Answers are grounded in this paper and cite their sources.
Today, Parkinson’s Disease (PD) is one of the most common neurodegenerative diseases in the world after Alzheimer’s disease. About 6.2 million people have it and it is estimated that by 2040 the number of Parkinson’s patients will double it. PD reduces motor function, which is why patients suffer from decreased movement, stiffness, tremors and even the voice and speech production including breathing, articulation, and phonation. For this reason, the voice features of patients vary in comparison to people who do not have PD. Therefore, we are looking for a method that allows us to select the features of the voice that affects the most to the patient's diagnosis. There are several methods for feature selection and in our case, we use genetic algorithms (GA). To validate our feature selection approach, we constructed an SVM classifier where the best accuracy of 88.54% was achieved with 8 features selected by GA.
No takes yet. Share an insight, caveat, or question.
Miranda et al. (2022) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: