Title :
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
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;
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
DOI :
10.1109/ICSES.2012.6382257
