Voice Analysis for Detecting Parkinson’s Disease Using Genetic Algorithm and KNN Classification Method

Abstract—Parkinson’s disease is a disorder of centralnervous system. It is estimated that 90 percent of people withparkinson’s disease suffer from speech and voice disorders.Vocal folds are usually undermined by this disease whichwould lead to creation of an improper voice in the patient’sspeech. In this paper, various features have been extractedfrom the voice signals of healthy people and people sufferingfrom parkinson’s disease. Afterwards, optimized features thatinfluenced the process of data classification were detected usinggenetic algorithm and ultimately, based on various numbers ofoptimized features, the data classification was done using KNNclassification method. It was shown that a classificationaccuracy percent of 93.7 per 4 optimized features, an accuracypercent of 94.8 per 7 optimized features and an accuracypercent of 98.2 per 9 optimized features could be achievedwhich is a notable result compared to other studies.