Authors: G. Janaki, P. Sangeetha, S. Swetha
Abstract: A Diophantine triple is a set of three positive integer a,b, c such that the product of any two distinct elements is added to one, is a perfect square .This article investigates the existence of a specific Diophantine triple involving Centered Hexagonal Number ensuring the product of any two members of the added to the property D(n).
DOI: https://doi.org/10.5281/zenodo.19019965
Authors: Deepak Tomar, Kismat Chhillar
Abstract: Water resource management has become increasingly challenging due to rapid population growth, climate variability, urbanization, and rising agricultural demand. Traditional hydrological models often struggle to capture the complex and nonlinear interactions between environmental variables affecting water systems. Machine Learning (ML) offers powerful data-driven techniques that can analyze large and heterogeneous datasets to support efficient water management. This paper explores the role of machine learning in water resource management, highlighting its applications in hydrological forecasting, irrigation optimization, groundwater monitoring, and water quality assessment. Various ML algorithms such as Artificial Neural Networks, Random Forest, Support Vector Machines, and Deep Learning architectures are examined for their ability to model complex hydrological processes. The study also discusses current challenges including data availability, model interpretability, and integration with existing hydrological frameworks. The findings indicate that ML-based approaches can significantly enhance predictive accuracy, optimize resource utilization, and support sustainable water management strategies.
DOI: https://doi.org/10.5281/zenodo.19019143
Authors: Akalya M, Mohammed Suhail Akthar J, Rohan P S, Dr R Karthik
Abstract: In Order To Detect And Track Wildlife In Real Time, Computer Vision Techniques Are Being Used More And More In Wildlife Monitoring. Modern YOLO Object Detectors (Yolov3, Yolov4, Yolov5, Yolov7, And Yolov8) Combined With Multiobject Tracking Algorithms, Specifically SORT And Deepsort, Are Assessed And Contrasted In This Study For Automated Wildlife Monitoring. Wildlife Camera Trap Datasets Are Used To Evaluate These Models' Performance, Taking Into Account Metrics Like Tracking Accuracy, Precision, Recall, Mean Average Precision (Map), And Inference Speed.According To Experimental Results, Deepsort Considerably Increases Tracking Stability By Lowering Identity Switches Through Appearance-Based Association, While Yolov8 Achieves The Best Detection Performance In Terms Of Map And AP@0.5. When Paired With Deepsort, Yolov5 Offers A Robust, Lightweight Baseline That Achieves High Tracking Accuracy (MOTA ≈ 94%) While Utilizing Computational Power Efficiently. Conversely, SORT, Which Has More Identity Switches And Only Uses Motion Cues. The Results Show The Trade-Offs Among YOLO Variants In Terms Of Detection Accuracy, Model Size, And Computational Cost. The Suggested YOLO + Deepsort Framework Shows Great Promise For Real-Time Wildlife Monitoring On Edge Devices Like Uavs And Field Cameras, Supporting Applications Like Habitat Analysis, Biodiversity Assessment, Antipoaching Surveillance, And Mitigating Conflicts Between Humans And Wildlife.
DOI: https://doi.org/10.5281/zenodo.19018863
Authors: Aswetha. M, Danwin shaju, Mrs. Sangeetha Priya
Abstract: The volume of unstructured texts has increased dramatically in recent years due to the internet and the digitization of information and literature. This onslaught of data will only grow, and it will come from new and unusual sources. Thus, it will be necessary to develop new and inventive approaches and tools to process and make sense of this data. Investors in the financial markets can now get information faster than ever before thanks to the expansion of communication channels, in addition to the online availability of news and reports in text format through providers like Reuters and Bloomberg. This contains a plethora of information that is often overlooked by financial market data. In order to measure the sentiment of a text, predictive and deductive methods are applied, these methods aim at extrapolating new feautures from big data.
DOI: https://doi.org/10.5281/zenodo.19018551
Authors: Vaishnav B.khokale, Aakash N.Nikam, Yash S. Patil, Aaditya S. Kshirsagar, Prof.S.S.Aher
Abstract: The continuous growth in population, urbanization, and technological advancement has resulted in a rapid increase in electrical energy demand. Conventional energy sources are not only limited but also responsible for environmental pollution. At the same time, a significant amount of human mechanical energy generated during physical activities such as gym workouts is wasted without any productive use. This research paper presents the concept of Harnessing Electricity from a Hybrid Green Gym, where human effort and solar energy are combined to generate electrical power. Mechanical energy produced during pedalling is converted into electrical energy using a generator, while solar energy acts as an additional and reliable source. The generated energy is stored in a battery system and can be used to operate small electrical loads. The proposed hybrid system ensures power availability during grid failures, power cuts, and environmental calamities. The system is eco-friendly, cost-effective, and suitable for decentralized energy generation. It also promotes physical fitness along with energy conservation.
Authors: Sagar Zodge, Rohit Vhawale, Vishal Vetal, Dikshant Zine
Abstract: This project presents a GPS and GSM based accident alert system that automatically detects accidents and sends emergency notifications. The system uses Arduino Uno and an accelerometer such as ADXL335 to detect sudden impacts. When an accident occurs, the location is obtained using the NEO-7M GPS Module and an alert message is sent through the SIM800 GSM Module to a predefined mobile number. This system helps provide faster emergency response and improves road safety .
Authors: Dr.S. Manikandan, Premkumar V, Thamarai Selvan T, Tharun M
Abstract: Independent navigation in dynamic and unfamiliar environments remains a major concern for individuals with visual impairments. Conventional mobility aids such as white canes and guide dogs offer limited spatial awareness and may not effectively detect obstacles at varying distances or heights. This paper introduces an Intelligent Shoe System for Blind Navigation that enhances user safety and mobility through real-time sensing and feedback mechanisms. The system embeds ultrasonic and infrared sensors within footwear to continuously monitor the surrounding environment and identify obstacles in the user’s path. A microcontroller processes sensor inputs and provides immediate feedback through vibration and audio cues, enabling intuitive and hands-free navigation. The design optionally incorporates GPS and wireless communication to support outdoor navigation, route assistance, and emergency alerts. Emphasis is placed on low power consumption, affordability, and comfort to ensure suitability for everyday use. Experimental results indicate improved obstacle detection performance and a noticeable reduction in collision incidents when compared to traditional assistive tools. The proposed intelligent shoe system aims to promote greater independence, confidence, and overall quality of life for visually impaired users.
DOI: https://doi.org/10.5281/zenodo.19017095
Authors: Prakash T, Sakthivelan K, Dharun M, Mrs. M. Vanitha
Abstract: This project presents an AI-based Tamil Learning Platform for Children aimed at improving early Tamil language education through intelligent and interactive methods. Traditional teaching approaches often lack interactivity and effective feedback for pronunciation, handwriting, and grammar. To address this issue, the proposed system integrates three AI-driven components: a Tamil Voice Model, a Tamil Letter Writing Recognition Model, and a Tamil Grammar Checker Model. The voice model evaluates pronunciation accuracy using speech processing techniques, while the handwriting recognition model analyzes written Tamil characters on a digital canvas. The grammar checker uses natural language processing to identify errors in simple Tamil words and sentences and provide corrections. By integrating speech, handwriting, and language processing, the platform creates an interactive learning environment that supports children in improving their Tamil language skills.
DOI: https://doi.org/10.5281/zenodo.19016934
Authors: Prof. Tejashree Pangare, Harshad More, Aryan Patil, Raj Patil
Abstract: In an age where digital information has reached an all-time high, it is essential to be able to access the most relevant and correct data out of the exorbitant storage of information from the internet and its various search engines, even more so when it comes to domain-specific knowledge like Space Science. The primary goal of this project is to propose an AI based Help Bot that can be used to do an intelligent search on data from MOSDAC (Meteorological and Oceanographic Satellite Data Archival Centre), a project of ISRO, in a manner that feels conversational and natural to the user through the use of Knowledge Graphs, NLP, and Semantic Search algorithms. In addition to providing a comprehensive and customized, easy, efficient, and smooth information-seeking experience to its users that can be a researcher/scientist, a student, or simply the general public, the implementation of a bot system as such with the state-of-art NLP techniques that understands relationships between entities and dynamic learning algorithms that adapt to newly updated information content in its database, will take us one step closer to achieving a no-miss search experience that also takes into account their intent, thereby improving the accessibility of information and decreasing information search time while truly revolutionizing the way we access Space-derived information regarding Meteorological and Oceanographic data.
DOI: https://doi.org/10.5281/zenodo.18999423
Authors: Mrs..K.M.Swarna Devi, Divith S, Jayaprakash C, Madhavan S
Abstract: Timely detection of eye-related diseases is critical for preserving vision and preventing permanent visual loss. With the growing availability of ophthalmic imaging, artificial intelligence has emerged as an effective tool for enabling fast and automated disease screening. This study proposes a real-time artificial intelligence–driven framework for eye disease detection based on deep learning techniques. The system employs convolutional neural networks (CNNs) to process retinal fundus images and optical coherence tomography (OCT) scans for identifying prevalent eye conditions such as diabetic retinopathy, glaucoma, and age-related macular degeneration. To support real-time operation, the model architecture is optimized for low computational complexity and rapid inference without compromising diagnostic accuracy. The proposed system assists ophthalmologists by providing instant diagnostic feedback, reducing manual examination time, and supporting early clinical decision-making. Experimental evaluation demonstrates that the model achieves high detection accuracy along with minimal processing delay, making it suitable for real-time deployment in clinical settings, telemedicine platforms, and large-scale eye screening programs. The results highlight the potential of AI-based solutions to enhance accessibility, efficiency, and reliability in modern ophthalmic diagnosis.
DOI: https://doi.org/10.5281/zenodo.18998750
