Application of Genetic Algorithms for the Selection of Neural Network Architecture in the Monitoring System for Patients with Parkinson’s Disease

Abstract

This article describes an approach for collecting and pre-processing phone owner data, including their voice, in order to classify their condition using data mining methods. The most important research results presented in this article are the developed approaches for the processing of patient voices and the use of genetic algorithms to select the architecture of the neural network in the monitoring system for patients with Parkinson’s disease. The process used to pre-process a person’s voice is described in order to determine the main parameters that can be used in assessing a person’s condition. It is shown that the efficiency of using genetic algorithms for constructing neural networks depends on the composition of the data. As a result, the best result in the accuracy of assessing the patient’s condition can be obtained by a hybrid approach, where a part of the neural network architecture is selected analytically manually, while the other part is built automatically.

Neural Network Applications in Electrical Drives—Trends in Control, Estimation, Diagnostics, and Construction

“…This approach differs from a typical training algorithm based on the gradient of the cost function because it does not need calculations of the derivatives. The most popular methods of this type are genetic algorithms and particle swarm optimization [25][26][27]. As recently shown in [25], such solutions increase the convergence and recognition efficiency of neural networks.…”