International Journal of Nonlinear Analysis and Applications
Genetic algorithm and principal components analysis in speech-based parkinson's early diagnosis studies
Document Type : Research Paper
Authors
Department of Electronics and Communication Engineering, College of Engineering and Technology, Faculty of Engineering and Technology SRM Institute of Science and Technology SRM Nagar, Kattankulathur 603203. Kanchipuram, Chennai T.N, India
Abstract
Parkinson's Disease (PD) is a neurodegenerative disorder that affects predominantly neurons in the brain. The main purpose of this paper is to define a way in detecting the PD in its early stages. This has been achieved through the use of recorded speech, a biomarker in the natural environment in its original state. In this paper, the Mel-Frequency Cepstral Coefficients (MFCC) method is utilized to extract features from the recorded speech. The principal component analysis (PCA) and Genetic algorithm (GA) are then applied for feature extraction/selection. Once the features are selected, multiple classifiers are then applied for classification. Performance metrics such as accuracy, specificity, and sensitivity are measured. The result shows that Support Vector Machine (SVM) along with the GA has shown optimal performance.
Keywords
a combination of DWT and MFCC feature warping in the presence of noise and reverberation conditions, IEEE
Access 5 (2017) 15400–15413.
[2] S. Arora, V. Venkataraman, A. Zhan, S. Donohue, K.M. Biglan, E.R. Dorsey and M.A. Little, Detecting and
monitoring the symptoms of Parkinson’s disease using smartphones: A pilot study, Parkinsonism & Related
Disorders 21(6) (2015) 650–653.
[3] T. Bocklet, E. N¨oth, G. Stemmer, H. Ruzickova and J. Rusz, Detection of persons with Parkinson’s disease by
acoustic, vocal, and prosodic analysis, Automatic Speech Recognition and Understanding (ASRU), 2011 IEEE
(2011) 478–483.
[4] M. Cernak, J.R. Orozco-Arroyave, F. Rudzicz, H. Christensen, J.C. V´asquez-Correa and E. N¨oth, Characterisation of voice quality of Parkinson’s disease using differential phonological posterior features, Comput. Speech
Lang, 46 (2017) 196–208.
[5] B. Gupta and A. Bala, Parkinson’s disease in India: An analysis of publications output during 2002-2011, Int. J.
Nutrition, Pharmacology, Neurological Diseases 3(3) (2013) 254–262.
[6] K. Gupta and D. Gupta, An analysis on LPC, RASTA, and MFCC techniques in automatic speech recognition
system, 6th Int. Conf. Cloud Syst. Big Data Engin. (2016) 493–497.
[7] L. Jeancolas, H. Benali, B.E. Benkelfat, G. Mangone, J.C. Corvol, M. Vidailhet, S. Lehericy and D.P. Delacr´etaz,
Automatic detection of early stages of Parkinson’s disease through acoustic voice analysis with Mel-frequency
cepstral coefficients, Int. Conf. Adv. Tech. Signal Image Proc. IEEE, (2017) 1–6.
[8] J. Jankovic, Parkinson’s disease: clinical features and diagnosis, J. Neurology 79(4) (2008) 368–376.
[9] R. Kr¨uger, J. Klucken, D. Weiss, L. T¨onges, P. Kolber, S. Unterecker, M. Lorrain, H. Baas, T. M¨uller and P.
Riederer, Classification of advanced stages of Parkinson’s disease: translation into stratified treatments, J. Neural
Transm. 124(8) (2017b) 1015–1027.
[10] D. Mirarchi, P. Vizza, G. Tradigo, N. Lombardo, G. Arabia and P. Veltri, Signal analysis for voice evaluation in
Parkinson’s disease, Healthcare Informatics (ICHI), 2017 IEEE Int. Conf. IEEE (2017) 530–535.
[11] L. Qian, Y. Zhang, L. Zheng, X. Fu, W. Liu, Y. Shang, Y. Zhang, Y. Xu, Y. Liu, H. Zhu and J.H. Gao, Frequency
specific brain networks in Parkinson’s disease and comorbid depression, Brain Imag. Behav. 11(1) (2017) 224–239.
[12] A.B. Soliman, M. Fares, M.M. Elhefnawi and M. Al-Hefnawy, Features selection for building an early diagnosis
machine learning model for Parkinson’s disease, Artificial Intelligence and Pattern Recognition (AIPR), Int. Conf.
IEEE (2016) 1–4.
[13] J.C. V´asquez-Correa, J. Serra, J.R.O. Arroyave, J.V. Bonilla and E. N¨oth, Effect of acoustic conditions on
algorithms to detect Parkinson’s disease from speech, Acoustics, Speech and Signal Processing (ICASSP), 2017
IEEE Int. Conf. IEEE (2017) 5065–5069.
[14] A.K. Verma, J. Raj, V. Sharma, T.B. Singh, S. Srivastava and R. Srivastava, Epidemiology and associated risk
factors of Parkinson’s disease among the north Indian population, Clinical Epidem. Global Health 5(1) (2017)
8–13.
[15] P. Wicks, J. Stamford, M.A. Grootenhuis, L. Haverman and S. Ahmed, Innovations in e-health, Qual. Life Res.
23(1) (2014) 195–203.
[16] J. Wenhai and L. Yongwen, Energy-based feature ranking for assessing the dysphonia measurements in Parkinson
detection, IET Signal Proc. 6(4) (2012) 300–305.
)
Volume 13, Issue 1
March 2022Pages 591-602
- Receive Date: 23 June 2021
- Accept Date: 16 September 2021
- First Publish Date: 23 September 2021