Optimization of a Similarity Performance on Bounded Content of Motion Histogram by Using Distributed Model
Abstract
In this paper, a content-based video retrieval (CBVR) system called Bounded Coordinate of Motion Histogram version 2 (BCMH v2) was processed on a distributed computing platform by using Apache Hadoop framework and a real-time distributed storage system using HBase. In fact, the amount of multimedia data is growing exponentially. Most of this data is available in image and video models. Analyzing huge data involves complex algorithms, which leads to challenges in optimizing processing time and data storage capacity. Many content-based video retrieval systems are suitable for processing large video dataset, but they are limited by the computational time and/or storage on a single machine. Thus, this paper presents the effectiveness of the proposed method with the distributed computing platform and its evaluation on the HOLLYWOOD2 video dataset. The experimental results demonstrate the good performances of the proposed approach.
... In 2021, Saoudi, E.M., et al [19] presented an HBase-based real-time ...
Developing Content-Based Video Retrieval (CBVR) for large-scale videos is a major challenge due to the enormous growth of video content on the internet. One of the major downfalls associated with CBVR is high search response time and low accuracy. In this paper, a Novel Fuzzy entropy based Leaky ShuffleNet CBVR system has been proposed to reduce the search response time and for high accuracy. The proposed system has three major phases i) Data Processing, ii) Feature Extraction and iii) Feature selection and iv) Similarity search. Initially, the video is processed using Apache storm to convert video into keyframes. Consequently, facial landmarks, head pose, and eye gaze, edges are extracted using various feature extraction techniques. The most relevant features are selected in the feature selection phase by using the Fuzzy entropy measure. Finally, based on the selected features Leaky ShuffleNet retrieve the relevant videos based on the user query. Experiments were performed on two different datasets such as Hollywood2 and UCF50 in three different setups (Single Node, Vertical Scaling, Horizontal Scaling). Several metrics were analyzed to measure the effectiveness of the suggested strategy, including recall, specificity, accuracy, precision, and the F-measure. According to experimental results, the proposed system has a search reaction time of 0.75 seconds, which is lower than the existing methods. The proposed method improves the overall accuracy by 1.2%, 2.5%, and 3.2% better than the existing ECBVR-ACNN, FALKON, and EE-CBVR respectively.
While the world wide web (www) has experienced series of evolutionary changes, beginning from www (the static web pages), passing through to web2 (social networking web) onto the present web3 (ubiquitous computing web), for the first time in its history, the internet is undergoing a major evolutionary change from Internet of people we have come to know to Internet of Things IoT. Just as the Internet changed our ways of life and communication, much more so will IoT change the world of Information and Communication Technologies. This development is not unconnected to the abundant availability of ubiquitous sensing enabled by Wireless Sensor Networks (WSN) technologies that cuts across many areas of modern day living. As recent adaptation of wireless technologies such as RFID tags fuels IoT, sensors and actuators will much more blend seamlessly with the environment around us and information will be shared across platforms in order to develop a common operating picture(COP), offering us the ability to measure, infer and understand environmental indicators, be it our ecological system, natural resources, man himself or man-made urban city and components. To that end there will definitely be issues with trust, privacy and security of data. This paper reviews technologies that will drive IoT and the place of Trust, Privacy and Data Security in these technologies and IoT in general.
Information Literacy now-a -days plays a very important role in everyday life because it involves a combination of education, job related task social involvements and social cultural practice. Information literacy is important for individuals to reach their desired goal in any field. The present study has been undertaken with a view to promote information literacy among Special library users with Special reference to the Silchar Medical College, Silchar, Assam. The present work was carried out during March 2018 to July 2018. For that purpose, survey method has been adopted, which comprises of questionnaire, for knowing the opinion of the respondents in respect of Promoting Information literacy among the library users. The study result reveals that a few students were aware about the different sources of information and also the different search techniques. The study also reveals that the promotion of information literacy is required in many areas such as Library OPAC, Classification and cataloguing etc.
Advice on how companies can succeed in the new digital business environment.
The most important skills a leader needs to succeed in a digital environment are not technical in nature but managerial—strategic vision, forward-looking perspective, change-oriented mindset. A company's digital transformation does not involve abandoning widget-making for app developing or pursuing “disruption” at the cost of stability. Rather, it is about adopting business processes and practices that position organizations to compete effectively in the digital environment. More important than technology implementation are strategy, talent management, organizational structure, and leadership aligned for the digital world. How to Go Digital offers advice from management experts on how to steer your company into the digital future.
The book will put you on the right strategic path, with articles from MIT Sloan Management Review on developing a digital strategy, reframing growth for a digital world, monetizing data, and generating sustainable value from social media. Talent acquisition and retention are addressed, with articles on HR analytics, data translators, and enabling employees to become brand ambassadors outside of the office. Operational makeovers are discussed in terms of sales, services, new technologies, and innovation.
ContributorsAllan Alter, Stephen J. Andriole, Bart Baesens, Gloria Barczak, Cynthia M. Beath, Alpheus Bingham, Didier Bonnet, Chris Brady, Joseph Byrum, Marina Candi, Manuel Cebrian, Marie-Cécile Cervellon, Simon Chadwick, Sophie De Winne, Mike Forde, Gerald C. Kane, Rahul Kapoor, David Kiron, Thomas Klueter, Mary C. Lacity, Rikard Lindgren, Pamela Lirio, Tucker J. Marion, Lars Mathiassen, Pete Maulik, Paul Michelman, Narendra Mulani, Pierre Nanterme, Doug Palmer, Alex “Sandy” Pentland, Anh Nguyen Phillips, Frank T. Piller, Iyad Rahwan, Deborah L. Roberts, Jeanne W. Ross, Ina M. Sebastian, Luc Sels, James E. Short, Fredrik Svahn, Steve Todd, Leslie P. Willcocks, H. James Wilson, Barbara H. Wixom
Neuroimaging, in particular magnetic resonance imaging (MRI), has been playing an important role in understanding brain functionalities and its disorders during the last couple of decades. These cutting-edge MRI scans, supported by high-performance computational tools and novel ML techniques, have opened up possibilities to unprecedentedly identify neurological disorders. However, similarities in disease phenotypes make it very difficult to detect such disorders accurately from the acquired neuroimaging data. This article critically examines and compares performances of the existing deep learning (DL)-based methods to detect neurological disorders—focusing on Alzheimer’s disease, Parkinson’s disease and schizophrenia—from MRI data acquired using different modalities including functional and
structural MRI. The comparative performance analysis of various DL architectures across different disorders and imaging modalities suggests that the Convolutional Neural Network outperforms other methods in detecting neurological disorders. Towards the end, a number of current research challenges are indicated and some possible future research directions are provided.
