An orthogonal least square approach to select features of infant cry with asphyxia

An investigation into the feature extraction and selection of infant cry with asphyxia is presented in this paper. The feature of the cry signal was extracted using mel frequency cepstrum coefficient (MFCC) analysis and the significant coefficients were selected using orthogonal least square (OLS) algorithm. The effect of varying the number of MFCC filter banks on the feature selection was examined. It was found that the best set of coefficients could be achieved when 40 filter banks were used.

[1]  K. Michelsson,et al.  Phonation in the newborn, infant cry. , 1999, International journal of pediatric otorhinolaryngology.

[2]  Thomas S. Huang,et al.  Feature analysis and selection for acoustic event detection , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[3]  Örjan Ekeberg,et al.  Precision grip force dynamics: a system identification approach , 2000, IEEE Transactions on Biomedical Engineering.

[4]  M. I. Yusof,et al.  Nonlinear system identification for a Dc motor using NARMAX approach , 2003, Asian Conference on Sensors, 2003. AsiaSense 2003..

[5]  Xiangjian He,et al.  Classification Techniques in Pattern Recognition , 2005 .

[6]  John H. L. Hansen,et al.  Discrete-Time Processing of Speech Signals , 1993 .

[7]  Hishamuddin Jamaluddin,et al.  ORTHOGONAL LEAST SQUARE ALGORITHM AND ITS APPLICATION FOR MODELLING SUSPENSION SYSTEM , 2001 .

[8]  Orion F. Reyes-Galaviz,et al.  A System for the Processing of Infant Cry to Recognize Pathologies in Recently Born Babies with Neural Networks , 2004 .

[9]  G. Várallyay.  The melody of crying. , 2007, International journal of pediatric otorhinolaryngology.

[10]  Saifur Rahman,et al.  SPEAKER IDENTIFICATION USING MEL FREQUENCY CEPSTRAL COEFFICIENTS , 2004 .

[11]  Rohilah Sahak,et al.  Classification of Infant Cries with Asphyxia Using Multilayer Perceptron Neural Network , 2010, 2010 Second International Conference on Computer Engineering and Applications.