Tiwari A. Emerging Trends in Computer Science and Its Application 2024 torrent

Textbook in PDF format

The conference brought together a diverse group of scholars, researchers, and industry professionals to engage in meaningful discussions and share insights on cutting-edge trends in Artificial Intelligence (AI), Machine Learning, Data Science, and their multifaceted applications. This collaboration and knowledge exchange fostered an environment of innovation, making the conference a successful and impactful event for all participants. It aimed to highlight these significant advancements and serve as a valuable resource for researchers, academicians, and practitioners who wish to stay informed about the recent innovations and methodologies shaping the landscape of Computational Intelligence. By showcasing a wide range of research topics and practical implementations, it not only addressed the current challenges but also inspired new ideas and approaches for future research.
In the world of Computer Vision and object detection, there’s a strong connection between these areas. Object recognition is all about recognizing specific things in pictures and videos. But this paper goes a step further than the usual methods of finding objects. It tries to understand images in more detail, like how our eyes do. The work starts by looking at deep learning and well- known object detection systems like CNN, R-CNN, and YOLO. These systems can typically find only a few objects in a picture, and they work best at distance of 5–6 meters. However, our new model is much better at this task and has an interesting feature it can even tell you the names of the objects it sees using Google Translate. This is especially helpful for people with vision problems because it helps them understand what’s around them better. In summary, the research combines computer vision, Deep Learning, and real-time object recognition to enhance visual perception and offer valuable assistance to individuals with visual impairments.
The exploration into leveraging Deep Learning (DL) to recognize false or deceptive information, commonly referred to as Falsehood, is a rapidly evolving field of study. Deep structure learning, a subset of Artificial Intelligence employing algorithms to learn from extensive datasets, has exhibited promise in the detection of counterfeit news. The dissemination of fake news poses potential economic, political, and social risks to society, underscoring the growing need to develop effective methods for identification along with prevention. This paper reviews recent studies employing DL techniques, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), as well as a cross media approach, for the purpose of detecting fake news. Additionally, it explores the use of word embedding models for converting script into vector representations and delves into the datasets utilized for model learning. Furthermore, the paper discusses the incorporation of attention mechanisms in conjunction with DL to process sequential data