Wavelets: An efficient tool for lung sounds analysis
Authors:
- 1 March 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 875-878
Abstract
The objective of this paper is to use adaptive wavelets for lung sounds analysis and show that wavelets with one vanishing moment can successfully detect pathological changes of the lung which produce sounds with measurable regularities. Local regularity measures allow us to detect some significant components of adventitious sounds which are difficult to detect by the physician ears due to their short duration. This paper will concentrate on a development of lung sounds pattern recognition features. The key properties of pattern recognition features, Lipschitz regularity at any point of wavelet transform modulus maxima along the maxima lines converging to this point, regularity of some adventitious lung sounds such as Crackles and Wheezes will be analyzed. Numerical results prove that normal lung sound is more regular than crackles lung sounds.Keywords
This publication has 4 references indexed in Scilit:
- Electronic auscultation based on wavelet transformation in clinical use2002
- Wavelet methods for pointwise regularity and local oscillations of functionsMemoirs of the American Mathematical Society, 1996
- Singularity detection and processing with waveletsIEEE Transactions on Information Theory, 1992
- Ten Lectures on Wavelets1992