Enhancing Facial Expression Recognition in Education with Hybrid Attention-Driven Feature Clustering , Kuldeep Vayadande, Yogesh Bodhe, , Amol Bhosle, , Gitanjali Yadav, , Ajit Patil, , Jyoti Chavhan, , Preeti Bailke, and Journal of Engineering Education Transformations, 2025 Facial Expression Recognition (FER) is increasingly being used in education to analyze student engagement and emotional responses, especially in online learning settings. By identifying emotions like interest, confusion, or frustration, FER provides educators with insights to refine their teaching methods and adapt to student needs. This paper reviews the current FER techniques applied in educational environments, emphasizing recent technological progress that has enhanced the accuracy and efficiency of these systems. Advances in computer vision and deep learning have significantly improved emotion detection, enabling real-time feedback and a more personalized learning experience. Despite these developments, challenges persist, such as high computational requirements and privacy issues related to students' emotional data. To tackle these problems, we suggest creating lightweight algorithms and privacy-focused solutions to make FER more applicable in classrooms. Additionally, we introduce a novel model, the Hybrid Attention-Driven Feature Clustering Network (HAFNet), which combines three components: the Feature Clustering Network (FCN), Multi-Head Attention Network (MAN), and Attention Fusion Network (AFN). The FCN enhances class separation using an affinity loss function, while the MAN captures detailed attention from different facial regions. The AFN integrates these attention maps to improve emotion classification accuracy, potentially enhancing educational outcomes through better FER performance.
Multiclass Classification of Epileptic Seizure Using Machine Learning Kavita Sultanpure, Jayashree Bagade, Deepali Joshi, Preeti Bailke, Chaitali Shewale, Poonam Pawar, Deepali Jadhav Ingenierie Des Systemes D Information, 2025 Epileptic seizures are neurological disorders instigated by sudden, uncontrolled electrical disturbances and activities in the brain, leading to changes in behavior, movements, or feelings, and, in some cases, loss of consciousness.Electroencephalogram (EEG) signals are utilized in the medical field to diagnose epileptic seizures.For effective management and treatment of patients, accurate and timely detection of these seizures is crucial.The paper presents a robust machine learning system to do multiclass classification of epileptic seizures using EEG data.The study uses datasets from Bonn University, which include five different sets representing various brain states of healthy and epileptic individuals.After preprocessing and normalizing the data, the features are extracted using techniques like power spectral density (PSD) and wavelet transforms.Various classification algorithms like Decision Tree, Random Forest, Na ve Bayes, and Support Vector Machine were evaluated through extensive hyperparameter tuning and cross-validation.The Random Forest model emerged as the best classifier, achieving a significant accuracy of 89% in classifying the data into five classes, showing its effectiveness in distinguishing between different classes of seizures.This approach shows significant promise for enhancing the accuracy of epilepsy classification and optimizing treatment strategies.
YouTube comment summarizer and time-based analysis Preeti Bailke, Rugved Junghare, Prajakta Kumbhare, Pratik Mandalkar, Pratik Mane, Netra Mohekar Quantum Computing Models for Cybersecurity and Wireless Communications, 2025 With the explosive growth of YouTube as a platform for sharing videos and fostering online communities, the comments section has become a vital arena for discourse and interaction. The YouTube Comment Analyzer is a powerful tool designed to delve into this vast repository of user-generated comments, offering invaluable insights and analytics. This innovative tool employs cutting-edge Natural Language Processing (NLP) techniques dissect and understand wealth of information contained within YouTube comments. Its primary functionalities include sentiment analysis, comment extraction, real-time monitoring, and summary generation.
Reimagining Asteroid Risk Assessment: A Comparative Review of Advanced Machine Learning Techniques Kuldeep Vayadande, Dnyaneshwar M. Bavkar, Ishwari Rohit Raskar, Umar Mubarak Mulani, Jyoti Kanjalkar, Rajashree Tukaram Gadhave, Preeti Bailke, Yogesh Bodhe, Ajit R. Patil Eai Endorsed Transactions on AI and Robotics, 2025 The escalating discovery rate of Near-Earth Asteroids (NEAs) has intensified the need for advanced computational frameworks capable of evaluating their impact risks with high precision. Traditional machine learning models, while foundational for early NEA classification and trajectory prediction, increasingly falter when confronted with the intricate, high-dimensional dynamics of asteroid motion. This limitation underscores the necessity for sophisticated techniques that reconcile computational efficiency with predictive accuracy across large, multi-dimensional datasets. This review systematically evaluates state-of-the-art machine learning algorithms—including quantum-enhanced models, hybrid quantum-classical frameworks, and lightweight convolutional neural networks (CNNs)—for their efficacy in asteroid risk assessment. By analyzing outcomes from recent studies, we contrast performance metrics such as accuracy, computational cost, and scalability. For instance, Quantum K-Nearest Neighbors (QKNN) demonstrates a 15% accuracy improvement over classical counterparts in high-dimensional data classification, while XGBoost achieves 99.99% precision in asteroid diameter prediction. Lightweight CNNs, such as MobileNetV1, further enable real-time processing on resource-constrained platforms like CubeSats, reducing latency by 30%.
Movie Recommendation System using Cosine Similarity 16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
Prediction of a birthweight of a baby using ML Models Preeti Bailke, Aatish Malve, Saket Kumbhar, Shravan Kulkarni, Amey Kulkarni, Jaysinh Madake 2nd International Conference on Research Methodologies in Knowledge Management Artificial Intelligence and Telecommunication Engineering Rmkmate 2025, 2025 One of the most significant reasons to predict the birth weight of infants is to identify the health risks and obtain prompt medical interventions in advance. In that regard, this paper analyzes the possible use of machine learning techniques in predicting baby weight by using maternal, foetal, and environmental factors. This dataset contains many explanatory and response variables such as maternal age, gestational period, nutrition, medical history, and ultrasound measurements, so we will apply and compare some of the most used ML models, namely Decision Tree, XGBoost, Extra Trees, feature engineering and data preprocessing to achieve the best level of model precision. This shows that ML models provide better results than traditional statistical techniques. Hence this holds great promise for machine learning in prenatal care because of high degree of accuracy. This may help healthcare professionals in in identifying risks in terms of low birth weight or macrosomia to improve neonatal outcomes
InquireBot: Safely Delving into PDFs for Your Queries 16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
VeriFIR: An Assistant for Legal Complaint Analysis and BNS Section Recommendation Preeti Bailke, Renuka Deshpande, Akash Gadekar, Rutvik Gaikwad, Vipul Gejage, Sarthak Ghavate International Conference on Nexgen Networks and Cybernetics Ic2nc 2025 Proceedings, 2025 The accuracy of First Information Reports (FIRs) is crucial to ensuring effective investigation and fair judicial outcomes in the Indian legal system. However, due to the absence of legal experts at police stations and the complexity of evolving legal frameworks, FIRs are often drafted with incorrect or missing legal sections. This challenge is further amplified by the recent introduction of the Bharatiya Nyaya Sanhita (BNS), which replaces the Indian Penal Code (IPC) and remains largely unexplored in computational legal research. This study presents VeriFIR, an AI-powered legal assistant that automates the identification of relevant legal sections from the BNS based on natural language complaint inputs. The system supports multilingual inputs, applies translation and NLP techniques for preprocessing, and leverages fine-tuned transformer models such as MiniLM and LegalBERT to compute semantic embeddings. These embeddings are then compared against vectorized BNS section representations using cosine similarity, returning a ranked list of the most contextually appropriate legal provisions. Experimental results demonstrate the system’s ability to retrieve semantically aligned legal sections with high relevance and interpretability. VeriFIR offers a scalable, modular solution for enhancing the quality and consistency of FIR drafting, with potential applications across diverse Indian law enforcement contexts.
Advanced Fake News Detection: Multi-Lingual Analysis and Image Forgery Detection Integration Preeti Bailke, Tejas Kulkarni, Yash Kulkarni, Atharva Kulkarni, Atharva Jadhav, Digvijayy Jadhav 2025 IEEE 14th International Conference on Communication Systems and Network Technologies Csnt 2025, 2025 The advent of the internet has brought about both positive changes and some critical issues. One critical issue is the spread of fake news, which leads to misinterpretation of events, threats to social integrity, and just gives rise to chaos. To tackle this problem, an efficient system is required which can detect fake news effectively. The proposed system introduces a multi-functional fake news detection system. The system makes the use of Gradient Boosting Classifier and Decision Tree Classifier algorithms to predict the authenticity of textual news articles with high accuracy. Furthermore, it integrates a novel feature to analyze the authenticity of images accompanying news articles, using Error Level Analysis (ELA) combined with Convolutional Neural Networks (CNN) to detect signs of image forgery. To enhance versatility and to reduce linguistic challenges, the system can analyze and classifying news articles in both English and Hindi, addressing the diversity of a country like India. The implementation involves preprocessing, feature extraction, and model training, ensuring reliability and robustness. This work contributes to the development of a comprehensive tool that can effectively classify text and images for authenticity, making it a valuable resource in combating the spread of fake news.
MediScan AI: Brain Tumor Detection Using Hybrid Model Kuldeep Vayadande, Preeti Bailke, Sneha Phatangare, Sahil Phatangare, Ketakee Suryawanshi, Arjun Thakur, Shreekar Nyayapathi Proceedings of the 3rd International Conference on Intelligent and Innovative Technologies in Computing Electrical and Electronics Iitcee 2025, 2025
FairHire: Unbiased Machine Learning for Ethical Hiring 16th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2025, 2025
Water Quality Detection Using Smartphone Images Kuldeep Vayadande, Preeti Bailke, Manasi Phand, Aditya Phadke, Vrushali Patil, Manthan Patle, Anagha Posugade Lecture Notes in Networks and Systems, 2025
Book Genre Prediction Using NLP: A Review Kuldeep Vayadande, Preeti Bailke, Ashutosh M. Kulkarni, R. Kumar, Ajit B. Patil How Machine Learning is Innovating Todays World A Concise Technical Guide, 2024
Converting Pseudo Code to Code: A Review Kuldeep Vayadande, Preeti A. Bailke, Anita Bapu Dombale, Varsha R. Dange, Ashutosh M. Kulkarni How Machine Learning is Innovating Todays World A Concise Technical Guide, 2024
A Review on Text Analysis Using NLP Kuldeep Vayadande, Preeti A. Bailke, Lokesh Sheshrao Khedekar, R. Kumar, Varsha R. Dange How Machine Learning is Innovating Todays World A Concise Technical Guide, 2024
Advanced Driving Assistance System: Real-Time Traffic Sign Detection and Driver Drowsiness Monitoring 15th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2024, 2024
Mood Detection Using Tokenization: A Review Kuldeep Vayadande, Preeti A. Bailke, Lokesh Sheshrao Khedekar, R. Kumar, Varsha R. Dange How Machine Learning is Innovating Todays World A Concise Technical Guide, 2024
Smart Attendance System using Geolocation 15th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2024, 2024
A User-Friendly Approach to Object Removal: CGANs and STTN for Enhanced Image and Video Editing 15th International Conference on Advances in Computing Control and Telecommunication Technologies Act 2024, 2024
Ted-Talks Recommendation System using ML Algorithms Preeti Bailke, Atharv Asalkar, Prathamesh Bansode, Niraj Baviskar, Atharva Belote, Hamlin Nadar 2024 1st International Conference on Software Systems and Information Technology Ssitcon 2024, 2024
Nurturing Awareness and Responsible Practices in E-waste Management International Journal of Intelligent Systems and Applications in Engineering, 2024
