A combination of genetic algorithm-based fuzzy C-means with a convex hull-based regression for real-time fuzzy switching regression analysis: Application to industrial intelligent data analysis

Azizul Azhar Ramli*, Junzo Watada, Witold Pedrycz

*この研究の対応する著者

    研究成果: Article査読

    13 被引用数 (Scopus)

    抄録

    Processing an increasing volume of data, especially in industrial and manufacturing domains, calls for advanced tools of data analysis. Knowledge discovery is a process of analyzing data from different perspectives and summarizing the results into some useful and transparent findings. To address such challenges, a thorough extension and generalization of well-known techniques such as regression analysis becomes essential and highly advantageous. In this paper, we extend the concept of regression models so that they can handle hybrid data coming from various sources which quite often exhibit diverse levels of data quality. The major objective of this study is to develop a sound vehicle of a hybrid data analysis, which helps in reducing the computing time, especially in cases of real-time data processing. We propose an efficient real-time fuzzy switching regression analysis based on a genetic algorithm-based fuzzy C-means associated with a convex hull-based fuzzy regression approach. The method enables us to deal with situations when one has to deal with heterogeneous data which were derived from various database sources (distributed databases). In the proposed design, we emphasize a pivotal role of the convex hull approach, which is essential to alleviate the limitations of linear programming when being used in modeling of real-time systems.

    本文言語English
    ページ(範囲)71-82
    ページ数12
    ジャーナルIEEJ Transactions on Electrical and Electronic Engineering
    9
    1
    DOI
    出版ステータスPublished - 2014 1月

    ASJC Scopus subject areas

    • 電子工学および電気工学

    フィンガープリント

    「A combination of genetic algorithm-based fuzzy C-means with a convex hull-based regression for real-time fuzzy switching regression analysis: Application to industrial intelligent data analysis」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