Skip to the content

Automated design of robust discriminant analysis classifier for foot pressure lesions using kinematic data

Goulermas, JY, Findlow, AH, Nester, CJ, Howard, D and Bowker, P 2005, 'Automated design of robust discriminant analysis classifier for foot pressure lesions using kinematic data' , IEEE Transactions on Biomedical Engineering, 52 (9) , pp. 1549-1562.

[img]
Preview
PDF (Publisher version)
Download (1078kB) | Preview

    Abstract

    In the recent years, the use of motion tracking systems for acquisition of functional biomechanical gait data, has received increasing interest due to the richness and accuracy of the measured kinematic information. However, costs frequently restrict the number of subjects employed, and this makes the dimensionality of the collected data far higher than the available samples. This paper applies discriminant analysis algorithms to the classification of patients with different types of foot lesions, in order to establish an association between foot motion and lesion formation. With primary attention to small sample size situations, we compare different types of Bayesian classifiers and evaluate their performance with various dimensionality reduction techniques for feature extraction, as well as search methods for selection of raw kinematic variables. Finally, we propose a novel integrated method which fine-tunes the classifier parameters and selects the most relevant kinematic variables simultaneously. Performance comparisons are using robust resampling techniques such as Bootstrap$632+$and k-fold cross-validation. Results from experimentations with lesion subjects suffering from pathological plantar hyperkeratosis, show that the proposed method can lead to$sim 96%$correct classification rates with less than 10% of the original features.

    Item Type: Article
    Uncontrolled Keywords: Bayes methods, feature extraction, gait analysis kinematics, medical signal processing, signal classification, Bayesian classifiers, Bootstrap 632+, biomechanical gait, feature extraction, foot motion, foot pressure lesions, k-fold cross-validation, kinematics, lesion formation, motion tracking systems, pathological plantar hyperkeratosis, robust discriminant analysis classifier, robust resampling, Bootstrap, classification, discriminant analysis, feature extraction/selection, foot kinematics, gait, genetic algorithm, hyperkeratosis, regularization
    Themes: Subjects / Themes > Q Science > Q Science (General)
    Subjects / Themes > R Medicine > R Medicine (General)
    Health and Wellbeing
    Subjects outside of the University Themes
    Schools: Colleges and Schools > College of Health & Social Care > School of Health Sciences > Centre for Health Sciences Research
    Colleges and Schools > College of Science & Technology
    Colleges and Schools > College of Science & Technology > School of Environment and Life Sciences
    Colleges and Schools > College of Science & Technology > School of Computing, Science and Engineering > CASE Control & Systems Engineering Research Centre
    Journal or Publication Title: IEEE Transactions on Biomedical Engineering
    Publisher: Institute of Electrical and Electronics Engineers (IEEE)
    Refereed: Yes
    ISSN: 00189294
    Related URLs:
    Depositing User: H Kenna
    Date Deposited: 07 Aug 2007 11:37
    Last Modified: 20 Aug 2013 16:45
    URI: http://usir.salford.ac.uk/id/eprint/131

    Actions (login required)

    Edit record (repository staff only)

    Downloads per month over past year

    View more statistics