BIROn - Birkbeck Institutional Research Online

    Neural network-based colonoscopic diagnosis using on-line learning and differential evolution

    Magoulas, George D. and Plagianakos, V.P. and Vrahatis, M.N. (2004) Neural network-based colonoscopic diagnosis using on-line learning and differential evolution. Applied Soft Computing 4 (4), pp. 369-379. ISSN 1568-4946.

    [img]
    Preview
    Text
    Binder1.pdf

    Download (565kB) | Preview

    Abstract

    In this paper, on-line training of neural networks is investigated in the context of computer-assisted colonoscopic diagnosis. A memory-based adaptation of the learning rate for the on-line back-propagation (BP) is proposed and used to seed an on-line evolution process that applies a differential evolution (DE) strategy to (re-) adapt the neural network to modified environmental conditions. Our approach looks at on-line training from the perspective of tracking the changing location of an approximate solution of a pattern-based, and thus, dynamically changing, error function. The proposed hybrid strategy is compared with other standard training methods that have traditionally been used for training neural networks off-line. Results in interpreting colonoscopy images and frames of video sequences are promising and suggest that networks trained with this strategy detect malignant regions of interest with accuracy.

    Metadata

    Item Type: Article
    Keyword(s) / Subject(s): minimally invasive imaging procedures, back-propagation networks, medical image interpretation, on-line learning, differential evolution strategies, artificial evolution
    School: Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences
    Research Centres and Institutes: Birkbeck Knowledge Lab
    Depositing User: Sandra Plummer
    Date Deposited: 05 Apr 2006
    Last Modified: 09 Aug 2023 12:29
    URI: https://eprints.bbk.ac.uk/id/eprint/350

    Statistics

    Activity Overview
    6 month trend
    983Downloads
    6 month trend
    538Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item