Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Reza Soleimani; Seyed Mpjtaba Rouhani
Volume 5, Issue 2 , June 2011, , Pages 89-103
Abstract
in this paper, a novel and effective algorithm for classification of important heart arrhythmia is presented. The proposed algorithm uses heart rate variation (HRV) signal which has better chaotic characteristics. In addition to commonly used linear time domain and frequency domain features, nonlinear ...
Read More
in this paper, a novel and effective algorithm for classification of important heart arrhythmia is presented. The proposed algorithm uses heart rate variation (HRV) signal which has better chaotic characteristics. In addition to commonly used linear time domain and frequency domain features, nonlinear (chaotic) features are examined, too. To increase classification accuracy and facilitate learning, two techniques are used: a) extracted features are reduced by generalized discriminant analysis (GDA) and b) by a self organizing map (SOM), the most informant data are selected. Chaotic features help to improve diagnosis accuracy from 92% up to 97%. The results indicate the importance of GDA and SOM in efficiency of proposed algorithm. MLP, SVM and PNN classifiers are examined and compared. The proposed algorithm was able to diagnose 7 arrhythmias PVC, AFL, AF, CHB, LBBB, VF, VT and normal sinus rhythm (NSR) with 97.4% accuracy.
