Principal component analysis and interpretation of bowel sounds

Author

Ranta, R. ; Louis-Dorr, V. ; Heinrich, C. ; Wolf, D. ; Guillemin, F.

Author_Institution

CRAN, Nancy, France

Volume

1

fYear

2004

fDate

1-5 Sept. 2004

Firstpage

227

Lastpage

230

Abstract

This work presents a method for abdominal sounds analysis based on principal component analysis (PCA). The first steps (wavelet denoising and segmentation, followed by spatial localization) were presented in previous works. After extracting physical features (activity indices) from long time six channel recordings, we propose a reduced representation space obtained by PCA and we present our results in phonoenterogram analysis.

Keywords

bioacoustics; feature extraction; medical signal processing; principal component analysis; wavelet transforms; abdominal sounds analysis; activity indices; bowel sounds; feature extraction; phonoenterogram analysis; principal component analysis; spatial localization; wavelet denoising; wavelet segmentation; Abdomen; Data mining; Frequency; Gastrointestinal tract; Information analysis; Medical diagnostic imaging; Pathology; Principal component analysis; Signal analysis; Signal processing; bowel sounds; principal component analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2004. IEMBS '04. 26th Annual International Conference of the IEEE

Conference_Location

San Francisco, CA

Print_ISBN

0-7803-8439-3

Type

conf

DOI

10.1109/IEMBS.2004.1403133

Filename

1403133