Computational and Mathematical Methods in Medicine

Research Article

An Efficient Diagnosis System for Parkinson’s Disease Using Kernel-Based Extreme Learning Machine with Subtractive Clustering Features Weighting Approach

Table 1

The details of the whole 22 features of the PD dataset.
LabelFeatureDescription
F1MDVP: Fo (Hz)Average vocal fundamental frequency
F2MDVP: Fhi (Hz)Maximum vocal fundamental frequency
F3MDVP: Flo (Hz)Minimum vocal fundamental frequency
F4MDVP: Jitter (%)Several measures of variation in fundamental frequency
F5MDVP: Jitter (Abs) 
F6MDVP: RAP 
F7MDVP: PPQ 
F8Jitter: PPQ 
F9MDVP: ShimmerSeveral measures of variation in amplitude
F10MDVP: Shimmer (dB) 
F11Shimmer: APQ3 
F12Shimmer: APQ5 
F13MDVP: APQ 
F14Shimmer: DDA 
F15NHRTwo measures of ratio of noise to tonal components in the voice
F16HNR 
F17RPDETwo nonlinear dynamical complexity measures
F18D2 
F19DFASignal fractal scaling exponent
F20Spread1Three nonlinear measures of fundamental frequency variation
F21Spread2 
F22PPE