Browsing by Author "Joseph, C."

Filter results by typing the first few letters
Now showing 1 - 5 of 5
  • No Thumbnail Available
    Item
    Machine Learning Approaches for Resource Allocation in the Cloud: Critical Reflections
    (2018) Murali, A.; Das, N.N.; Sukumaran, S.S.; Chandrasekaran, K.; Joseph, C.; Martin, J.P.
    Resource Allocation is the effective and efficient use of a Cloud's resources and is a very challenging problem in cloud environments. Many attempts have been made to make Resource Allocation automated and optimal in terms of profit. The best of these methods used Machine Learning, but this comes with an overhead for computation. A lot of research has been done in this domain to find more efficient methods. Distributed Neural Networks (DNN) is the future of computation and will soon be used to make the computation of large-scale data faster and easier. DNN is currently the most researched area. This paper will summarize the major research works in these fields. A new taxonomy is proposed and can be used as a reference for all future research in this domain. The paper also proposes some areas that need more research in the foreseeable future. � 2018 IEEE.
  • No Thumbnail Available
    Item
    Paving the way for autonomic clouds: State-of-the-art and future directions
    (Springer Verlag service@springer.de, 2018) Joseph, C.; Chandrasekaran, K.
    Cloud Computing is the core technology that helps in catering to the computing needs of the current generation. As the customers increase, data center providers are looking for efficient mechanisms to handle the management of the large reservoir of resources involved in the Cloud environment. In order to support efficient managing, it is the need of the day to adopt the concept of Autonomic Computing into Cloud. Several researchers have been attempted to improve the managing capability of the Cloud, by encorporating autonomic capabilities for resources in the Cloud. Most of the researches attempt to automate some aspects while the remaining portion of the Cloud does not have autonomic functionalities. An autonomic Cloud is one where all the operations can be handled without human intervention. There is a long way to go to achieve this vision. In our study, we first categorize the various existing approaches on the basis of the methodology employed and analyze the different self-*properties considered by the different approaches. It is observed that in each approach, researchers focus on one or at most two self-*properties. Based on our analysis, we suggest some of the future directions that can be paved on by researchers working in this domain. © 2018, Springer Nature Singapore Pte Ltd.
  • No Thumbnail Available
    Item
    Sentiment extraction from naturalistic video
    (2018) Radhakrishnan, V.; Joseph, C.; Chandrasekaran, K.
    Sentiment analysis on video is quite an unexplored field of research wherein the emotion and sentiment of the speaker are extracted by processing the frames, audio and text obtained from the video. In recent times, sentiment analysis from naturalistic audio has been an upcoming field of research. This is typically done by performing automatic speech recognition on audio, followed by extracting the sentiment exhibited by the speaker. On the other hand, techniques for extracting sentiments from text are quite developed and tech giants have already optimized these methods to process large amounts of customer review, feedback and reactions. In this paper, a new model for sentiment analysis from audio is proposed which is a hybrid of Keyword Spotting System (KWS) and Maximum Entropy (ME) Classifier System. This model is developed with the aim to outperform other conventional classifiers and to provide a single integrated system for audio and text processing. In addition, a web application for dynamic processing of YouTube videos is described. The WebApp provides an index-based result for each phrase that is detected in the video. Often, the emotion of the viewer of a video corresponds to its content. In this regard, it is useful to map these emotions to the text transcript of the video and assign a suitable weight to it while predicting the sentiment that the speaker exhibits. This paper describes such an application that was developed to analyze facial expressions using Affdex API. Thus, using the combined statistics from all the three aforementioned components, a robust and portable system for emotion detection is obtained that provides accurate predictions and can be deployed on any modern systems with minimal configuration changes. � 2018 The Authors. Published by Elsevier B.V.
  • No Thumbnail Available
    Item
    Sentiment extraction from naturalistic video
    (Elsevier B.V., 2018) Radhakrishnan, V.; Joseph, C.; Chandrasekaran, K.
    Sentiment analysis on video is quite an unexplored field of research wherein the emotion and sentiment of the speaker are extracted by processing the frames, audio and text obtained from the video. In recent times, sentiment analysis from naturalistic audio has been an upcoming field of research. This is typically done by performing automatic speech recognition on audio, followed by extracting the sentiment exhibited by the speaker. On the other hand, techniques for extracting sentiments from text are quite developed and tech giants have already optimized these methods to process large amounts of customer review, feedback and reactions. In this paper, a new model for sentiment analysis from audio is proposed which is a hybrid of Keyword Spotting System (KWS) and Maximum Entropy (ME) Classifier System. This model is developed with the aim to outperform other conventional classifiers and to provide a single integrated system for audio and text processing. In addition, a web application for dynamic processing of YouTube videos is described. The WebApp provides an index-based result for each phrase that is detected in the video. Often, the emotion of the viewer of a video corresponds to its content. In this regard, it is useful to map these emotions to the text transcript of the video and assign a suitable weight to it while predicting the sentiment that the speaker exhibits. This paper describes such an application that was developed to analyze facial expressions using Affdex API. Thus, using the combined statistics from all the three aforementioned components, a robust and portable system for emotion detection is obtained that provides accurate predictions and can be deployed on any modern systems with minimal configuration changes. © 2018 The Authors. Published by Elsevier B.V.
  • No Thumbnail Available
    Item
    Virtual machine migration—a perspective study
    (Springer Verlag service@springer.de, 2018) Joseph, C.; Martin, J.P.; Chandrasekaran, K.; Kandasamy, A.
    The technology of Cloud computing has been ruling the IT world for the past few decades. One of the most notable tools that helped in prolonging the reign of Cloud computing is virtualization. While virtualization continues to be a boon for the Cloud technology, it is not short of its own pitfalls. One such pitfall results from the migration of virtual machines. Though migration incurs an overhead on the system, an efficient system cannot neglect migrating the virtual machines. This work attempts to carry out a perspective study on virtual machine migration. The various migration techniques proposed in the literature have been classified based on the aspects of migration that they consider. A survey of the various metrics that characterize the performance of a migration technique is also done. © 2018, Springer Nature Singapore Pte Ltd.