Support Vector Machine Performance with Optimal Parameters Identification in Recognising Asphyxiated Infant Cry

  • Authors

    • R Sahak
    • W Mansor
    • Khuan Y. Lee
    • A Zabidi
    2018-08-13
    https://doi.org/10.14419/ijet.v7i3.15.17513
  • Asphyxia, Infant cry, orthogonal least square, principal component analysis, support vector machine.

  • Abstract

    Detection of asphyxia in infant at an early stage is crucial to reduce the rate of infant morbidity. The information regarding asphyxia can be extracted from infant cry signals using support vector machine (SVM) combined with effective feature selection methods such as principal component analysis (PCA) or orthogonal least square (OLS). The performance of SVM in recognizing infant cry with asphyxia after undergone comprehensive identification of optimal parameters at the feature extraction and classification stages has not been     reported. This paper describes the two stages of optimal parameter identification; at Mel-frequency Cepstral coefficient (MFCC) analysis stage, SVM with and without employing the PCA and OLS stages, and the performance of the SVM in recognizing infant cry with asphyxia resulted from all levels of optimal parameters identification. The SVM was first optimized after performing MFCC analysis to find the optimum parameters. Two types of kernels were used, the polynomial and RBF kernels. The subsequent SVM optimizations were conducted after PCA and OLS were employed. In the PCA, the significant features were selected using eigenvalue-one-criterion (EOC), cumulative percentage variance (CPV) and the Scree test (SCREE). The SVM performance was evaluated based on classification accuracy and computation time. The experimental results have shown that the optimized SVM was able to recognize the asphyxiated infant cry with an accuracy of 94.84% and computation time of 1.98s using PCA with EOC and RBF kernel.

     

     

  • References

    1. [1] M. Laberge, Infancy through Adolescence Gale, Farmington Hills, MI: Gale Group, Thomson Gale, 2006.

      [2] D. Lederman, Automatic Classification of Infants’ Cry, M.Sc. Thesis, Ben-Gurion University of the Negev, Oct 2002.

      [3] .J. Orozco and C. A. Reyes-Garcia.Detecting Pathologies from Infant Cry Applying Scaled Conjugate Gradient Neural Networks, Proceedings of the 2003 European Symposium of Artificial Neural Networks (ESANN 2003). Bruges, Belgium. 2003; 349-354.

      [4] R. Sahak, Y. K. Lee, W. Mansor, A. I. M. Yassin and A. Zabidi.Optimized Support Vector Machine for Classifying Infant Cries with Asphyxia using Orthogonal Least Squar. International Conference on Computer Applications & Industrial Electronics (ICCAIE), 2010; 692-696.

      [5] O. F. Reyes-Galaviz and C. A. Reyes-Garcia. A System for the Processing of Infant Cry to Recognize Pathologies in Recently Born Babies with Neural Networks. 9th Conference Speech and Computer (SPECOM) Saint-Petersburg, Russia. 2004;1-6.

      [6] A. Zabidi, Y. K. Lee; W. Mansor, F. Yasmin and R. Sahak. Classification of Infant Cry with Asphyxia Using Multilayer Perceptron NeuralNetwork.2nd International Conference on Computer Engineering and Applications 2010 (ICCEA 2010). Bali Island, Indonesia, 2010: 204-208.

      [7] E. A. Camargo and C. A. Reyes-Garcia. Applying Statistical Vectors of Acoustic Characteristics for the Automatic Classification of Infant Cry. Advanced Intelligent Computing Theories and Applications with Aspects of Theoretical and Methodological Issues, Vol. 4681, Lecture Notes in Computer Science. Heidelberg. 2007: 1078-1085.

      [8] O. F. Reyes-Galaviz and C. A. Reyes-Garcia. Fuzzy Relational Compression Applied on Feature Vectors for Infant Cry Recognition. MICAI 2009:Advances in Artificial Intelligence, Vol. 5845, Lecture Notes in Computer Science,A.Aguirre, R. Borja and C. Garcia,Ed., Springer Berlin/ Heidelberg, 2009. 420-431.

      [9] S. E. Barajas-Montiel and C. A. Reyes-Garcia. Identifying Pain and Hunger in Infant Cry with Classifiers Ensembles.International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'05). 2005. 770-775.

      [10] S. Barajas-Montiel, C. A. Reyes-Garcia, E. Arch-Tirado and M. Mandujano. Improving Baby Caring with Automatic Infant Cry Recognition.Computers Helping People with Special Needs. Vol. 4061, Lecture Notes in Computer Science, J. Klaus, W. Zagler and A. Karshmer, Ed., Springer Berlin/Heidelberg, 2006. 691-698.

      [11] R. Sahak, W. Mansor, Y. K. Lee, A. I. M. Yassin and A. Zabidi. An Orthogonal Least Square Approach to Select Features of Infant Cry with Asphyxia.6th International Colloquium on Signal Processing and Its Applications (CSPA). 2010. 1-4.

      [12] R. Sahak, W. Mansor, Y. K. Lee, A. I. M. Yassin and A. Zabidi. Orthogonal Least Square Based Support Vector Machine for the Classification of Infant Cry with Asphyxia. 3rd International Conference on Biomedical Engineering and Informatics (BMEI). 2010. 986-990.

      [13] Y. Ming-Jing, Z. Hui-Ru, W. Hai-Ying, S. Mcclean, N. Harris. Combining feature ranking with PCA: An application to gait analysis. 2010 International Conference on Machine Learning and Cybernetics (ICMLC). 2010 (1): 494-499.

      [14] V. V. Chamundeeswari, D. Singh, K. Singh. An Analysis of Texture Measures in PCA-Based Unsupervised Classification of SAR Images.IEEE Geoscience and Remote Sensing Letters. 2009. 6(2): 214-218.

      [15] S. Zhou, L.Wu, X. Yuan, W. Tan. Parameters Selection of SVM for Function Approximation Based on Differential Evolution. International Conference on Intelligent Systems and Knowledge Engineering (ISKE). 2007. 7.

      [16] V. Vapnik. An Overview of Statistical Learning Theory. IEEE Transactions on Neural Networks. 1999; 5: 988-99.

      [17] W. C. Chan, K.C.Cheung and C.J.Harris. On the Modelling on Nonlinear Dynamic System Using Support Vector Neural Networks. Engineering Applications of Artificial Intelligence,2001; 14. 105-113.

      [18] G. Q. Zhu, S. R. Liu and J. S. Yu. Support Vector Machine and Its Applications to Function Approximation. Journal of East China University of Science and Technology.2002; 5: 555-559.

      [19] O. F. Reyes-Garcia [Online database], July 30, 2009. Available: “http://ingenieria.uatx.mx/~orionfrg/cry/,â€

      [20] Md. R. Hasan, M. Jamil, Md. G. Rabbani Md. S. Rahman. Speaker Identification using Mel Frequency Cepstral Coefficients. 3rd International Conference on Electrical & Computer Engineering ICECE 2004; 4.

      [21] Jr., J. D., Hansen, J., and Proakis, J. Discrete-Time Processing of Speech Signals.Second ed. IEEE Press, New York, 2000.

      [22] F. Soong, E. Rosenberg, B. Juang, and L. Rabiner. A Vector Quantization Approach to Speaker Recognition.AT&T Technical Journal. 1987; 66: 14-26.

      [23] Ch. Latry, C. Panem, P. Dejean. Cloud detection with SVM technique.IEEE International Geoscience and Remote Sensing Symposium. 2007; 448-451.

      [24] C. Lei, L. Jie, S. Yaoru, Z. Huaping, Y. Chungang, "EEG-based vigilance analysis by using Fisher score and PCA algorithm," IEEE International Conference onProgress in Informatics and Computing (PIC 2010), vol.1, 10-12 Dec. 2010, pp.175-179.

      [25] C. Cun-Gui ,C. Lu-Yao, X. Run-sheng, "Classification of FTIR Gastric Cancer Data Using Wavelets and SVM," Third International Conference on Natural Computation, 2007 (ICNC 2007), vol.1, 24-27 Aug. 2007, pp.543-547.

      [26] A. Ali, K. Minkoo, "Amalgamation of SVM Based Classifiers for Prognosis of Breast Cancer Survivability," 2010 Fourth International Conference on Genetic and Evolutionary Computing (ICGEC),13-15 Dec. 2010, pp.173-176.

      [27] T. S. Furey, “Support Vector Machine Classification and Validation of Cancer Tissue Samples Using Microarray Expression Dataâ€, J. Bioinformatics, vol. 16(10), pp. 906-914, 2000.

      [28] M. Sewak, P. Vaidya, C. Chien-Chung, D. Zhong-Hui, "SVM Approach to Breast Cancer Classification," Second International Multi-Symposiums on Computer and Computational Sciences, 2007 (IMSCCS 2007), 13-15 Aug. 2007, pp.32-37.

      [29] M. Moradi, P. Mousavi, A. H. Boag, E. E. Sauerbrei, D. R. Siemens, P. Abolmaesumi, "Augmenting Detection of Prostate Cancer in Transrectal Ultrasound Images Using SVM and RF Time Series," IEEE Transactions on Biomedical Engineering, vol.56, no.9, Sept. 2009, pp.2214-2224.

      [30] W. Jie, H. Qingyong, Y. Kui-wu, W.Rong, X. Yanwei, Y. Zhang, "Support Vector Machine (SVM) and Traditional Chinese Medicine: Syndrome Factors Based an SVM from Coronary Heart Disease Treated by Prominent Traditional Chinese Medicine Doctors," Fifth International Conference on Natural Computation, 2009 (ICNC '09), vol.2, 14-16 Aug 2009, pp.176-180.

      [31] S. Hongzong, W. Tao, Y. Xiaojun, L. Huanxiang, H. Zhide, L. Mancang and F. BoTao, "Support Vector Machines Classification for Discriminating Coronary Heart Disease Patients From Non-coronary Heart Disease," Journal of West Indian Medicine, vol. 56, pp. 451-457, October 2007.

      [32] L. Hongyan, C.Jianrong, "Detection and Segmentation of Moving Objects Based on Support Vector Machine," Third International Symposium on Information Processing (ISIP 2010), 15-17 Oct. 2010, pp.193-197.

      [33] W. Xianxing Wu, Z. Jieyu Zhao, "Curvelet feature extraction for face recognition and facial expression recognition," Sixth International Conference on Natural Computation (ICNC 2010), vol.3, 10-12 Aug 2010, pp.1212-1216.

      [34] J. Kan, W. Li, and K. Gao, “Use of Support Vector Machines in Recognition of Fork Branches of the Standing Treesâ€, 2nd IEEE Conference on Industrial Electronics and Applications, 2007, pp. 783-786.

      [35] O. Ivanciuc, “Chapter 6: Applications of Support Vector Machines in Chemistryâ€, Computational Chemistry, vol 23, Wiley-VCH, John Wiley&Sons, Inc, 2007.

      [36] S. Z. Boujelbene, D. Ben AyedMezghani, N. Ellouze, "Application of combining classifiers for text-independent speaker identification," 16th IEEE International Conference on Electronics, Circuits, and Systems, 2009 (ICECS 2009), 13-16 Dec 2009, pp.723-726.

      [37] S. Z. Boujelbene, D. Ben AyedMezghani, N. Ellouze, "Support vector machines approaches and its application to speaker identification," 3rd IEEE International Conference on Digital Ecosystems and Technologies, 2009 (DEST '09), 1-3 June 2009, pp.662-667.

      [38] N. Rabbani, M. H. Sedaaghi, "Novel approach in speaker identification using support vector machines," 9th International Symposium onSignal Processing and Its Applications, 2007(ISSPA 2007),12-15 Feb. 2007, pp.1-4.

      [39] S. Zhou, L.Wu, X. Yuan, W. Tan, “Parameters Selection of SVM for Function Approximation Based on Differential Evolutionâ€, International Conference on Intelligent Systems and Knowledge Engineering (ISKE), 2007, p. 7.

      [40] W. J. Wang, Z. B. Xu, W. Z. Lu, “Determination of the Spread Parameter in the Gaussian Kernel for Classification and Regressionâ€, Neurocomputing, vol. 55, 643-663, 2003.

      [41] Principal Component Analysis, unpublished note, available: “http:www.support.sas.com/publishing/pubcat/chap5/55129.pdfâ€

      [42] M. Suzuki, H. Miyashita, A. Kamo, T. Watanabe, H. Asai, "A synthesis technique of time-domain interconnect models by MIMO type of selective orthogonal least-square method," IEEE Transactions on Microwave Theory and Techniques, vol.49, no.10, Oct 2001, pp.1708-1714.

      [43] S. Chen, C. F. N. Cowan, P. M. Grant, "Orthogonal least squares learning algorithm for radial basis function networks," IEEE Transactions on Neural Networks, vol.2, no.2, Mar 1991, pp.302-309.

      [44] A. Fagergren, O. Ekeberg, and, H. Forssberg, “Precision Grip Force Dynamics: A System Identification Approach,†IEEE Transactions on Biomedical Engineering, vol. 47, no. 10, October 2000, pp. 1366-1375.

      [45] N. A. Rahim, et al., “Nonlinear system identification for a DC motor using NARMAX Approach,â€Asian Conference on Sensors (AsiaSense), 2003, pp. 305-311.

  • Downloads

  • How to Cite

    Sahak, R., Mansor, W., Y. Lee, K., & Zabidi, A. (2018). Support Vector Machine Performance with Optimal Parameters Identification in Recognising Asphyxiated Infant Cry. International Journal of Engineering & Technology, 7(3.15), 114-119. https://doi.org/10.14419/ijet.v7i3.15.17513

    Received date: 2018-08-14

    Accepted date: 2018-08-14

    Published date: 2018-08-13