Dysphonic Voice Pattern Analysis of Patients in Parkinson’s Disease Using Minimum Interclass Probability Risk Feature Selection and Bagging Ensemble Learning Methods

<div>Estimated probability density functions of (a) recurrence period density entropy measure (RPDE) and (b) Shimmer-LDA features, plotted with blue and red curves for healthy control (CO) and idiopathic Parkinson’s disease (IPD) subjects, respectively. The overlapping interclass probability risk (ICPR) areas are shown in gray color. Normalized histograms of (c) RPDE and (d) Shimmer-LDA features are also provided with the overlapped areas in gray color, for the purpose of comparison.</div>

Computational and Mathematical Methods in Medicine

fig1

Figure 1

Figure 1: Dysphonic Voice Pattern Analysis of Patients in Parkinson’s Disease Using Minimum Interclass Probability Risk Feature Selection and Bagging Ensemble Learning Methods 

Figure 1 | Dysphonic Voice Pattern Analysis of Patients in Parkinson’s Disease Using Minimum Interclass Probability Risk Feature Selection and Bagging Ensemble Learning Methods 