Peak Detection using Syntactic Pattern Recognition in the ECG signal

Syntactic 패턴인식에 의한 심전도 피이크 검출에 관한 연구

  • 신건수 (연세대학교 공과대학 전기공학과) ;
  • 김용만 (연세대학교 공과대학 전기공학과) ;
  • 윤형로 (연세대학교 보건과학대학 의용공학과, 의과대학) ;
  • 이웅구 (연세대학교 심장내과) ;
  • 이명호 (연세대학교 공과대학 전기공학과)
  • Published : 1989.05.26

Abstract

This paper represents a syntactic peak detection algorithm which detects peaks in the ECG signal. In the algorithm, the input waveform is linearly approximated by "split-and-merge" method, and then each line segment is symbolized with primitive set. The peeks in the symbolized input waveform are recognized by the finite-state automata, which the deterministic finite-state language is parsed by. This proposed algorithm correctly detects peaks in a normal ECG signal as well as in the abnormal ECG signal such as tachycardia and the contaminated signal with noise.

Keywords