An Efficient Approach for Recognition of Motor Imagery EEG Signals Using the Fourier Decomposition Method

Abstract

This research paper presents an approach for recognizing motor imagery (MI) movements through brain signals, which has essential applications in assisting people with mobility disorders. One of the critical challenges in this field is that such individuals should be exposed to their surroundings with the help of exact motion recognition. This article represents an algorithm where Fourier-based filters are used for obtaining sub-bands of EEG signals for motion recognition and brain computer interface (BCI) application. Specifically, we segment motor imagery signals into eight orthogonal Fourier intrinsic band functions (FIBFs) and extract statistical feature matrices from each FIBF. We then propose a methodology derived from the k-nearest neighbor (kNN) classifier which is also compared with state-of-the-art classifiers like decision tree (DT), support vector machine (SVM), and naive Bayes (NB), to classify the extracted features and to establish its outperforming nature. Our experimental results show that our proposed approach achieves the highest classification accuracy of 96% and 84.03% with the kNN classifier on the BCI III IVa and BCI IV 2a datasets, outperforming state-of-the-art methods. These results demonstrate the potential of our approach in enabling accurate motion recognition and assisting people with mobility disorders.

Keywords

• Electroencephalography
• motor imagery
• brain–computer interface
• k-nearest neighbour
• naïve Bayes
• decision tree