Comparing the performance of three neural classifiers for use in embedded applications

Yuhua Li, MJ Pont, CR Parikh, NB Jones

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    In this paper, we provide a detailed empirical comparison of three neural-based classifiers used in embedded applications. The three techniques (multi-layer Perceptrons, radial basis function networks and adaptive fuzzy systems) are compared with one another and with a classical kNN classifier. In this study, we observe that the MLP provides similar levels of performance to the RBFN, AFS land kNN) classifiers while exerting a lower computational load on the processor.
    Original languageEnglish
    Title of host publicationUnknown Host Publication
    Pages34-39
    Number of pages6
    Publication statusPublished - 2000
    EventSOFT COMPUTING TECHNIQUES AND APPLICATIONS -
    Duration: 1 Jan 2000 → …

    Publication series

    NameADVANCES IN SOFT COMPUTING

    Conference

    ConferenceSOFT COMPUTING TECHNIQUES AND APPLICATIONS
    Period1/01/00 → …

    Keywords

    • multi-layer perceptron network
    • radial basis function network
    • adaptive fuzzy system
    • k-nearest neighbour
    • embedded system

    Fingerprint Dive into the research topics of 'Comparing the performance of three neural classifiers for use in embedded applications'. Together they form a unique fingerprint.

  • Cite this

    Li, Y., Pont, MJ., Parikh, CR., & Jones, NB. (2000). Comparing the performance of three neural classifiers for use in embedded applications. In Unknown Host Publication (pp. 34-39). (ADVANCES IN SOFT COMPUTING).