Discriminating Between Patients With Parkinson's and Neurological Diseases Using Cepstral Analysis

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 24; no. 10; pp. 1100 - 1108
• Main Authors: Benba, Achraf, Jilbab, Abdelilah, Hammouch, Ahmed
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adult; Cepstral analysis; Diagnosis, Computer-Assisted - methods; Diagnosis, Differential; Discriminant Analysis; Diseases; Feature extraction; Female; Fourier Analysis; Humans; Male; Mel frequency cepstral coefficient; Mel frequency cepstral coefficients (MFCC); Middle Aged; Nervous System Diseases - complications; Nervous System Diseases - diagnosis; neurological disorders; Parkinson Disease - complications; Parkinson Disease - diagnosis; Parkinson's disease; perceptual linear prediction (PLP); ReAlitive SpecTrAl PLP (RASTA-PLP); Reproducibility of Results; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Sound Spectrography - methods; Speech; Speech Disorders - diagnostic imaging; Speech Disorders - etiology; supervised learning; Support vector machines
• ISSN: 1534-4320; 1558-0210
• DOI: 10.1109/TNSRE.2016.2533582

In this paper, we wanted to discriminate between two groups of patients (patients who suffer from Parkinson's disease and patients who suffer from other neurological disorders). We collected a variety of voice samples from 50 subjects using different recording devices in different conditions. Subsequently, we analyzed and extracted features from these samples using three different Cepstral techniques; Mel frequency cepstral coefficients (MFCC), perceptual linear prediction (PLP), and ReAlitive SpecTrAl PLP (RASTA-PLP). For classification we used leave one subject out validation scheme along with five different supervised learning classifiers. The best obtained result was 90% using the first 11 coefficients of the PLP and linear SVM kernels.