Optimization of Principal Component Analysis and Support Vector Machine for the Recognition of Infant Cry with Asphyxia

Abstract The optimization of principal component analysis–support vector machine (PCA–SVM) for recognizing infant cry with asphyxia is presented in this paper. Three types of PC A selection techniques such as cumulative percent of variance, eigenvalue-one-criterion and scree test were employed to select significant features of Mel-frequency cepstrum coefficient that is extracted from normal and asphyxia cry. The asphyxiated infant cries were differentiated from normal cries using SVM with linear and radial basis function (RBF) kernels. The performance of the PCA–SVM in recognizing asphyxiated infant cries was compared with the SVM (without PCA) to prove its efficiency. Classification accuracy and support vector number were computed to examine the performance of both techniques. The results show that PCA–SVM is the best technique for recognizing asphyxiated infant cries since it produces the highest classification accuracy (95.323%). The RBF kernel with optimal regularization of 100 and γ=0.025 should be used in the PCA–SVM technique.

[1]  A. Ismaelli,et al.  A new device for computerized infant cry analysis in the NICU , 1994, Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[2]  Yuan Xiaofang,et al.  Parameters selection of SVM for function approximation based on Differential Evolution , 2007 .

[3]  D. Shinar.  BEN-GURION UNIVERSITY OF THE NEGEV , 2012 .

[4]  Chris J. Harris,et al.  On the modelling of nonlinear dynamic systems using support vector neural networks , 2001 .

[5]  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 .

[6]  Jehan Zeb Shah,et al.  Neural networks and support vector machines based bio-activity classification , 2006 .

[7]  Wenjian Wang,et al.  Determination of the spread parameter in the Gaussian kernel for classification and regression , 2003, Neurocomputing.

[8]  Haizhou Li,et al.  Complexity analysis of normal and deaf infant cry acoustic waves , 2005, MAVEBA.

[9]  Alfred S. Malowany,et al.  Classification of infant cry vocalizations using artificial neural networks (ANNs) , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[10]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[11]  Jiangming Kan,et al.  Use of Support Vector Machines in recognition of fork branches of the standing trees , 2007, 2007 2nd IEEE Conference on Industrial Electronics and Applications.

[12]  Nello Cristianini,et al.  Support vector machine classification and validation of cancer tissue samples using microarray expression data , 2000, Bioinform..

[13]  Dimitri P. Bertsekas,et al.  Dynamic Programming and Optimal Control, Two Volume Set , 1995 .

[14]  Herbert Gish,et al.  Speaker identification via support vector classifiers , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[15]  K. Michelsson,et al.  Effect of Training on Ability to Identify Preverbal Vocalizations , 1964, Developmental medicine and child neurology.

[16]  Rohilah Sahak,et al.  An investigation into infant cry and Apgar score using principle component analysis , 2009, 2009 5th International Colloquium on Signal Processing & Its Applications.

[17]  L. Huanxiang,et al.  Support vector machines classification for discriminating coronary heart disease patients from non-coronary heart disease. , 2007, The West Indian medical journal.

[18]  Zhu Guo.  Support Vector Machine and Its Applications to Function Approximation , 2002 .

[19]  Ming-Hsuan Yang,et al.  Gender classification using support vector machines , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[20]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[21]  K. Michelsson,et al.  The identification of some specific meanings in infant vocalization , 1964, Experientia.

[22]  Ovidiu Ivanciuc,et al.  Applications of Support Vector Machines in Chemistry , 2007 .

[23]  Carlos A. Reyes García,et al.  Identifying Pain and Hunger in Infant Cry with Classifiers Ensembles , 2005, International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'06).

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

[25]  G. Várallyay,et al.  FUTURE PROSPECTS OF THE APPLICATION OF THE INFANT CRY IN THE MEDICINE , 2006 .

[26]  Carlos A. Reyes García,et al.  Detecting Pathologies from Infant Cry Applying Scaled Conjugated Gradient Neural Networks , 2003, ESANN.

[27]  Xiao Sun,et al.  Support vector machine for classification of meiotic recombination hotspots and coldspots in Saccharomyces cerevisiae based on codon composition , 2005, BMC Bioinformatics.

[28]  Biing-Hwang Juang,et al.  A vector quantization approach to speaker recognition , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

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

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

[31]  S KARELITZ,et al.  The cry latencies of normal infants and those with brain damage. , 1963, The Journal of pediatrics.