OPTIMIZATION OF DUAL-TREE COMPLEX WAVELET PACKET BASED ENTROPY FEATURES FOR VOICE PATHOLOGIES DETECTION
DOI:
https://doi.org/10.11113/jurnalteknologi.v82.14748Keywords:
DT-CWPT, Feature Extraction, Feature Selection, Voice PathologiesAbstract
The Dual-Tree Complex Wavelet Packet Transform (DT-CWPT) has been successfully implemented in numerous field because it introduces limited redundancy, provides approximately shift-invariance and geometrically oriented signal in multiple dimensions where these properties are lacking in traditional wavelet transform. This paper investigates the performance of features extracted using DT-CWPT algorithms which are quantified using k-Nearest Neighbors (k-NN) and Support Vector Machine (SVM) classifiers for detecting voice pathologies. Decomposition is done on the voice signals using Shannon and Approximate entropy (ApEn) to signify the complexity of voice signals in time and frequency domain. Feature selection methods using the ReliefF algorithm and Genetic algorithm (GA) are applied to obtain the optimum features for multiclass classification. It is observed that the best accuracies obtained using DT-CWPT with ApEn entropy are 91.15 % for k-NN and 93.90 % for SVM classifiers. The proposed work provides a promising detection rate for multiple voice disorders and is useful for the development of computer-based diagnostic tools for voice pathology screening in health care facilities.
References
Saldanha, J. C., Ananthakrishna, T., and Pinto, R. 2013. Vocal Fold Pathology Assessment using PCA and LDA. International Conference on Intelligent Systems and Signal Processing, ISSP 2013. 140-144.
DOI: https://doi.org/10.1109/ISSP.2013.6526890
Harar, P., Galaz, Z., Alonso-Hernandez, J. B., Mekyska, J., Burget, R., and Smekal, Z. 2018. Towards Robust Voice Pathology Detection. Neural Computing and Applications. 1-11.
DOI: https://doi.org/10.1007/s00521-018-3464-7
Selvakumari, N. A. S., and Radha, V. 2017, March. Voice Pathology Identification: A Survey on Voice Disorder. I.J. Engineering and Manufacturing. 2. 39-49.
Mekyska, J., Janousova, E., Gomez-Vilda, P., Smekal, Z., Rektorova, I., Eliasova, I., Kostalova, M., Mrackova, M., Alonso-Hernandez, J. B., Faundez-Zanuy, M., and López-de-Ipiña, K. 2015. Robust and Complex Approach of Pathological Speech Signal Analysis. Neurocomputing. 167 94-111.
DOI: https://doi.org/10.1016/j.neucom.2015.02.085
Hariharan, M., Polat, K., and Yaacob, S. 2014. A New Feature Constituting Approach to Detection of Vocal Fold Pathology. International Journal of Systems Science. 45(8).1622-1634.
DOI: https://doi.org/10.1080/00207721.2013.794905
Saidi, P., and Almasganj, F. 2015. Voice Disorder Signal Classification Using M-Band Wavelets and Support Vector Machine. Circuits, Systems, and Signal Processing. 34(8). 2727-2738.
DOI: https://doi.org/10.1007/s00034-014-9927-x
Majidnezhad, V. 2015. A Novel Hybrid of Genetic Algorithm and ANN for Developing A High Efficient Method for Vocal Fold Pathology Diagnosis. EURASIP Journal on Audio, Speech, and Music Processing .1. 1-11.
DOI: https://doi.org/10.1186/s13636-014-0046-1
Akbari, A., and Arjmandi, M. K. 2014. An Efficient Voice Pathology Classification Scheme Based on Applying Multi-Layer Linear Discriminant Analysis to Wavelet Packet-Based Features. Biomedical Signal Processing and Control.10(1). 209-223.
DOI: https://doi.org/10.1016/j.bspc.2013.11.002
Hegde, S., Shetty, S., Rai, S., and Dodderi, T. 2018. A Survey on Machine Learning Approaches for Automatic Detection of Voice Disorders. Journal of Voice.
Roffo, G. 2016. Feature Selection Library (MATLAB Toolbox). Retrieved from http://arxiv.org/abs/1607.01327
Daimi, S. N., and Saha, G. 2014. Classification of Emotions Induced by Music Videos and Correlation with Participants' Rating. Expert Systems with Applications. 41(13). 6057-6065.
DOI: https://doi.org/10.1016/j.eswa.2014.03.050
Wu, D., Zhang, P., Ren, G., Li, B., and Cao, J. 2009. Study on Engine Vibration Signal Denoising Method of SURE Block Threshold Based on DT-CWPT. International Conference on Measuring Technology and Mechatronics Automation, ICMTMA 2009. 1. 719-722.
DOI: https://doi.org/10.1109/ICMTMA.2009.529
Häfner, M., Liedlgruber, M., and Uhl, A. Colonic Polyp Classification in High-Definition Video Using Complex Wavelet-Packets .2015. In Bildverarbeitung für die Medizin 2015. Springer Vieweg, Berlin. 365-370.
DOI: https://doi.org/10.1007/978-3-662-46224-9_63
Qu, J., Zhang, Z., and Gong, T. 2016. A Novel Intelligent Method for Mechanical Fault Diagnosis Based on Dual-Tree Complex Wavelet Packet Transform and Multiple Classifier Fusion. Neurocomputing .171. 837-853.
DOI: https://doi.org/10.1016/j.neucom.2015.07.020
Serbes, G., Gulcur, H. O., and Aydin, N. 2016. Directional Dual-Tree Complex Wavelet Packet Transforms For Processing Quadrature Signals. Medical and Biological Engineering and Computing.54(2-3). 295-313.
DOI: https://doi.org/10.1007/s11517-014-1224-0
Lim, W. J., Muthusamy, H., Vijean, V., Yazid, H., Nadarajaw, T., and Yaacob, S. 2018. Dual-Tree Complex Wavelet Packet Transform and Feature Selection Techniques for Infant Cry Classification. Journal of Telecommunication, Electronic and Computer Engineering (JTEC). 10(1-16). 75-79.
Abdullah, R., Hariharan, M., Vijean, V., Abdullah, Z., and Kassim, F.N.C. 2019. Real and Complex Wavelet Transform Approaches for Malaysian Speaker and Accent Recognition. Pertanika Journal Science and Technology. 27(2). 737-752.
Bayram, I., and Selesnick, I. W. ,2008. On the Dual-Tree Complex Wavelet Packet and M-Band Transforms. IEEE Transactions on Signal Processing.56(6).2298-2310.
DOI: https://doi.org/10.1109/TSP.2007.916129
Sović, A., and Seršić, D. 2012. Signal Decomposition Methods for Reducing Drawbacks of the DWT. Engineering Review. 32(2).70-77.
Al-nasheri, A., Muhammad, G., Alsulaiman, M., Ali, Z., Mesallam, T. A., Farahat, M., Malki, K. H., and Bencherif, M. A. 2017. An Investigation of Multidimensional Voice Program Parameters in Three Different Databases for Voice Pathology Detection and Classification. Journal of Voice. 31(1).
DOI: https://doi.org/10.1016/j.jvoice.2016.03.019
Patil, H. A. 2019. Combining Evidences from Variable Teager Energy Source and Mel Cepstral Features for Classification of Normal Vs. Pathological Voices. European Signal Processing Conference. 2. 1-5.
DOI: https://doi.org/10.23919/EUSIPCO.2019.8903126
Pincus, S. M., Gladstone, I. M., and Ehrenkranz, R. A. 1991. A Regularity Statistic for Medical Data Analysis. Journal of Clinical Monitoring. 7(4).335-345.
DOI: https://doi.org/10.1007/BF01619355
Urbanowicz, R. J., Meeker, M., La Cava, W., Olson, R. S., and Moore, J. H. 2018, July. Relief-Based Feature Selection: Introduction and Review. Journal of Biomedical Informatics.85.189-203.
DOI: https://doi.org/10.1016/j.jbi.2018.07.014
Holland, J. H. Adaptation in Natural and Artificial Systems. 1975. In University of Michigan Press,Ann Arbor.
Firdos, S., and Umarani, K. 2016. Disordered Voice Classification Using SVM and Feature Selection Using GA. Proceedings of the 2nd International Conference on Cognitive Computing and Information Processing (CCIP 2016).1-6.
DOI: https://doi.org/10.1109/CCIP.2016.7802868
Oluleye, B., Leisa, A., Leng, J., and Dean, D. 2014. A Genetic Algorithm-Based Feature Selection. International Journal of Electronics Communication and Computer Engineering .5(4). 899-905.
Fethi, A., and Mohamed, F. 2013. Voice Pathologies Classification Using GMM and SVM Classifiers. Proceedings of the 2013 International Conference on Biology, Medical Physics, Medical Chemistry, Biochemistry and Biomedical Engineering.65-69.
Al Mojaly, M., Muhammad, G., and Alsulaiman, M. 2014. Detection and Classification of Voice Pathology Using Feature Selection. In 2014 IEEE/ACS 11th International Conference on Computer Systems and Applications (AICCSA). 571-577.
DOI: https://doi.org/10.1109/AICCSA.2014.7073250
Hammami, I., Salhi, L., and Labidi, S. 2020. Voice Pathologies Classification and Detection Using EMD-DWT Analysis Based on Higher Order Statistic Features. IRBM.1. 1-11.
DOI: https://doi.org/10.1016/j.irbm.2019.11.004
Srinivasan, V., Ramalingam, V., and Sellam, V. 2012. Classification of Normal and Pathological Voice using GA and SVM. International Journal of Computer Applications.60(3).34-39.
DOI: https://doi.org/10.5120/9675-4102
Chang, C. C., and Lin, C. J. 2011. LIBSVM: A Library for Support Vector Machines. ACM Transactions on Intelligent Systems and Technology. 2(3). 1-39.
DOI: https://doi.org/10.1145/1961189.1961199
Muhammad, G., Alsulaiman, M., Ali, Z., Mesallam, T. A., Farahat, M., Malki, K. H., Al-nasheri, A., and Bencherif, M. A. 2017. Voice Pathology Detection Using Interlaced Derivative Pattern on Glottal Source Excitation. Biomedical Signal Processing and Control .31.156-164.
DOI: https://doi.org/10.1016/j.bspc.2016.08.002.
Cai, J., Luo, J., Wang, S., and Yang, S. 2018. Feature Selection In Machine Learning: A New Perspective. Neurocomputing, 300, 70-79.
DOI: https://doi.org/10.1016/j.neucom.2017.11.077
Gómez-GarcÃa, J. A., Moro-Velázquez, L., and Godino-Llorente, J. I. 2019. On the Design of Automatic Voice Condition Analysis Systems. Part I: Review of Concepts and An Insight to The State of The Art. Biomedical Signal Processing and Control.51.181-199.
Downloads
Published
Issue
Section
License
Copyright of articles that appear in Jurnal Teknologi belongs exclusively to Penerbit Universiti Teknologi Malaysia (Penerbit UTM Press). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions, or any other reproductions of similar nature.