본문 바로가기
  • Home

Rhythm Classification of ECG Signal by Rule and SVM Based Algorithm

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2013, 18(9), pp.43-51
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science

Sungoan Kim 1 김대환 1

1수원과학대학교

Accredited

ABSTRACT

Classification result by comprehensive analysis of rhythm section and heartbeat unit makes a reliable diagnosis of heart disease possible. In this paper, based on feature-points of ECG signals,rhythm analysis for constant section and heartbeat unit is conducted using rule-based classification and SVM-based classification respectively. Rhythm types are classified using a rule base deduced from clinical materials for features of rhythm section in rule-based classification, and monotonic rhythm or major abnormality heartbeats are classified using multiple SVMs trained previously for features of heartbeat unit in SVM-based classification. Experimental results for the MIT-BIH arrhythmia database show classification ratios of 68.52% by rule-based method alone and 87.04% by fusion method of rule-based and SVM-based for 11 rhythm types. The proposed fusion method is improved by about 19% through misclassification improvement for monotonic and arrangement rhythms by SVM-based method

Citation status

* References for papers published after 2022 are currently being built.