17 research outputs found
Pandemic Lockdown in Kerala: Vishu and Thrissur Pooram Festivals
No full textThis paper reflects on the impact of Covid 19 lockdown in India on religious festivals. Two Hindu religious festivals in the state of Kerala namely Vishu and Thrissur Pooram are addressed here. Both festivals are immensely popular and close to the heart of the Malayali Hindu and non-Hindu communities alike. Rather than focusing on the economic impact, the emphasis here is on the socio cultural and psychological impact that it has had on the community. The nature and spirit of these festivals differ from one another which has helped or worsened the impact for the festival lovers. Due to the Covid 19 lockdown measures, secondary data collection is reduced to data sources such as newspaper articles, magazines, media reports, reflections and author insights regarding the general ‘vibe’ of the community. The findings suggest that the Vishu festival, even after the strict measures in place, was successful in the eyes of the community and its spirit was not broken. However, in the case of Thrissur Pooram, there is massive disappointment amongst the community and possible alternatives such as a Virtual Pooram could shape the future of such festivals
Knowledge engineering for modern information systems: methods, models and tools De Gruyter series on smart computing applications ;, v. 3./ edited by Anand Sharma, Sandeep Kautish, Prateek Agrawal, Vishu Madaan, Charu Gupta, Saurav Nanda.
No full textIncludes bibliographical references and index.Knowledge Engineering (KE) is a field within artificial intelligence that develops knowledge based systems. KE is the process of imitating how a human expert in a specific domain would act and take decisions. It contains large amounts of knowledge, like metadata and information about a data object that describes characteristics such as content, quality, and format, structure and processes. Such systems are computer programs that are the basis of how a decision is made or a conclusion is reached. It is having all the rules and reasoning mechanisms to provide solutions to real-world problems. This book presents an extensive collection of the recent findings and innovative research in the information system and KE domain. Highlighting the challenges and difficulties in implementing these approaches, this book is a critical reference source for academicians, professionals, engineers, technology designers, analysts, undergraduate and postgraduate students in computing science and related disciplines such as Information systems, Knowledge Engineering, Intelligent Systems, Artificial Intelligence, Cognitive Neuroscience, and Robotics. In addition, anyone who is interested or involved in sophisticated information systems and knowledge engineering developments will find this book a valuable source of ideas and guidance.P. Megaladevi -- Saikat Samanta, Achyuth Sarkar, Charu Gupta, Aditi Sharma -- Kudirat Abiola Adegoke, Akor P. Usman, Mohamed Bitagi -- Anagha Shenoy R, Bhoomika M, Annaiah H -- Neeraj Bhanot, Parth Padalkar -- Shubhika Gaur, Vibha Maheshwari -- Sanjive Saxena -- Ria Rawal, Kartik Goel, Akshay Gulati, Shivang Sharma, Palak Girdhar, Charu Gupta, Prateek Agrawal -- A. Ilmudeen -- Andualem Walelign Lale -- Hazik Mohamed -- Priyanka Jain, Ram Bhavsar, B.V. Pawar, N.K. Jain, Hemant Darbari, Virendrakumar C. Bhavsar. Knowledge engineering for industrial expert systems / Machine learning integrated blockchain model for Industry 4.0 smart applications / Prototyping the expectancy disconfirmation theory model for quality service delivery in federal university libraries in Nigeria / Design of chatbot using natural language processing / Algorithm development based on an integrated approach for identifying cause and effect relationships between different factors / Risk analysis and management in projects / Assessing and managing risks in smart computing applications / COVID-19 visualization and exploratory data analysis / Business intelligence and decision support systems: business applications in the modern information system era / Business intelligence implementation in different organizational setup evidence from reviewed literatures / Conceptualization of a modern digital-driven health-care management information system (HMIS) / Knowledge engine for a Hindi text-to-scene generation system /1 online resource (vi, 232 pages)
Deep Learning-Based Video Compression for Surveillance Footage
No full textThe utilization of closed-circuit television (CCTV) monitoring plays a pivotal role in the realm of video processing, providing an effective means for vigilant surveillance. However, a significant challenge associated with this practice is the substantial demand it places on storage space. Traditionally, surveillance footage is stored on hard disk drives, and due to limited storage capacities, it often necessitates periodic deletion. To tackle this issue, we have introduced an innovative method for compressing CCTV video, named “Detection-Based video Compression” (DBVC). Our DBVC model is a two-step process. In the first step, we employ advanced neural network approaches such as Mask-RCNN and YOLOv4 to determine active and idle frames within the surveillance video. These cutting-edge techniques enable precise identification of objects and events of interest in the video feed. In the second step, we construct a new video composed solely of the active frames, eliminating redundant or uneventful segments. After conducting a comprehensive analysis of the experimental results, it is evident that Mask-RCNN stands out with an impressive detection accuracy of 98% on the COCO dataset, making it a robust choice for identifying objects and events in the surveillance footage. Consequently, we chose to leverage the output generated by Mask-RCNN and YOLOv4 for subsequent processing stages. Our DBVC approach is a breakthrough in video compression technology, significantly reducing the storage space required for CCTV footage. In fact, it achieves an average compression ratio of up to 85% when using YOLOv4, surpassing the capabilities of existing state-of-the-art compression methods. This innovation not only optimizes storage efficiency but also maintains a high level of surveillance data integrity, making it a valuable advancement in the field of CCTV video processing and storage management
