Front Inner Page - Volume 1 No.2 October 2014

  • » Back to Index

  • Title

    :

    A GROUP INCREMENTAL APPROACH TO FEATURE SELECTION APPLYING ROUGH SET TECHNIQUE

    Authors

    :

    E. Anushya1, Mr.K.Selvaraj2

    Keywords

    :

    Heuristic algorithms, Entropy, Information entropy, Uncertainty, Approximation algorithms, Measurement uncertainty, rough set theory, Dynamic data sets, incremental algorithm, feature selection.

    Issue Date

    :

    October – 2014

    Abstract

    :

    The dynamic growth in the size of numerous real data occurs in several domains such as population studies, economics and medical research. As an effective and efficient mechanism to deal those data, an incremental technique has been proposed in the literature and attracted great attention, which stimulates the result in this paper. We present the incremental mechanisms for three representative information entropies. A group incremental rough feature selection algorithm is also proposed based on information entropy. When multiple objects are added to a decision table, the proposed algorithm aims to find the new feature subset within a shorter time. The experiments have been carried out on 8 UCI data sets and the experimental results show that the algorithm is efficient than the existing algorithm.

    Page(s)

    :

    1-6

    ISSN

    :

    2347- 4734

    Source

    :

    Vol. 1, No.2, October 2014

    Download

    :


  • » Back index