Daily Archives: May 28, 2025

Authors: Assistant Professor Mrs. G. Sangeetha Lakshmi, Mrs. S. Hemalatha

Abstract: Early and precise detection of oral cancer is critical for improving patient outcomes, yet conventional diagnostic methods often involve manual analysis, which can be slow and susceptible to human error. To overcome these limitations, this research introduces an automated detection system that combines deep learning for feature extraction with the Random Forest algorithm for classification. By analyzing medical images, the deep learning component identifies essential features such as texture, color inconsistencies, and irregular tissue structures. These features are then processed by the Random Forest classifier, which utilizes an ensemble of decision trees to enhance classification accuracy and minimize errors. Trained on a dedicated dataset of oral cancer images, the model effectively differentiates between malignant and benign tissues. Experimental findings reveal that this hybrid approach outperforms standard machine learning techniques, offering a faster and more dependable diagnostic tool to aid clinicians in early oral cancer detection and improve patient survival rates.

 

 

Published by: vikaspatanker

Authors: Assistant Professor Priya Tyagi, Assistant Professor Dr. A.P Srivastava, Sandeep Kumar Yadav, Sahil Gupta

Abstract: The Edu Tracker Association Platform is a comprehensive web-based application developed using the MERN stack (MongoDB, Express.js, React.js, Node.js) that aims to streamline and enhance the management of educational activities, associations, and student performance tracking within academic institutions. The platform serves as a centralized hub for administrators, faculty, and students to interact, monitor, and manage academic and extracurricular engagements efficiently. By leveraging the full-stack capabilities of MERN, the system ensures a highly responsive user interface (React.js), robust server-side logic (Node.js and Express.js), and scalable data storage (MongoDB). Key features include student profile management, real-time performance tracking, association membership management, event scheduling, and detailed reporting tools. Role-based access control ensures secure data handling and personalized user experiences for students, faculty, and administrators. The Edu Tracker Association Platform enhances transparency, encourages student engagement in academic and non-academic activities, and simplifies the evaluation process. With its modular architecture and RESTful API integration, the platform is designed for scalability, future expansion, and integration with existing educational systems.

Published by: vikaspatanker

Authors: Sishank Singh Rawat, Satyam Dhar, Assistant Professor Dr. Prakash

Abstract: With rising expectations for instant, contactless, and personalized retail experiences, companies like Mars Inc., a global leader in the confectionery industry, are looking to modernize their vending operations. Traditional vending systems are constrained by static inventory models, manual restocking, and a lack of real-time adaptability—leading to stockouts, waste, and poor customer satisfaction. This paper introduces the Intelligent Vending Machine Optimization System, a smart retail solution designed to transform Mars Inc.'s global vending infrastructure. The system integrates IoT sensors, Azure-based Medallion architecture, machine learning, and edge computing to deliver predictive restocking, autonomous maintenance, and real-time customer insights. Voice and gesture-based interfaces improve accessibility, while Power BI dashboards offer centralized monitoring. This approach ensures scalable, energy-efficient, and intelligent vending operations, enabling Mars Inc. to lead the future of automated retail with data-driven precision.

 

 

Published by: vikaspatanker

Authors: Parth Rastogi

Abstract: The gaming industry has witnessed an absolute change because of the Free-to-Play (F2P) model, which not only provides everyone with the chance to enjoy games free of charge but also produces substantial revenue through in-game purchases. The potential threats to the player experience posed by intrusive monetization methods, in particular, loot boxes and pay-2-win mechanics, can result in decreased user engagement and long-run dissatisfaction. This survey studies the ways in which a game developer can achieve the balance between monetization optimization and a player experience – maintaining a high-quality player experience. A research that used a mixed-methods approach was carried out by the authors, including surveys, interviews, and sentiment analysis. The preliminary results support the idea that ethical, viable monetization schemes, like digital clothes in shop and game passes, are good methods for revenue generation and maintaining the player base. On the contrary, those that use exploitative measures will often encounter dislike and a high churn rate, as well. -seen in the gamers' reactions to this interaction. The strategies include the most suitable ones for fair, transparent, and sustainable monetization in F2P games.

 

 

Published by: vikaspatanker

Authors: Asif S Majeed, Evelyn Treasa Jaison, Fathima S, Arunlal M L, Dr. Jyothi R L, Swathi S

Abstract: This study introduces an approach for depression detection through an Additive Cross-Modal Attention Network (ACMA) that integrates audio and textual data to improve diagnostic accuracy without relying on self-report questionnaires. Traditional depression assessments often depend on patient- disclosed information, which may not always be accurate due to stigma or personal reluctance, leading to potential underdiagno- sis. The ACMA model addresses these limitations by leveraging cross-modal attention mechanisms within a Bidirectional Long Short-Term Memory (BiLSTM) and Transformer model to cap- ture and assign optimal weights to relevant features across audio and text modalities. This enables the model to effectively detect depressive symptoms by analyzing both linguistic and acoustic cues. The model is designed for both binary classification (depressed vs. non-depressed) and regression tasks to estimate depression severity, utilizing the DAIC-WOZ dataset for evaluation. ACMA demonstrates significant improvements over baseline models, achieving high accuracy, recall, and F1 scores. Additionally, the model’s adaptability across different datasets underscores its potential as a robust, non-intrusive tool for clinical applications in mental health diagnostics. This work advances the field of au- tomated depression detection, providing a foundation for further research in cross-modal mental health assessment systems.

 

 

Published by: vikaspatanker

Authors: Professor Adel Elgammal

Abstract: It is within this context of the growing popularity of electric vehicles (EVs) that the development of smart energy management, which can optimally manage the power consumption, increase the battery life, and enhance the vehicle efficiency in various driving patterns and conditions, has become essential. Conventional control strategies such as rule-based strategies and model predictive control can work well in controlled environments, but may be insufficiently resilient to the real-world complexity of changing traffic, gradients, and driver actions. In this work, a new real-time energy management strategy for EVs is developed by means of a RL-based optimal control framework, where DQN is adopted to dynamically optimize decisions about energy utilization. The proposed RL controller learns the optimal policies by exploring the real-time high-fidelity EV simulation environment, which accounts for vehicle dynamics, battery attributes, and external driving conditions. Unlike classical controllers, the RL-based solution does not require any predefined models or future prediction horizon to operate, as it continually learns from its own experience to decide in real-time on the power split between the electrical machine and auxiliary systems. The reward functions are designed to optimize for, for instance, energy efficiency, battery health, and driving performance features e.g. acceleration and driving smoothness. Simulation results show that the proposed RL-based controller can outperform benchmark strategies in various driving scenarios, obtaining up to 18% better energy efficiency and increased adaptability to changing situations. Moreover, the learned policy is robust in controlling battery temperature and state of charge (SOC) fluctuation which results in an increased battery life. This research reveals the capabilities of reinforcement learning as a promising scalable and self-adaptive technique for energy control in future EVs. For future works, we plan to further consider practical applications, multi-agent vehicle coordination, and integrating the proposed algorithm with V2I to realize cooperative energy optimization in smart transportation networks.

 

 

Published by: vikaspatanker