Share Email Print

Proceedings Paper

Automatic detection of wheezes by evaluation of multiple acoustic feature extraction methods and C-weighted SVM
Author(s): Germán D. Sosa; Angel Cruz-Roa; Fabio A. González
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This work addresses the problem of lung sound classification, in particular, the problem of distinguishing between wheeze and normal sounds. Wheezing sound detection is an important step to associate lung sounds with an abnormal state of the respiratory system, usually associated with tuberculosis or another chronic obstructive pulmonary diseases (COPD). The paper presents an approach for automatic lung sound classification, which uses different state-of-the-art sound features in combination with a C-weighted support vector machine (SVM) classifier that works better for unbalanced data. Feature extraction methods used here are commonly applied in speech recognition and related problems thanks to the fact that they capture the most informative spectral content from the original signals. The evaluated methods were: Fourier transform (FT), wavelet decomposition using Wavelet Packet Transform bank of filters (WPT) and Mel Frequency Cepstral Coefficients (MFCC). For comparison, we evaluated and contrasted the proposed approach against previous works using different combination of features and/or classifiers. The different methods were evaluated on a set of lung sounds including normal and wheezing sounds. A leave-two-out per-case cross-validation approach was used, which, in each fold, chooses as validation set a couple of cases, one including normal sounds and the other including wheezing sounds. Experimental results were reported in terms of traditional classification performance measures: sensitivity, specificity and balanced accuracy. Our best results using the suggested approach, C-weighted SVM and MFCC, achieve a 82.1% of balanced accuracy obtaining the best result for this problem until now. These results suggest that supervised classifiers based on kernel methods are able to learn better models for this challenging classification problem even using the same feature extraction methods.

Paper Details

Date Published: 28 January 2015
PDF: 6 pages
Proc. SPIE 9287, 10th International Symposium on Medical Information Processing and Analysis, 928709 (28 January 2015); doi: 10.1117/12.2073614
Show Author Affiliations
Germán D. Sosa, Univ. Nacional de Colombia (Colombia)
Angel Cruz-Roa, Univ. Nacional de Colombia (Colombia)
Fabio A. González, Univ. Nacional de Colombia (Colombia)

Published in SPIE Proceedings Vol. 9287:
10th International Symposium on Medical Information Processing and Analysis
Eduardo Romero; Natasha Lepore, Editor(s)

© SPIE. Terms of Use
Back to Top