Title :
Heart sound analysis using neural and statistical classifiers: a comparison
Author :
Bothe, Alexander
Abstract :
The results of a classical pattern recognition approach to heart sound analysis are compared with those of a trained neural network classifier. Noise not correlated with the specific heart operation is reduced by use of adaptive digital online filtering. The results, indicating the advantages of learning neural classifiers, are regarded as being transferable to other applications
Keywords :
bioacoustics; cardiology; computerised signal processing; medical diagnostic computing; neural nets; adaptive digital online filtering; classical pattern recognition approach; heart sound analysis; noise; specific heart operation; statistical classifier; trained neural network classifier; Acoustic noise; Adaptive filters; Cardiac disease; Frequency domain analysis; Heart beat; Noise reduction; Pattern recognition; Power generation; Pulse measurements; Stethoscope;
Conference_Titel :
Computers in Cardiology 1989, Proceedings.
Conference_Location :
Jerusalem
Print_ISBN :
0-8186-2114-1
DOI :
10.1109/CIC.1989.130582
