DETECTION OF PARKINSON’S DISEASE DETECTION THROUGH MACHINE LEARNING

A motor complication of Parkinson’s disease (PD), which is a neurodegenerative illness, includes speech difficulties. Since the management and treatment of this disease entails clinical and pharmacological intervention, early and precise identification of PD plays a critical role in medical knowledge. In this piece, the characteristics of the speech signal and potential machinery learning methods to diagnose Parkinson’s illness are discussed. In line with standard protocols, voice signals were elicited from the participants, which comprised PD and a mere control group. From these signals, many characteristics from the spectral, temporal, and cepstral were extracted. To locate the characteristics that can provide the most informative features for the classification, feature selection methods were applied. A support vector machine (SVM) was next used to classify PD in the healthy control participants using the selected features.