In this paper, a ensemble learning classification algorithm based on the novel feature selection method is proposed. The feature selection method takes full account of the discrimination and class information of each feature by calculating the scores. Specially, the scores are fused for getting a weight for each feature. We select the significant features according to the weights. The result of feature selection will help to improve the classification accuracy. The ensemble learning method improves the classification performance of single classifier. We compare our method with several classical feature selection methods by theoretical analysis and extensive experiments. Experimental results show that our method can achieve higher predictive accuracy than several classical feature selection methods.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Research on the ensemble learning classification algorithm based on the novel feature selection method


    Contributors:
    Ming-hai, Yao (author) / Na, Wang (author)


    Publication date :

    2013-07-01


    Size :

    351314 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Lower bounds in classification for feature and algorithm selection

    Lampropoulos, G. A. / Chuhong Fei, / Ting Liu, et al. | IEEE | 2011


    Novel Selective Support Vector Machine Ensemble Learning Algorithm

    Tang, Y. / Gao, J. / Qianzong, B. | British Library Online Contents | 2008


    Urban Road Traffic State Level Classification Based on Dynamic Ensemble Learning Algorithm

    Liu, Qingchao / Cai, Yingfeng / Jiang, Haobin et al. | ASCE | 2018


    A novel feature selection framework for automatic web page classification

    Alamelu Mangai, J. / Santhosh Kumar, V. / Appavu alias Balamurugan, S. | British Library Online Contents | 2012