An outlier mining algorithm based on approximate outlier factor

Zhifang Liao, Limin Liu, Xiaoping Fan, Yueshan Xie, Zhining Liao, Yan Zhang

    Research output: Contribution to journalArticle

    Abstract

    In order to improve the efficiency of the method by clustering outlier detection, outlier mining algorithm based on approximate outlier factor (OMAAOF) algorithm based on approximate outlier factor is proposed in this paper. The algorithm first presents the definition of the approximate distance and outlier approximate coefficient, then provides an heuristic pruning strategies to reduce the suspect candidate sets to decrease the computational complexity. Experiments have been carried out with public datasets iris, labour and segment-test. The experimental results show that the performance of OMAAOF is effective.
    Original languageEnglish
    Pages (from-to)243-256
    Number of pages14
    JournalInternational Journal of Autonomous and Adaptive Communications Systems
    Volume8
    Issue number2/3
    DOIs
    Publication statusPublished - May 2015

    Fingerprint

    Computational complexity
    Personnel
    Experiments

    Keywords

    • outlier detection
    • outlying degree
    • pruning strategy
    • outlier mining
    • clustering
    • approximate distance
    • outlier approximate coefficient

    Cite this

    Liao, Zhifang ; Liu, Limin ; Fan, Xiaoping ; Xie, Yueshan ; Liao, Zhining ; Zhang, Yan. / An outlier mining algorithm based on approximate outlier factor. In: International Journal of Autonomous and Adaptive Communications Systems. 2015 ; Vol. 8, No. 2/3. pp. 243-256.
    @article{38b979312a5c4acc904fccaf234b9878,
    title = "An outlier mining algorithm based on approximate outlier factor",
    abstract = "In order to improve the efficiency of the method by clustering outlier detection, outlier mining algorithm based on approximate outlier factor (OMAAOF) algorithm based on approximate outlier factor is proposed in this paper. The algorithm first presents the definition of the approximate distance and outlier approximate coefficient, then provides an heuristic pruning strategies to reduce the suspect candidate sets to decrease the computational complexity. Experiments have been carried out with public datasets iris, labour and segment-test. The experimental results show that the performance of OMAAOF is effective.",
    keywords = "outlier detection, outlying degree, pruning strategy, outlier mining, clustering, approximate distance , outlier approximate coefficient",
    author = "Zhifang Liao and Limin Liu and Xiaoping Fan and Yueshan Xie and Zhining Liao and Yan Zhang",
    year = "2015",
    month = "5",
    doi = "10.1504/IJAACS.2015.069567",
    language = "English",
    volume = "8",
    pages = "243--256",
    journal = "International Journal of Autonomous and Adaptive Communications Systems",
    issn = "1754-8632",
    publisher = "Inderscience",
    number = "2/3",

    }

    An outlier mining algorithm based on approximate outlier factor. / Liao, Zhifang; Liu, Limin ; Fan, Xiaoping ; Xie, Yueshan; Liao, Zhining ; Zhang, Yan.

    In: International Journal of Autonomous and Adaptive Communications Systems, Vol. 8, No. 2/3, 05.2015, p. 243-256.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - An outlier mining algorithm based on approximate outlier factor

    AU - Liao, Zhifang

    AU - Liu, Limin

    AU - Fan, Xiaoping

    AU - Xie, Yueshan

    AU - Liao, Zhining

    AU - Zhang, Yan

    PY - 2015/5

    Y1 - 2015/5

    N2 - In order to improve the efficiency of the method by clustering outlier detection, outlier mining algorithm based on approximate outlier factor (OMAAOF) algorithm based on approximate outlier factor is proposed in this paper. The algorithm first presents the definition of the approximate distance and outlier approximate coefficient, then provides an heuristic pruning strategies to reduce the suspect candidate sets to decrease the computational complexity. Experiments have been carried out with public datasets iris, labour and segment-test. The experimental results show that the performance of OMAAOF is effective.

    AB - In order to improve the efficiency of the method by clustering outlier detection, outlier mining algorithm based on approximate outlier factor (OMAAOF) algorithm based on approximate outlier factor is proposed in this paper. The algorithm first presents the definition of the approximate distance and outlier approximate coefficient, then provides an heuristic pruning strategies to reduce the suspect candidate sets to decrease the computational complexity. Experiments have been carried out with public datasets iris, labour and segment-test. The experimental results show that the performance of OMAAOF is effective.

    KW - outlier detection

    KW - outlying degree

    KW - pruning strategy

    KW - outlier mining

    KW - clustering

    KW - approximate distance

    KW - outlier approximate coefficient

    U2 - 10.1504/IJAACS.2015.069567

    DO - 10.1504/IJAACS.2015.069567

    M3 - Article

    VL - 8

    SP - 243

    EP - 256

    JO - International Journal of Autonomous and Adaptive Communications Systems

    JF - International Journal of Autonomous and Adaptive Communications Systems

    SN - 1754-8632

    IS - 2/3

    ER -