“RAKSHAK” - A Voice Controlled Smart Safety Device 16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
Skilldev: Genai-Powered Skill Upgrading Platform Deepali Deshpande, Renuka Deshpande, Akash Gadekar, Rutvik Gaikwad, Vipul Gejage, Sarthak Ghavate Icdt 2025 3rd International Conference on Disruptive Technologies, 2025 The rapid evolution of technology has transformed the landscape of education, making it essential for students to stay up-to-date with industry-relevant skills. The project presents a web-based platform to enhance campus placement preparation for pre-final and final-year engineering students of various computer-related faculties. The platform uses Generative AI to assess student skill levels in various core and important subjects under the computer domain. By categorizing students into Beginner, Intermediate, or Advanced levels, the platform delivers personalized learning resources and tutorial recommendations as per the user's needs while tracking the overall progress. The system provides visual insights through graphical analysis of student performance to improve employability and better equip students for competitive placement processes. Additionally, it also delivers responsive feedback for the overall achievement and progress of the user. Through various self-designed recommendation and evaluation algorithms, the system adapts to student's learning needs, ensuring an optimized and dynamic learning experience.
Multimodule Legal Analytics Pipeline for Outcome Prediction and Transparent Justification in Commercial Cases Deepali Deshpande, Atharva Kulkarni, Tanaya Jadhav, Atharva Jadhav, Digvijayy Jadhav, Shalvi Kshirsagar International Conference on Intelligent Communication Networks and Computational Techniques Icicnct 2025, 2025 Indian commercial courts face heavy caseloads, increasing the need for rapid legal research and reliable case outcome prediction. To address this, an AI-powered legal research engine was developed, tailored for Indian commercial litigation under the Commercial Courts Act, 2015. The system processes statutes and judgments to build a semantic search index and uses an LSTM-based neural model to predict outcomes (petitioner win or loss). Training is done on the ILDC dataset containing annotated court judgments. For interpretability, a LIME-based module highlights critical facts and legal provisions. A fine-tuned LLaMA language model then generates human-readable justifications aligned with judicial reasoning by leveraging LSTM outputs and LIME attributions. The model achieves 91% accuracy and 0.95 AUC, with a balanced confusion matrix. The explainability layer emphasizes critical contract terms and legal citations, enhancing transparency. This system also addresses limitations such as data bias, domain shifts in lower courts, and ethical concerns. It aims to streamline research and improve legal decision support.
A Decentralized Ethereum-Based Donation Platform Using Smart Contracts for Transparent Charity Transactions Pankaj Kunekar, Sushma Mehetre, Shweta Kambare, Renuka Nagpure, Deepali Deshpande, Vedant Sambhar Proceedings 2025 2nd International Conference on Networks and Soft Computing Icnsoc 2025, 2025 Charitable donations play a vital role in supporting humanitarian causes across the globe. However, traditional donation systems frequently encounter significant dispute like insufficient transparency, operational inefficiencies, and vulnerability to fraud or mismanagement. These issues often erode donor trust and create barriers to effective and timely distribution of funds. To overcome these limitations, this paper presents a decentralized donation platform Constructed on the Ethereum blockchain, leveraging smart contracts to enable secure transparent, and tamper-proof transactions. The proposed system enables donors to track their contributions in real time and Guarantees that funds are released solely when specified conditions are fulfilled, thus removing the requirement for third-party intermediaries. A functional prototype was created utilizing the Solidity programming language. and deployed on Ethereum test network. Experimental results show successful automation of donation tracking, verification, and conditional fund release with minimal transaction overhead. The proposed approach significantly enhances transparency, trust, accountability, and operational efficiency, offering a scalable and reliable alternative to traditional donation mechanisms.
Enhancing Underwater Mine Detection Accuracy through Sonar Signal Analysis 15th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2024, 2024
Empowering Data Sovereignty: Decentralized Image Sharing through Blockchain and Interplanetary File System International Journal of Intelligent Systems and Applications in Engineering, 2024
Next-Gen Security: YOLOv8 for Real-Time Weapon Detection Deepali Deshpande, Manas Jain, Adhip Jajoo, Devika Kadam, Harshvardhan Kadam, Aryan Kashyap 7th International Conference on I Smac Iot in Social Mobile Analytics and Cloud I Smac 2023 Proceedings, 2023
Research Article Summarizer Deepali Deshpande, Rishikesh Unawane, Roopal Tatiwar, Aditya Taware, Aryaman Todkar, Shubhankar Munshi 2023 International Conference for Advancement in Technology Iconat 2023, 2023
A Survey on the Role of IoT in Agriculture for Smart Farming Deepali Deshpande, Swapnil Jadhav, Rushikesh Chounde, Tejas Kachare, Kaustubh Bhale, Pratik Waso Proceedings 2021 1st IEEE International Conference on Artificial Intelligence and Machine Vision Aimv 2021, 2021
