrunk green and blue spaces, a situation that emphasizes the urgency for incorporating blue-green infrastructure to improve climate resilience. Challenges that people faced around the country included access to up-to-date ward boundaries, transforming shapefiles and high prices of datasets. Sensitve areas for restoration and management had been successfully mapped if imperfectly served by maps
A Comprehensive Review Of Advances In Smart Agriculture
Authors: Rachna Chandra, Manoj Mittal, Anmol Dobriyal, Suneet Bhalla, Utsav
Abstract: We analysed the peer-reviewed literature published between 2021 and 2025 focusing on smart agriculture techniques which integrates advanced technologies such as the Internet of Things (IoT), wireless sensor networks (WSN), machine learning, artificial intelligence (AI), unmanned aerial vehicles (UAVs), remote sensing, edge–fog–cloud computing, and renewable energy systems to enhance farming efficiency and sustainability. Recent research shows significant progress in precision irrigation, automated monitoring, and data driven decision support systems that optimize water usage and improve crop yield. This paper presents a comprehensive review of forty research papers focused on smart agriculture techniques, highlighting IoT-based soil moisture monitoring, LoRaWAN enabled long-range communication, machine learning-based disease detection, UAV assisted irrigation planning, and solar powered intelligent water systems. The findings show that integrating smart technologies enables resource optimization, climate resilience, and scalable automation across diverse agricultural scenarios. The study contributes a consolidated view of recent advancements to support the development of sustainable agriculture.
Big Data In Healthcare
Authors: Dr. C.K. Gomathy, VD Sasank, R Srishreya
Abstract: Big Data in healthcare leverages advanced analytics on massive, heterogeneous datasets (electronic health records, medical images, genomics, wearable sensor streams, etc.) to improve patient outcomes and operational efficiency. Traditional healthcare IT systems cannot cope with the volume, velocity, and variety of these data. Modern distributed platforms (Hadoop, Spark, cloud) and AI methods (machine learning, deep learning) are therefore crucial for enabling real-time predictive modeling and trend analysis in medicine. This paper reviews recent (2015–2025) developments in healthcare-focused Big Data analytics, including architectures, algorithms, and applications. A comprehensive end-to-end methodology is proposed, comprising data ingestion, preprocessing, distributed model training, and deployment via containerized services. We describe the implementation of a prototype healthcare analytics system and present experimental results demonstrating its scalability and accuracy for real-time patient risk prediction. The findings underscore that Big Data analytics has become a foundational tool in healthcare, enabling evidence-based clinical decision support, disease surveillance, and personalized medicine.
DOI: http://doi.org/10.5281/zenodo.17813444
Exploring The Role Of Artificial Intelligence In Agriculture: Innovations, Challenges, And Future Prospects
Authors: Dr. Goldi Soni, Reddi Rishitha, Karri AmruthaVarshini
Abstract: The review highlights the significant impact of artificial intelligence (AI) on agriculture, showcasing its ability to enhance efficiency, productivity, and sustainability in response to global food scarcity and a rising population. Key applications of AI include advanced soil, crop, weed, and disease management, facilitated by technologies such as automated irrigation, drones, and data analytics. Despite these advancements, challenges such as uneven distribution of mechanization, the necessity for big data, complexities in soil treatment, pest control issues, and gaps in farmers' technological knowledge hinder widespread adoption. The integration of AI with vertical farming presents a promising solution for urban land and water scarcity by significantly improving crop monitoring and yield predictions through machine learning and IoT technologies. As the agricultural sector faces pressure to increase production by 70% by 2050 amid limited resources and climate change, AI emerges as a crucial element in developing expert systems for crop management and enhancing overall economic efficiency while supporting sustainable farming practices. Nevertheless, significant hurdles remain, including high implementation costs, privacy concerns, and the need for interdisciplinary collaboration to develop holistic AI applications that consider economic, social, and environmental impacts alongside ethical implications. Overall, AI is positioned as a transformative force that could revolutionize agriculture, addressing core challenges and paving the way for smarter, more sustainable farming methods.
“Personalized Learning Through AI: A Case Study Of Implementation In A Blended Learning Environment”
Authors: Ritesh Kumar
Abstract: The integration of Artificial Intelligence (AI) in education has transformed traditional instructional methods by enabling real-time data-driven personalization of learning. This qualitative case study investigates the implementation of an AI-powered personalized learning platform within a blended learning environment at a private secondary school in Bengaluru, India. The study aims to explore how AI supports personalized learning in practice, the experiences of students and teachers using the system, and the broader implications for pedagogy, curriculum, and educational equity. Blended learning—combining face-to-face instruction with digital platforms—has gained traction in recent years, especially with the rise of hybrid learning post-COVID-19. Within this context, AI promises a transformative potential to analyze individual learning patterns and provide customized pathways for student progress. However, the successful integration of AI tools into everyday teaching remains a challenge, particularly in diverse educational contexts. This study adopts a qualitative case study design to provide in-depth insight into how AI can both support and complicate the goals of personalized learning. Data were collected through semi-structured interviews with six secondary school students, three teachers, and one administrator; classroom observations during AI-facilitated sessions; and analysis of related documents such as lesson plans and platform analytics.
DOI: http://doi.org/10.5281/zenodo.17814800
“Artificial Intelligence In Teaching Methodology: Transforming Classroom Strategies
Authors: Saroj Singh
Abstract: The integration of Artificial Intelligence (AI) into teaching methodology is reshaping traditional classroom strategies, opening new pathways for innovation, personalization, and efficiency in education. AI technologies such as adaptive learning platforms, intelligent tutoring systems, automated assessment tools, and data-driven analytics are gradually transforming how teachers design, deliver, and evaluate learning experiences. Unlike conventional methods that often rely on uniform approaches, AI introduces the capacity to customize learning content according to individual student needs, learning pace, and preferred styles, thereby fostering inclusivity and enhancing engagement. Teachers are increasingly able to shift their roles from knowledge transmitters to facilitators and mentors, using AI-generated insights to guide interventions, provide targeted support, and cultivate higher-order thinking skills. The transformative impact of AI in classroom strategies is visible across multiple dimensions. Firstly, AI supports differentiated instruction by offering personalized pathways that address the strengths and weaknesses of diverse learners. Secondly, real-time feedback and automated grading save valuable instructional time, enabling teachers to focus more on interactive, student-centered activities. Thirdly, predictive analytics help identify at-risk students early, empowering educators to implement timely interventions. Additionally, AI-driven immersive tools, including virtual reality and natural language processing applications, enrich learning environments and make complex concepts more accessible. However, the integration of AI into teaching also raises critical challenges such as data privacy, ethical considerations, teacher preparedness, and equitable access to digital resources. This article explores how AI is redefining teaching methodologies by aligning technological innovation with pedagogical goals. It emphasizes the dual role of AI as both a supportive assistant for teachers and a personalized guide for students. The discussion highlights examples of AI applications in curriculum delivery, assessment, and classroom management, while also acknowledging limitations and areas for future research. By transforming classroom strategies, AI not only enhances the effectiveness of teaching but also repositions education as a dynamic, learner-centered process. The study concludes that while AI cannot replace the human element in teaching, it can significantly complement and enrich the educational experience when thoughtfully integrated into pedagogy.
DOI: http://doi.org/10.5281/zenodo.17814824
Big Data Computing: Architectures, Technologies, And Future Perspectives
Authors: Dr. C K Gomathy, Vishnuvel Ragavan K E C, Ghiridharan S
Abstract: Big Data computing has become a cornerstone technology driving digital transformation across industries. This paper provides a comprehensive exploration of Big Data computing paradigms, architectural frameworks, processing technologies, and contemporary challenges. We examine the evolution from traditional data warehousing to modern cloud-native architectures, analyze key processing frameworks including Apache Spark, Hadoop, Flink, and Kafka, and discuss real-time analytics capabilities. Furthermore, this paper addresses critical challenges including data privacy, security, scalability, and regulatory compliance, while highlighting emerging trends such as AI-ML integration, federated learning, and edge computing. Our findings demonstrate that hybrid approaches combining on-premise and cloud solutions are becoming mainstream, with approximately 65% of enterprises adopting Hadoop and Spark in tandem. This research concludes by identifying future research directions necessary to address emerging complexities in distributed data systems and regulatory landscapes.
DOI: http://doi.org/10.5281/zenodo.17838338
Digital Transformation Of Human Resource Management: A Conceptual Framework For Enhancing Organizational Performance In Small And Medium-Sized Enterprises
Authors: Buddhika YPAS
Abstract: This conceptual paper discusses the role of HR digitalization in the performance of SMEs in the context of agility, efficiency, and innovation. Combining the Resource-Based View, Dynamic Capabilities Theory and Technology Acceptance Model, the framework defines the HR digitalization as a strategic resource that converts human capital into competitive advantage. The research hypothesizes eight research propositions which connect HR digitalization with performance results via mediating variables of employee engagement and organizational agility and are modulated by digital leadership, resource limitation, and institutional contexts. The results provide a theoretical understanding and practical recommendations to SME leaders and policymakers to use digital HR systems to benefit their sustainable growth and competitiveness in the digital economy.
“Mapping Sustainability: Evaluating Channapatna’s Green Spaces, Water Bodies, And Mobility Networks”
Authors: Mohammed Khan, Jyoti Gupta
Abstract: This study conducts a geospatial analysis of Channapatna’s urban fabric, focusing on the spatial distribution and interrelationship of green spaces, water bodies (blue infrastructure), and transportation networks. Leveraging Google Maps and other mapping tools, the paper identifies the placement and accessibility of parks, urban lakes, river systems, and transit corridors within the town. Findings reveal a landscape shaped by both ecological assets—such as Shettahalli and Kudlur lakes—and robust connectivity via road and rail, highlighting critical roles in urban quality, economic activity, and environmental sustainability. This research presents a comprehensive geospatial analysis of Channapatna’s green spaces, water bodies, and transportation infrastructure, using Google Maps and other spatial mapping tools to generate a nuanced urban profile. The study systematically maps the distribution and accessibility of public parks, open areas, lakes, and rivers, assessing their impact on land use, environmental quality, and urban well-being. Through NDVI and Air Quality Index analysis, the research highlights disparities in green space allocation, emphasizing their role in city resilience, ecological health, and recreation. The examination of Channapatna’s blue infrastructure uncovers significant deterioration: key water bodies like Shettahalli and Kudlur Lakes, once lifelines for agriculture and community use, now face acute pollution and encroachment. Extensive sewage inflow, lack of Underground Drainage (UGD) systems, encroachment, and unregulated dumping threaten water quality, agricultural productivity, and public health. The study reviews recent policy interventions and ongoing planning efforts—including proposals for a dedicated Sewage Treatment Plant (STP) and expansion of UGD—framing these within the broader context of sustainable urban management.