Combining multiple classifiers to quantitatively rank the impact of abnormalities in flight data

Edward Smart, David J. Brown, J. Denman

    Research output: Contribution to journalArticlepeer-review

    119 Downloads (Pure)

    Abstract

    This paper presents a novel two phase method that combines one class support vector machine classifiers using combination rules to quantitatively assess the degree of abnormality at various heights during individual aircraft descents and also over the whole descent. Whilst classifiers have been combined before in the literature with success, it is the first time they have been applied to the problem of analysing the act of descending of commercial jet aircraft. The method is tested on artificial Gaussian data and flight data from an industrial partner, Flight Data Services Ltd., the world's leading flight data analysis provider, with promising results.
    Original languageEnglish
    Pages (from-to)2583 - 2592
    Number of pages10
    JournalApplied Soft Computing
    Volume12
    Issue number8
    DOIs
    Publication statusPublished - Aug 2012

    Keywords

    • Support vector machines

    Fingerprint

    Dive into the research topics of 'Combining multiple classifiers to quantitatively rank the impact of abnormalities in flight data'. Together they form a unique fingerprint.

    Cite this