• Login
    View Item 
    •   Treasures Home
    • Electronic Theses and Dissertations
    • UTD Theses and Dissertations
    • View Item
    •   Treasures Home
    • Electronic Theses and Dissertations
    • UTD Theses and Dissertations
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Guidelines and Benchmarks for Deployment of Deep Learning Models on Smartphones as Real-Time Apps

    Thumbnail
    View/Open
    Dissertation (3.220Mb)
    Date
    2019-05
    Author
    Sehgal, Abhishek
    Metadata
    Show full item record
    Abstract
    Abstract
    In many pattern recognition or machine learning applications, deep learning models or deep neural networks have provided superior performance relative to feature-based classifiers. Although there exist a number of publicly available software tools that enable the development of deep learning models to be achieved with ease, no guidelines are currently available in one place and in a unified manner in the literature for using these tools towards real-time deployment of deep learning models on smartphones, which have now become the most widely used computing device in the world. A uniform flow of implementation is developed in this dissertation for deployment of deep learning models on smartphones as real-time apps on both Android and iOS devices. A benchmarking framework consisting of accuracy, CPU/GPU consumption, and real-time throughput is devised for this deployment. These guidelines are applied to image and audio processing applications. As an image processing application, six widely used deep learning models are implemented to run in real-time on smartphones for recognizing objects based on video captured by their cameras. As an audio processing application, a low audio-latency signal processing pipeline along with a multi-rate processing technique are developed in order to achieve a convolutional neural network-based voice activity detection.
    URI
    https://hdl.handle.net/10735.1/6945
    Collections
    • UTD Theses and Dissertations

    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     

    Browse

    All of TreasuresCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    Login

    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV