Neural Networks to Diagnose the Parkinson’s Disease

Abstract

To identify the presence of Parkinson’s disease, a neural network system with back propagation together with a majority voting scheme is presented in this paper. The data used has an imparity of the ratio 3:1. Previous research with regards to predict the presence of the disease has shown accuracy rates up to 92.9% [1] but it comes with a cost of reduced prediction accuracy of the small class. The designed neural network system is boosted by filtering, and this causes a significant increase of robustness. It is also shown that by majority voting of eleven parallel networks, recognition rates reached to > 90 in spite of 3:1 imbalanced class distribution of the Parkinson’s disease data set.