DocumentCode :
3782066
Title :
Respiratory disease diagnosis using lung sounds
Author :
Y.P. Kahya;E.C. Guler;S. Sahin
Author_Institution :
Dept. of Electr. Eng., Bogazici Univ., Istanbul, Turkey
Volume :
5
fYear :
1997
Firstpage :
2051
Abstract :
Lung sounds recorded from pathological and healthy subjects were classified as belonging to restrictive and obstructive respiratory diseases and healthy subjects. Feature parameters were obtained from autoregressive (AR) models applied to overlapping segments of respiratory sounds. Crackle parameters obtained from Prony model were further incorporated into the feature space for classification improvement. Two different multi-stage classifiers composed of k-nearest neighbor (k-NN) and voting and k-NN and multinominal classification were designed and their performances were compared.
Keywords :
"Diseases","Lungs","Pathology","Acoustical engineering","Voting","Explosives","Electronic mail","Mouth","Acoustic noise","Frequency"
Publisher :
ieee
Conference_Titel :
Engineering in Medicine and Biology Society, 1997. Proceedings of the 19th Annual International Conference of the IEEE
ISSN :
1094-687X
Print_ISBN :
0-7803-4262-3
Type :
conf
DOI :
10.1109/IEMBS.1997.758751
Filename :
758751
Link To Document :
بازگشت