Lower limb rehabilitation exoskeleton using brain–computer interface based on multiband filtering with classifier fusion

Abstract

In this study, we propose two adaptive frameworks based on evolutionary algorithms for improving the accuracy of motor imagery (MI) task classification. In an MI task, each participant has a different reaction time delay. In this study, the reaction delay was used as a parameter. Specifically, the time point after the reaction delay was defined as the starting point (SP) when MI began. Various classification and optimization algorithms were employed. The methods include the use of a fixed and dynamic SP for each individual, a genetic algorithm, particle swarm optimization (PSO), spatial filter tuning, the use of common spatial patterns, linear discriminant analysis, bagged decision trees, convolutional neural network (CNN), and long short‐term memory (LSTM). Moreover, a dynamic optimization method for multiband filtering (MBF) method for the subbands of EEG signals was developed that improved accuracy by 5.4%. Combining MBF with bagged decision trees with PSO‐optimized parameters achieved the highest accuracy of 82.3%. Moreover, after optimization by PSO, the CNN‐LSTM method achieved a classification accuracy of 81.4% for 1‐s signals, shorter than those in other studies. The method enables the use of EEG signals to control an exoskeleton for patient rehabilitation.