MRMR-based feature selection for automatic asthma wheezes recognition

Author

Wisniewski, Marcin ; Zielinski, Tomasz P.

Author_Institution

Dept. of Telecommun., AGH The Univ. of Sci. & Technol., Krakow, Poland

fYear

2012

fDate

18-21 Sept. 2012

Firstpage

1

Lastpage

5

Abstract

In this paper application of the mRMR (minimum Redundancy Maximum Relevance) algorithm to reduction of the number of lung sounds features used for asthma wheezes recognition is proposed. The paper presents the reduction of following features: Tonal Index (TI), Kurtosis (K), Energy Ratio (ER), correlation feature (CF1), Difference to Mean ratio (D2M), Eigen Value Decomposition feature (EVD), Linear Prediction feature (LP),Spectral Flatness (SF), Spectral Peaks Entropy (SPE), and two features that has not been presented yet in wheezes detection: Audio Spectral Envelope (ASE) taken from ISO/IEC MPEG-7 standard and Vector Comparison (VC). As a classifier the SVM algorithm was used.

Keywords

acoustic signal processing; bioacoustics; diseases; lung; medical signal processing; patient diagnosis; signal classification; support vector machines; SVM classifier; audio spectral envelope; automatic asthma wheeze recognition; correlation feature; difference-mean ratio; eigenvalue decomposition feature; energy ratio; kurtosis; linear prediction feature; lung sounds feature reduction; mRMR based feature selection; minimum redundancy maximum relevance algorithm; spectral flatness; spectral peak entropy; tonal index; Accuracy; Feature extraction; IEC standards; ISO standards; Lungs; Redundancy; Sensitivity;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals and Electronic Systems (ICSES), 2012 International Conference on

Conference_Location

Wroclaw

Print_ISBN

978-1-4673-1710-8

Electronic_ISBN

978-1-4673-1709-2

Type

conf

DOI

10.1109/ICSES.2012.6382257

Filename

6382257