• Login
    View Item 
    •   DORA Home
    • Faculty of Computing, Engineering and Media
    • School of Computer Science and Informatics
    • View Item
    •   DORA Home
    • Faculty of Computing, Engineering and Media
    • School of Computer Science and Informatics
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Comparing CNN and Human Crafted Features for Human Activity Recognition

    Thumbnail
    View/Open
    Main article (4.750Mb)
    Date
    2019-08
    Author
    Cruciani, Federico;
    Vafeiadis, Anastasios;
    Nugent, Chris;
    Cleland, Ian;
    McCullagh, Paul;
    Votis, Konstantinos;
    Giakoumis, Dimitrios;
    Tzovaras, Dimitrios;
    Chen, Liming;
    Hamzaoui, Raouf
    Metadata
    Show attachments and full item record
    Abstract
    Deep learning techniques such as Convolutional Neural Networks (CNNs) have shown good results in activity recognition. One of the advantages of using these methods resides in their ability to generate features automatically. This ability greatly simplifies the task of feature extraction that usually requires domain specific knowledge, especially when using big data where data driven approaches can lead to anti-patterns. Despite the advantage of this approach, very little work has been undertaken on analyzing the quality of extracted features, and more specifically on how model architecture and parameters affect the ability of those features to separate activity classes in the final feature space. This work focuses on identifying the optimal parameters for recognition of simple activities applying this approach on both signals from inertial and audio sensors. The paper provides the following contributions: (i) a comparison of automatically extracted CNN features with gold standard Human Crafted Features (HCF) is given, (ii) a comprehensive analysis on how architecture and model parameters affect separation of target classes in the feature space. Results are evaluated using publicly available datasets. In particular, we achieved a 93.38% F-Score on the UCI-HAR dataset, using 1D CNNs with 3 convolutional layers and 32 kernel size, and a 90.5% F-Score on the DCASE 2017 development dataset, simplified for three classes (indoor, outdoor and vehicle), using 2D CNNs with 2 convolutional layers and a 2x2 kernel size.
    Description
    Citation : F. Cruciani, A. Vafeiadis, C. Nugent, I. Cleland, P. McCullagh, K. Votis, D. Giakoumis, D. Tzovaras, L. Chen, R. Hamzaoui, Comparing CNN and human crafted features for human activity recognition. In: Proc. 16th IEEE International Conference on Ubiquitous Intelligence and Computing (UIC 2019), Leicester, Aug. 2019.
    URI
    https://www.dora.dmu.ac.uk/handle/2086/18111
    Research Institute : Cyber Technology Institute (CTI)
    Peer Reviewed : Yes
    Collections
    • School of Computer Science and Informatics [2968]

    Submission Guide | Reporting Guide | Reporting Tool | DMU Open Access Libguide | Take Down Policy | Connect with DORA
    DMU LIbrary
     

     

    Browse

    All of DORACommunities & CollectionsAuthorsTitlesSubjects/KeywordsResearch InstituteBy Publication DateBy Submission DateThis CollectionAuthorsTitlesSubjects/KeywordsResearch InstituteBy Publication DateBy Submission Date

    My Account

    Login

    Submission Guide | Reporting Guide | Reporting Tool | DMU Open Access Libguide | Take Down Policy | Connect with DORA
    DMU LIbrary