Multiclass classification of Parkinson’s disease using cepstral analysis
- 139 Downloads
This paper addressees the problem of an early diagnosis of PD (Parkinson’s disease) by the classification of characteristic features of person’s voice knowing that 90% of the people with PD suffer from speech disorders. We collected 375 voice samples from healthy and people suffer from PD. We extracted from each voice sample features using the MFCC and PLP Cepstral techniques. All the features are analyzed and selected by feature selection algorithms to classify the subjects in 4 classes according to UPDRS (unified Parkinson’s disease Rating Scale) score. The advantage of our approach is the resulting and the simplicity of the technique used, so it could also extended for other voice pathologies. We used as classifier the discriminant analysis for the results obtained in previous multiclass classification works. We obtained accuracy up to 87.6% for discrimination between PD patients in 3 different stages and healthy control using MFCC along with the LLBFS algorithm.
KeywordsParkinson’s disease Cepstral analysis Classification PCA LLBFS Discriminant analysis
These Datasets were generated through collaboration between Sage Bionetworks, PatientsLikeMe and Dr. Max Little as part of the Patient Voice Analysis study (PVA). They were obtained through Synapse ID [syn2321745].
- “An Automatic Speaker Recognition System”, http://www.ifp.uiuc.edu/~minhdo/teaching/speaker_recognition.
- Alcaraz Meseguer, N. (2009) “Speech Analysis for Automatic Speech Recognition “, Thesis submitted to Norwegian University of Science and Technology Department of Electronics and Telecommunications.Google Scholar
- Baken, R. J., & Orlikoff, R. F. (2000). Clinical measurement of speech and voice (2nd edn.). San Diego: Singular Thomson Learning.Google Scholar
- Duffy, R. J., & Motor (2005). Speech disorders: Substrates, differential diagnosis and management (2nd edn.). St. Louis: Elsevier Mosby.Google Scholar
- Ferchichi, S. E., Zidi, S., Laabidi, K., & Maouche, S. (2009) Feature selection using an SVM learning machines. In Proceedings of the 422 3rd International Conference on Signals, Circuits and Systems (SCS 2009); 1–6.Google Scholar
- Guérif, S. (2006) Réduction de dimension en apprentissage numérique non supervisée. PhD thesis, Université Paris 13. p. 420 148. 421.Google Scholar
- Guo, P. F., Bhattacharya, P., & Kharma, N. (2010) Advances in detecting Parkinson’s disease. Medical Biometrics 306–314.Google Scholar
- Kumar, C. S., & Mallikarjuna, P. R. (2011) Design of an automatic speaker recognition system using MFCC, vector quantization and LBG algorithm. International Journal on Computer Science and Engineering, 3(8), 2942.Google Scholar
- Little, M. A., et al., (2009). Suitability of dysphonia measurements for telemonitoring of Parkinson’ disease, IEEE Transactions on Biomedical Engineering.Google Scholar
- Malode, A. A., Sahare, S. (2012) Advanced speaker recognition. International Journal of Advances in Engineering and Technology, 4, 443–455Google Scholar
- Miller, N., Revista de Logopedia, Foniatría y Audiología (2009) Communication changes in Parkinson’s disease. Amsterdam: Elsevier, Vol. 29, pp. 37–46.Google Scholar
- Spadoto, A. A., et al., (2011) Improving Parkinson’s disease identification through evolutionary-based feature selection, In Engineering in Medicine and Biology Society, EMBC, Annual International Conference of the IEEE.Google Scholar
- Tsanas, A., Little, M. A., McSharry, P. E., & Ramig, L. O. (2012a) Using the cellular mobile telephone network to remotely monitor Parkinson’s disease symptom severity IEEE Transactions on Biomedical Engineering.Google Scholar
- Viallet, F., & Teston, B. (2007). La dysarthrie dans la maladie de Parkinson. Les dysarthries, pp. 169–174.Google Scholar
- Young, S., Evermann, G., Hain, T., Kershaw, D., Liu, X., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V., & Woodland, P. (2006). The HTK book (for HTK version 3.4). Cambridge: Cambridge University Engineering Department.Google Scholar