Application of independent component analysis in removing artefacts from the electrocardiogram

被引:154
作者
He, TG [1 ]
Clifford, G [1 ]
Tarassenko, L [1 ]
机构
[1] Univ Oxford, Signal Proc & Neural Networks Res Grp, Dept Engn Sci, Oxford OX1 2JD, England
关键词
independent component analysis; artefacts; noise removal; ECG; permutation;
D O I
10.1007/s00521-005-0013-y
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Routinely recorded electrocardiograms (ECGs) are often corrupted by different types of artefacts and many efforts have been made to enhance their quality by reducing the noise or artefacts. This paper addresses the problem of removing noise and artefacts from ECGs using independent component analysis (ICA). An ICA algorithm is tested on three-channel ECG recordings taken from human subjects, mostly in the coronary care unit. Results are presented that show that ICA can detect and remove a variety of noise and artefact sources in these ECGs. One difficulty with the application of ICA is the determination of the order of the independent components. A new technique based on simple statistical parameters is proposed to solve this problem in this application. The developed technique is successfully applied to the ECG data and offers potential for online processing of ECG using ICA.
引用
收藏
页码:105 / 116
页数:12
相关论文
共 25 条
[11]  
Hyvarinen A., 1999, Neural Computing Surveys, V2
[12]  
Jung TP, 2000, PSYCHOPHYSIOLOGY, V37, P163, DOI 10.1017/S0048577200980259
[13]  
JUNG TP, 2000, 2 INT WORKSH IND COM, P633
[14]   ON MULTIPLE PATTERN EXTRACTION USING SINGULAR-VALUE DECOMPOSITION [J].
KANJILAL, PP ;
PALIT, S .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1995, 43 (06) :1536-1540
[15]   ADAPTIVE FILTER FOR EVENT-RELATED BIOELECTRIC SIGNALS USING AN IMPULSE CORRELATED REFERENCE INPUT - COMPARISON WITH SIGNAL AVERAGING TECHNIQUES [J].
LAGUNA, P ;
JANE, R ;
MESTE, O ;
POON, PW ;
CAMINAL, P ;
RIX, H ;
THAKOR, NV .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 1992, 39 (10) :1032-1044
[16]  
MCCLELLAN P, 1979, ALGORITHM 5 1 PROGRA
[17]   A transform domain SVD filter for suppression of muscle noise artefacts in exercise ECG's [J].
Paul, JS ;
Reddy, MR ;
Kumar, VJ .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2000, 47 (05) :654-663
[18]  
SPEIRS CA, 1994, P EURIPCO 94 EUR SIG, P1129
[19]   ADAPTIVE GAUSSIAN FILTERING IN ROUTINE ECG/VCG ANALYSIS [J].
TALMON, JL ;
KORS, JA ;
VANBEMMEL, JH .
IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1986, 34 (03) :527-534
[20]  
TARASSENKO L, 2001, P IEEE DERA WORKSH I