Title :
A heart sound feature extraction algorithm based on wavelet decomposition and reconstruction
Author :
Liang, Huiying ; Hartimo, Iiro
Author_Institution :
Signal Process. & Comput. Technol. Lab., Helsinki Univ. of Technol., Espoo, Finland
fDate :
29 Oct-1 Nov 1998
Abstract :
An algorithm based on the wavelet decomposition and reconstruction method was developed to extract features from the heart sound recordings. An artificial neural networks classification method based on these features was used to classify the heart sound signals into physiological and pathological murmurs. The classification result indicated 74.4% accuracy
Keywords :
acoustic signal processing; bioacoustics; cardiology; feature extraction; medical signal processing; neural nets; signal reconstruction; wavelet transforms; artificial neural networks classification method; classification result; heart sound feature extraction algorithm; heart sound recordings; pathological murmurs; physiological murmurs; reconstruction method; wavelet decomposition; Acoustic signal processing; Cardiac disease; Feature extraction; Frequency; Heart valves; Pathology; Pediatrics; Signal processing algorithms; Testing; Timing;
Conference_Titel :
Engineering in Medicine and Biology Society, 1998. Proceedings of the 20th Annual International Conference of the IEEE
Conference_Location :
Hong Kong
Print_ISBN :
0-7803-5164-9
DOI :
10.1109/IEMBS.1998.747181
