Title :
A multi-stage neural network classifier for ECG events
Author :
Hosseini, H. Gholam ; Reynolds, K.J. ; Powers, D.
Author_Institution :
Dept. of Electrotechnol., Auckland Univ. of Technol., New Zealand
Abstract :
In this paper, a multi-stage network including two multilayer perceptron (MLP) and one self organizing map (SOM) networks is presented. The input of the network is a combination of independent features and the compressed ECG data. The proposed network as a form of data fusion, performs better than using the raw data or individual features. We classified six common ECG waveforms using ten ECG records of the MIT/BIH arrhythmia database. An average recognition rate of 0.883 was achieved within a short training and testing time.
Keywords :
electrocardiography; feature extraction; medical expert systems; medical signal processing; multilayer perceptrons; self-organising feature maps; sensor fusion; signal classification; ECG event classifier; ECG signal diagnosis; MIT/BIH arrhythmia database; atrial premature beat; compressed data; computer-aided diagnosis; data fusion; extracted features; multilayer perceptron networks; multistage neural network classifier; paced beats; premature ventricular contraction; right bundle branch block; self organizing map network; short training time; Autocorrelation; Electrocardiography; Event detection; Feature extraction; Heart beat; Histograms; Neural networks; Performance evaluation; Signal processing; Testing;
Conference_Titel :
Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE
Print_ISBN :
0-7803-7211-5
DOI :
10.1109/IEMBS.2001.1020536
