Human tremor analysis using particle swarm optimization

Abstract

The paper presents methods for the analysis of human tremor using particle swarm optimization. Two forms of human tremor are addressed: essential tremor and Parkinson's disease. Particle swarm optimization is used to evolve a neural network that distinguishes between normal subjects and those with tremor. Inputs to the neural network are normalized movement amplitudes obtained from an actigraph system. The results from this preliminary investigation are quite promising, and work is continuing.