Category Archives: Uncategorized

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

Published by: vikaspatanker

Authors: Yashmita Mudgal, M Akhila, E Abhishek, G Sravan, S Praveena

Abstract: Fire incidents are hazardous events that can result in the loss of lives, significant property damage, and severe environmental consequences. This project introduces a fire-fighting robotic vehicle capable of detecting and extinguishing fires autonomously, thereby minimizing human involvement and improving overall safety. The robotic vehicle employs flame sensors for accurate fire detection and an Arduino UNO microcontroller to control its operations. Equipped with gear motors, motor driver, and servo- controlled water pump, the robot navigates toward the fire source and extinguishes it. It also includes a GSM module to send SMS alerts and a Bluetooth module for manual override via mobile. This system provides a practical, scalable, and intelligent solution to fire emergencies, particularly in industrial and hazardous environments.

 

 

Published by: vikaspatanker

Authors: Professor Deepak V Lokare, Mr. Mahmadtoufik Rajjusab Mekamungali, Mr. Vijay Byadagi, Mr. Vishal Navilkar, Mr. Sachin Basavaraj Padesur

Abstract: This paper introduces a design and realization of an Automated Wireless Charging System based on Arduino microcontroller. The reader is configured to sense presence of a device in an assigned slot and automatically switch on wireless charging. The system consists of ultrasonic sensors, relay modules and an LCD display to efficiently regulate the charging slots. You put your charging device in front of it and under the ultrasonic sensors, and the distance that is detected switch the relay by the Arduino to start or stop the charging. A 16×2 LCD Display through I2C communication for real time feedback about the charging status, which slot is occupied (either Slot 1 or Slot 2). The system works at two voltages, 5V and 2.5V. The goal is to make charging all the more convenient – in the simplest turn of the wrist power transmission is activated free of contact, without any cables and connectors getting involved. It's especially great for wireless charging pads, smart furniture, and industrial automation. Experimental results show that the system can perform accurate object detection, activate the charging process, and reflect slot status in real time.

DOI: http://doi.org/

Published by: vikaspatanker

Authors: Assistant Professor Mainka Saharan

Abstract: This Paper describes the high speed multiplier by using Booth Algorithm. Booth algorithm produces less delay in comparison with a normal multiplication process and it also moderates the number of partial products. We also proposed a new hybrid CLA from the existing hierarchical CLA which exhibits high performance in terms of computation, power consumption and area. Area, delay and power complexities of the resulting design are reported. Booth algorithm gives a procedure for multiplying binary integers in signed 2’s complement representation in efficient way, i.e., less number of additions/subtractions required.

 

 

Published by: vikaspatanker

Authors: Sachin Sing, Neelanshu Pande, Jay Prakash Pandey, Yatharth Singh

Abstract: Skin conditions are among the most widespread health concerns globally, often triggered by factors such as fungal and bacterial infections, allergies, viruses, genetic predispositions, or exposure to chemicals. Additionally, environmental influences—such as ultraviolet (UV) radiation, pollution, and varying climate conditions—play a significant role in the development of skin disorders. Early detection and diagnosis are crucial for effective treatment. Traditionally, skin diseases have been identified through biopsies and manual assessment by dermatologists. However, advancements in laser and photonics-based medical technologies have significantly enhanced the speed and precision of skin disease diagnosis. Despite this progress, such high-end diagnostic tools remain costly and less accessible. As a cost-effective alternative, image processing techniques have emerged, enabling the creation of automated dermatological screening systems at preliminary stages. In this work, we introduce a hybrid diagnostic model that integrates deep learning (DL) and machine learning (ML) approaches. Patients submit images of affected skin areas, which serve as input to the system. The primary goal of this project is to accurately identify the specific type of skin disease and suggest appropriate treatments. Employing a range of ML and DL algorithms, the proposed method not only enhances diagnostic accuracy but also accelerates the entire process.

 

 

Published by: vikaspatanker

Authors: Anchal Kashyap

Abstract: This research investigates the transformative impact of emerging technologies on digital marketing strategies. Focusing on artificial intelligence (AI), machine learning, augmented reality (AR), and virtual reality (VR), the study examines how these innovations enhance customer engagement and personalization. The paper also explores the evolution of social media platforms into e-commerce hubs, the growing significance of influencer marketing, and the critical importance of data privacy and ethical practices. By analyzing current trends and consumer behaviors, the research provides insights into effective digital marketing strategies that align with technological advancements and ethical considerations.

 

Published by: vikaspatanker

Authors: Ashu Gulia, Ajay Dagar, Dr.Sangeeta Rani, Ms. Monika Saini

Abstract: Pacemakers serve as critical medical devices for monitoring and regulating heart rhythms within patients afflicted with arrhythmias or heart failure. Truly ensuring their accuracy, with reliability and cybersecurity, is paramount. This paper here explores the usage of Support Vector Machines (SVM), and particularly one-class SVM, for the anomaly detection of pacemaker signal patterns. Effectively, deviations showing device failure, cardiac irregularities, or potential cyberattacks can be identified via training models to recognize "normal" cardiac signals. Drawing on methodologies from malware anomaly detection [1][2][3], we adapt as well as repurpose these machine learning techniques to the medical context. The study presents several implementation steps and deployment challenges. The study gives a comparative evaluation with many detection methods, contributing to a safer, clever, and secure pacemaker infrastructure.

 

 

Published by: vikaspatanker

Authors: Mobin Erteghaie

Abstract: The revolution in the two dimensions of information and communication has changed and transformed various aspects of human life. In other words, the behaviors and interactions of individuals have been greatly affected by the changes and transformations in the two aforementioned dimensions. The emergence of new technologies in both dimensions has provided very powerful platforms and tools for the formation of thoughts and communication between different people from different places. In line with these remarkable developments, everyone has been able to provide a lot of new information in various ways and in a wide range of dimensions and scope to a wide range of their fellow human beings. One of the most important communication and information tools between individual humans is mobile phones, especially smart phones. Also, the expansion of social networks in the Internet space, which is actually considered one of the foundations of the new revolution, has provided a very powerful and suitable platform for exchanging information and communicating between different people. Mobile social networks are a comprehensive software platform and a cyberspace in which smartphones that are physically close to each other can create a wireless network. So that people can easily carry out a dating process in public spaces such as airports, coffee shops, and theaters by sharing their interests with those who are nearby. With this development and increased use, there is still a concern in the hearts of people. Given that a lot of information and data is stored and shared in people's personal profiles, the most important issue in such situations is security and personalization. In this study, an attempt has been made to introduce and fully investigate a secure dating protocol in mobile social networks. The present study, focusing on a model of a secure dating process in mobile social networks, examines its impact on social networks and analyzes existing problems. So that by using this profile protocol, users are able to communicate with each other without being fully familiar with each other's complete personal details. In the following, to improve the execution time of the protocol, a high-performance encryption algorithm is used and it is shown that by applying this algorithm and the possibility of using a long-length encryption key while maintaining efficiency, the security of the protocol is significantly increased. The results of the implementation and experiments as well as the evaluations indicate that the efficiency of the proposed protocol in terms of execution time has been significantly improved.

 

 

Published by: vikaspatanker