Bengal Tanning InstituteThe Government College of Engineering and Leather Technology, often referred to as GCELT, is an institute offering engineering courses at the undergraduate levels in Computer Science & Engineering, Information Technology and Leather Technology, diploma in shoes and leather goods making and M.tech in Leather technology. The college is affiliated to the Maulana Abul Kalam Azad University of Technology (formerly known as West Bengal University of Technology) and is approved by AICTE.
The financial market is undergoing a significant transformation with the advent of Generative AI, marking a paradigm shift in its design. This groundbreaking technology leverages advanced intelligent systems and extensive datasets to reshape the financial domain. In this study, we present SentEM-GEN, an advanced Generative AI model designed to identify and explain user sentiments and emotions. SentEM-GEN follows a text-to-text generative framework, incorporating dual selective attention mechanisms to optimize sentiment and emotion analysis. The model consists of two variants: Variant-1, which focuses on sentiment analysis, and Variant-2, which emphasizes emotional aspects and includes BART-Large for nuanced causal generation. We trained SentEM-GEN using the FinEMA dataset, a carefully constructed dataset annotated with sentiment, emotion, and cause labels. FinEMA analyzes shifts in the financial stock market based on various sources, such as tweets, financial reports, and news articles, achieving 93 https://github.com/ankan8145/SentEM_GEN
Recent advancements in microelectrode-dot-array (MEDA) based biochips have significantly reshaped the landscape of Lab-on-chip devices. By integrating concepts from computer-aided design automation and cyber-physical systems, these innovations enhance ease of use, throughput, and reliability. Nevertheless, a notable security concern in MEDA-based biochips lies in their vulnerability to actuation tampering attacks, which aim to disrupt the control sequence in the daisy chain input, resulting in erroneous bioassays. In this paper, we identify actuation tampering attacks specific to MEDA-based biochips and propose a technique to detect and safeguard against such attacks. This method vigilantly monitors for malicious activities and can halt operations upon detecting any anomalies. Our hardware-based approach identifies the tampering sequence, rectifies it, processes it through the daisy-chained structure, and ultimately verifies the output pattern, accepting or rejecting the result based on the status of the associated hardware flags. By addressing these security challenges, our technique ensures the reliability and integrity of MEDA-based biochips in biomedical applications.
Road accidents are increasing worldwide, resulting in numerous deaths and disabilities each year all over the world. So road safety has become one of the major public safety concerns in a country like India. Sometimes such road accidents occur because drivers are unable to detect of road anomalies such as potholes, speed-breakers, etc on road surfaces in time and consequently the driver cannot reduce or control the speed of the vehicle at right time. This study aims to develop a computer vision-based model to assist in detecting the road anomalies and thereby contribute to reducing road accidents. In this direction, as a first step, it builds a new dataset of bump images of Indian road surfaces. All the images of national/state highways, local roads were captured under uncontrolled environmental and lighting conditions. This dataset comprises of high resolution road surface images captured in different states of India under diverse weather and lighting conditions. It specifically tries to capture the complexities and variations of real-world Indian road surfaces. The image dataset has a total of 9323 images comprising 6028 bump images and 3295 non-bump(normal) image. Moreover bump images cover a total of 24 categories and non-bump (normal) images cover 9 categories. After collection of images, in the next step, it has attempted a few Deep Learning hybrid models (MobileNetv2, EfficientNetB0, ResNet-50) are utilized for speed-breaker detection using the dataset. Also, the study leveraged specialized multi-scale feature extraction network Feature Pyramid Network, lightweight attention mechanism CBAM, feature aggregation module Horizontal Pyramid Pooling. Experimental results show that the hybrid pre-trained models achieves up to 97.75% accuracy on INR-SPEED-BUMP image dataset. To improve the interpretability and reliability of the model predictions, two Explainable Artificial Intelligence (XAI) techniques, namely Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP), are utilized. The image dataset of Indian road surface may serve as a valuable resource for academicians and researchers and contribute significantly for the development of computer vision-based system for advancing of road safety technologies in the Indian subcontinent.
