Handwritten dynamics classification of Parkinson's disease through support vector machine and principal component analysis

Abstract

Parkinson's disease is a chronic neurodegenerative disease that affects the daily lives of tens of thousands of middle-aged and elderly people. The intelligent classification method of Parkinson's disease has received extensive attention in recent years. The paper proposes a new auxiliary classification model of Parkinson's disease based on principal component analysis and support vector machine. The model first samples and preprocesses the collected handwritten sensor data, then performs dimensionality reduction by principal component analysis, and finally inputs the dimensionality reduction data into a linear kernel support vector machine for Parkinson's disease classification and prediction. The experiment uses 5-fold cross-validation for dataset segmentation and performance verification. The average performance results obtained on the Meander r dataset are: accuracy is 70.86%, specificity is 67.23%, sensitivity is 75.98%, and F1-Score is 69.72%, and the average performance results obtained on the Spiral dataset are: accuracy is 77.45%, specificity is 70.26%, sensitivity is 85.58%, and F1-Score is 77.10%.