Classification of respiratory sounds by using an artificial neural network

Author

Sezgin, M.C. ; Dokur, Z. ; Olmez, T. ; Korurek, Mehmet

Author_Institution

Dept. of Electron. & Commun. Eng., Istanbul Tech. Univ., Turkey

Volume

1

fYear

2001

fDate

2001

Firstpage

697

Abstract

In this paper, a classification method for respiratory sounds (RSs) in patients with asthma and in healthy subjects is presented. A wavelet transform is applied to a window containing 256 samples. Elements of the feature vectors are obtained from the wavelet coefficients. The best feature elements are selected by using dynamic programming. A Grow and Learn (GAL) neural network is used for the classification. It is observed that RSs of patients (with asthma) and healthy subjects are successfully classified by the GAL network.

Keywords

acoustic signal processing; bioacoustics; diseases; dynamic programming; medical signal processing; neural nets; pneumodynamics; vectors; wavelet transforms; artificial neural network; asthma; feature vector elements; grow & learn neural network; healthy subjects; respiratory sounds classification; wavelet coefficients; Acoustical engineering; Artificial neural networks; Discrete wavelet transforms; Dynamic programming; Feature extraction; Lungs; Neural networks; Signal analysis; Signal processing; Wavelet coefficients;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE

ISSN

1094-687X

Print_ISBN

0-7803-7211-5

Type

conf

DOI

10.1109/IEMBS.2001.1019035

Filename

1019035