Segmentation of respiratory signals by evidence theory

Author

Belghith, Akram ; Collet, Christophe

Author_Institution

LSIIT, Strasbourg Univ., Strasbourg, France

fYear

2009

fDate

3-6 Sept. 2009

Firstpage

1905

Lastpage

1908

Abstract

This paper presents an evidential segmentation scheme of respiratory signals for the detection of the wheezing sounds. The segmentation is based on the modeling of the data by evidence theory which is well suited to represent such uncertain and imprecise data. In this paper, we particularly focus on the modelization of the data imprecision using the fuzzy theory. The modelization result is then used to define the mass function. The effectiveness of the method is demonstrated on synthetic and real signals.

Keywords

acoustic signal detection; acoustic signal processing; bioacoustics; fuzzy set theory; medical signal detection; medical signal processing; pneumodynamics; evidence theory; fuzzy theory; mass function definition; respiratory signal segmentation; wheezing sound detection; Data fusion; evidence theory; fuzzy membership function; imprecision; segmentation; Analysis of Variance; Auscultation; Computer Simulation; Equipment Design; Humans; Models, Theoretical; Probability; Respiratory Sounds; Sensitivity and Specificity; Signal Transduction; Stethoscopes;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE

Conference_Location

Minneapolis, MN

ISSN

1557-170X

Print_ISBN

978-1-4244-3296-7

Electronic_ISBN

1557-170X

Type

conf

DOI

10.1109/IEMBS.2009.5333026

Filename

5333026