Building a memetic algorithm based support vector machine for imbalaced classification

Wu Mingnan*, Junzo Watada, Zuwarie Ibrahim, Marzuki Khalid

*この研究の対応する著者

    研究成果: Conference contribution

    抄録

    Classification analysis is one of core research topics in pattern recognition field. According to the distribution of samples, algorithms like artificial network (ANN) and support vector machine (SVM) have been proposed to perform binary classification. But these traditional classification algorithms hardly work well for imbalanced dataset. In this study, a novel model on the basis of memetic algorithm (MA) and support vector machine (SVM) is proposed to perform the classification for large imbalanced dataset. It is named MSVC (memetic support vector classification) model. Memetic Algorithm is recently proposed and used as a heuristic framework for the large imbalanced classification. Because of the high performance of SVM in balanced binary classification, support vector classification (SVC) is combined with MA to improve the classification accuracy. G-mean is used to check the final result. Compared with some conventional models, the results showed that this model is a proper alternative for imbalanced dataset classification, and it expends the applications of memetic algorithm.

    本文言語English
    ホスト出版物のタイトルProceedings - 2011 5th International Conference on Genetic and Evolutionary Computing, ICGEC 2011
    ページ389-392
    ページ数4
    DOI
    出版ステータスPublished - 2011
    イベント5th International Conference on Genetic and Evolutionary Computing, ICGEC2011 - Xiamen
    継続期間: 2011 8 292011 9 1

    Other

    Other5th International Conference on Genetic and Evolutionary Computing, ICGEC2011
    CityXiamen
    Period11/8/2911/9/1

    ASJC Scopus subject areas

    • 計算理論と計算数学
    • コンピュータ サイエンスの応用

    フィンガープリント

    「Building a memetic algorithm based support vector machine for imbalaced classification」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

    引用スタイル