Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Author: search.filters.author.Radhakrishnan, V.

Search Results

Now showing 1 - 2 of 2
  • 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
    Trace-Driven Simulation and Design Space Exploration of Network-on-Chip Topologies on FPGA
    (Institute of Electrical and Electronics Engineers Inc., 2018) Sangeetha, G.S.; Radhakrishnan, V.; Prabhu Prasad, P.; Parane, K.; Talawar, B.
    Networking On Chips is now becoming an extremely important part of the present and future of electronic technology. It is extensively used in Multiprocessor System-on-Chips and in Chip Multiprocessors. Using an NoC, the backend wiring involved has drastically reduced in an SoC. Further, SoCs with NoC interconnect operates at a higher operating frequency, mainly because the hardware required for switching and routing are simplified. The NoC researchers have relied on simulators based on performance and power to study the different factors of NoC such as algorithm in place, the topology, the buffer management and location schemes, the flow control and routing among others. In this paper, we present a trace-driven NoC architecture that gives the user access to realistic details about the resource utilization of NoC architectures and their individual components. This includes exploration of various design decision parameters of NoC by modeling them on a FPGA. The paper also presents the performance of these architectures by conducting trace-driven simulations using benchmarks like PARSEC. Different topologies are considered for experimentation purposes with different routing algorithms. © 2018 IEEE.