Analysis of PSO, AIS and GA-based optimal Wavelet-Neural Network classifier in Brain–Robot Interface

Abstract

ObjectivesThis paper studies the effectiveness of three classifiers (Particle Swarm Optimization (PSO) based optimal Wavelet Neural Network (WNN), Artificial Immune System (AIS) based optimal WNN and Genetic Algorithm (GA) based optimal Neural Network) in Brain–Robot Interface system. Material and methodsC3 & C4 are selected as inputs. Wavelet coefficients, auto-regressive and the power of wavelet coefficients are employed as features. WNN is used as classifier and its performance in terms of accuracy is improved through meta-heuristic optimization techniques (PSO, AIS and GA). They are used to optimize neural network weights and wavelet parameters. ResultsAccuracy of three classification algorithms: a) PSO-based optimal WNN, b) AIS-based optimal WNN and c) GA-based optimal ANN is calculated. Results show that the mean accuracy/standard deviation of a), b) and c) are 76%/4.9, 65%/2.6 and 64%/2.2, respectively. In addition, results of the best classifier (PSO-based optimal WNN), are compared with Support Vector Machine (the mean accuracy of SVM is 60%). ConclusionPSO-based optimal WNN results in the best classification accuracy. Outputs of this classifier are implemented on a mobile robot named K-junior and a fixed robot named Tabriz-Puma. The experimental results show the applicability and effectiveness of these methods.