8th International Conference on Communications and Networking in China

Research Article

ECG Classification based on Sparse Constrained Nonnegative-Matrix Factorization and Decision Tree

  • @INPROCEEDINGS{10.1109/ChinaCom.2013.6694689,
        author={yao li and qingning zeng},
        title={ECG Classification based on Sparse Constrained Nonnegative-Matrix Factorization and Decision Tree},
        proceedings={8th International Conference on Communications and Networking in China},
        publisher={IEEE},
        proceedings_a={CHINACOM},
        year={2013},
        month={11},
        keywords={sparse decomposition; nonnegative matrix factorization (nmf); eigenvector; electrocardiograph (ecg); classification method},
        doi={10.1109/ChinaCom.2013.6694689}
    }
    
  • yao li
    qingning zeng
    Year: 2013
    ECG Classification based on Sparse Constrained Nonnegative-Matrix Factorization and Decision Tree
    CHINACOM
    IEEE
    DOI: 10.1109/ChinaCom.2013.6694689
yao li1,*, qingning zeng1
  • 1: Guilin University of Electronic Technology
*Contact email: 297419356@qq.com

Abstract

In this paper, several data dimensionality reduction methods are compared. Then an ECG classification method is proposed which, employs the sparse decomposition of Nonnegative Matrix Factorization (SCNMF) for data dimensionality reduction, and Decision Tree for signal classification. The experimental results, in which five common heart diseases in the MIT-BIH database are used, indicate that the overall accuracy by the proposed ECG classification method reaches more than 99%. In addition, the employed data dimensionality reduction method can better retain the useful raw information and can save storage space.