Authors - Yash Tekade, Mayur Shinde, Bhumika Lipane, Nikita Patil, Suhasini Bhat Abstract - The paper presents the idea and methodology of development of a real-time threat detection system designed to enhance women's safety across various environments using AI technology and CCTV surveillance. The system consists of features like real-time person detection, gender classification, and SOS gesture recognition, all connected to an alert system for law enforcement authorities. It effectively identifies potential threats, including a lone woman at night or a woman surrounded by men, enabling proactive actions before incidents escalate. Additionally, the system maps hotspot areas where previous incidents have been recorded, allowing authorities to allocate resources efficiently. It also alerts security personnel about low-light conditions in an area, ensuring surveillance even in challenging environments. By combining these capabilities, the system aims to create a safer atmosphere for women, promoting proactive measures that can significantly reduce crime rates and contribute to enhance overall safety strategies.
Authors - Ritveek Rana, Manisha Manoj,vAnitha Dhanasekaran Abstract - This research endeavors to apply artificial intelligence to estimate past energy statistics and forecast future energy consumption patterns in India. The research utilizes energy indicators such as access to electricity, the share of renewable energy, CO2 emissions, and economic development to develop a model to forecast future energy needs and renewable energy share. The future energy consumption patterns and the share of renewable energy are forecast using regression analysis. The intention is to provide insights into energy transition required in order to ensure sustainability by reducing the reliance on fossil fuels and increasing renewable sources.
Authors - G.B. Sambare, Sankarsha Shelke, Sahil Wawdhane, Harshad Wable, Abhinav Thube Abstract - The KYC Powered by Blockchain for decentralized, secure, and more efficient Know Your Customer (KYC) system using blockchain. This system solves the inherent inefficiencies of traditional KYC by allowing institutions to share validated customer data, mitigating redundancy among KYC providers, and reducing both costs and compliance time. Tamper-proof architecture of blockchain allows for strong data privacy, security, and compliance of AML and GDPR regulations. Customers gain full control over their personal data, with the ability to grant and revoke access dynamically, reducing risks of breaches and fraud. The framework integrates off-chain storage for sensitive data and combines advanced cryptographic methods like AES and ECC for encryption and security. Smart contracts automate data handling and permissions management, ensuring secure, transparent, and immutable data sharing across institutions.
Authors - Sakshi G. Wagh, Snehal S. Shirsath, Vaibhavi V. Pujari, Shrirang A. Sonawane, Milindkumar B. Vaidya Abstract - Diagnosing brain tumors is a complex task due to their intricate characteristics and variability in presentation. Timely and accurate detection plays a vital role in ensuring effective treatment and improving patient prognosis. This study presents the development of an automated system for brain tumor detection and segmentation using Convolutional Neural Networks (CNNs). The model is trained on annotated MRI datasets to distinguish between normal and tumorous brain tissues with high accuracy. The proposed approach involves a comprehensive pipeline that includes image preprocessing to enhance MRI quality, training a CNN-based model for tumor recognition, and applying post-processing techniques to refine the output. By automating the diagnostic process, the system aims to support radiologists by increasing accuracy, reducing diagnostic delays, and minimizing manual interpretation errors. Furthermore, the project incorporates various image processing techniques and data augmentation strategies to strengthen the model’s performance and generalizability across diverse imaging conditions. The result is an intelligent and accessible diagnostic tool intended to assist healthcare professionals in delivering more precise and efficient brain tumor diagnoses, ultimately contributing to better clinical decision-making and patient care.
Authors - Monali P. Deshmukh, Dhanashri Arjun Ghadage, Mrunali Sunil Rangankar, Prajakta Dattatray Supugade, Deep Isane Abstract - This research paper presents an AI-assisted web-based coding platform, Code Understanding using Sherlock, that integrates a real-time compiler with an AI-powered chatbot. The chatbot provides contextual assistance based on selected code snippets or general programming queries. Users can toggle between a standard chatbot mode and a code-aware mode, where the chatbot analyzes selected code portions to answer relevant questions. The system enhances the coding experience by providing explanations, debugging help, and execution functionalities. By leveraging AI and NLP techniques, the chatbot can understand syntax, logical structures, and common programming errors, offering detailed feedback and solutions. The platform streamlines the development process by reducing debugging time and enhancing code comprehension. Additionally, the system provides a seamless file management experience, enabling users to create, edit, and organize their projects efficiently. This integration fosters an interactive learning and development environment, making it valuable for both beginners and experienced programmers.
Authors - Anandhukrishna A S, Santanu Mandal, Raghu Raman Abstract - Digital Twin (DT) technology offers unprecedented capabilities that are transforming supply chain management (SCM), delivering a new level of system-wide resilience, real-time insights and predictive analytics. Yet, the nascent research still lacks in terms of cohesion, with most studies being heavily centralised around technical solutions and missing strategic, managerial and empirical perspectives. In light of this gap, the current study provides a thorough bibliometric analysis of 99 peer-reviewed articles published from 2016 to 2024 selected from Scopus with analytical tools of Biblioshiny R package. The results clearly showed that there was a higher growth of DT-related SCM research after 2020, indeed due to significant intercontinental disruptions and the demand of resilient, sustainable, and intelligent infrastructure systems. Resilience in the supply chain, sustainability, interoperability, and AI-driven optimization are core themes. Importantly, while China, Germany, and the USA dominate in terms of number of papers produced, institutions such as The Hong Kong Polytechnic University are also leading in productivity metrics here. However, the analysis reveals important gaps — notably a lack of cross-border cooperation and empirical case studies as well as longitudinal research. Less developed but rich prospects, like the integration with blockchain, extended reality and physical internet also emerge as compelling themes. This work offers actionable insights into the way forward for researchers, policymakers, and industry leaders, calling for cross-disciplinary partnerships, real-world pilots, and frameworks for applying overarching compliance. This also advances the role of Digital Twins as a strategic enabler of a resilient and future-ready supply chain.
Thursday August 27, 2026 3:30pm - 5:30pm IST Virtual Room CGOA, India
Authors - Jhalak Bansal, Janvi Jain, Sukti Jain, Harsh Chaudhary, Vikas Srivastava Abstract - Traffic accidents, a leading cause of death worldwide with nearly one million fatalities annually (WHO), are often driven by fatigue-related drowsiness. Our project introduces a real-time drowsiness detection system leveraging technologies like OpenCV, Python, and machine learning to enhance safety and accuracy. Using a camera, the system monitors facial features and eye movements, Using facial landmark detection to identify 68 key points, the system calculates the Eye Aspect Ratio (EAR). Extended periods of eye closure activate an alert, and GPS-enabled location tracking enhances response by sending automated emails with the vehicle’s real-time location to pre-registered contacts. The methodology integrates image processing, real-time facial landmark detection, and a dynamic scoring system to evaluate drowsiness. With an accuracy target of over 85%, the system addresses the limitations of existing solutions while introducing innovative location-based intervention. Results highlight its potential to reduce drowsy driving incidents, ensuring safer roads.
Authors - Aoudumber Londhe, Ravindra Apare, Parikshit Mahalle, Ravindra Borhade Abstract - Aqua status quality prediction is a vital part of environmental monitoring, with significant implications for public health, ecosystem sustainability, and Aqua resource management. Traditional methods for evaluating aqua quality, is like taking the manual sample and to perform the laboratory analysis, are often labour-intensive and limited in scope. Recent developments in deep learning have transformed this domain by empowering the expansion of predictive models accomplished with analysing non-linear relationships in Aqua quality. Hybrid deep learning models, merging Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Convolutional Neural Networks (CNNs), and Gated Recurrent Units (GRUs), have verified superior performance in apprehending spatial and temporal dependencies in Aqua quality data. Optimization algorithms such as Particle Swarm Optimization, Grey Wolf Optimization, Sparrow Search Optimization (SSO), and Beluga Whale Optimization (BWO) have been integrated to enhance model accuracy and efficiency. Attention mechanisms and feature selection techniques have further improved model performance, while the integration of IoT has enabled real-time monitoring, addressing the limitations of traditional methods. Despite these advancements, challenges related to model interpretability, computational complexity and most important part data availability remain as it is. This review explores the pragmatic augmentation in hybrid deep learning models for Aqua quality prediction, focusing on their architecture, optimization techniques, and real-world applications.
Thursday August 27, 2026 3:30pm - 5:30pm IST Virtual Room CGOA, India
Authors - Rakhi Bharadwaj, Mohit Deo, Pratham Jain, Ashishkumar Jha, Harsh Bachhav Abstract - This study introduces a novel open-source educational website that makes use of AI-powered 3D environments and interaction with historical individuals to deliver immersive historical learning experiences. The site offers both contemporary views of these environments using 3D Gaussian splatting technology and offers precise historical recreations using Pixel Streaming. Interactive conversation with AI-powered historical individuals, dynamic quizzes to validate the knowledge of users, and AI-powered historical narratives are all among the offerings. To support knowledge about historical events and cultures from the past, the system merges interactive learning and storytelling for a fun and educational experience. Advanced natural language processing (NLP), speech-to-text, and AI-powered tour guides are all included as part of the platform architecture to provide personalized historical tours without necessitating complicated personal details.
Authors - A. Harshavardhan, Konkathi Nihal, Ramini Srinidhi, Konda Poojithasai, Gochika Bhanu prasad, Dhanraj Sai Ganesh Abstract - This paper presents a novel, dual-layer secure steganographic system that combines hybrid cryptography and steganography to ensure the confidentiality, integrity, and security of secret communications. Initially, the sender inputs their message and selects a cover image. The message is encrypted using a hybrid substitution (playfair cipher and columnar transposition cipher) and transposition cipher, and then embedded in randomly selected pixel positions of the image using Least Significant Bit (LSB) steganography. A position file that records these embedding locations is generated and encrypted. To obfuscate the presence of the stego-image, multiple duplicate images are created alongside the steganographic image. On the receiver's side, a ResNet50-based feature extractor followed by K-means clustering is used to identify the stego-image from the duplicates. The encrypted position file enables accurate message extraction and subsequent decryption. Experimental results show excellent performance with high imperceptibility (MSE: 0.0175, PSNR: 65.69 dB, SSIM: 0.9994) and strong resilience to brute-force and statistical steganalysis.
Thursday August 27, 2026 3:30pm - 5:30pm IST Virtual Room CGOA, India
