Motor Imagery Classification Using Feature Fusion of Spatially Weighted Electroencephalography

TL;DR

This work tackles motor imagery EEG classification by combining brain-region-based channel grouping with multi-domain feature fusion. It applies CSP, Fuzzy C-Means, and Tangent Space Mapping to region-specific channel groups, concatenating the results into a high-dimensional feature vector of $248$ features per trial, then selects discriminative features with Random Forest and classifies using SVM, MLP, RF, or XGBoost. Validations on public benchmarks (BCI III IVA and BC I IV I) show mean accuracies of $90.77\%$ and $84.50\%$, respectively, with SVM often delivering the best per-subject performance. The approach reduces channel dependency and computational load while improving robustness and interpretability, offering a practical path toward real-time MI-BCI applications; future work includes multiclass MI scenarios and integration with deep learning models.

Abstract

A Brain Computer Interface (BCI) connects the human brain to the outside world, providing a direct communication channel. Electroencephalography (EEG) signals are commonly used in BCIs to reflect cognitive patterns related to motor function activities. However, due to the multichannel nature of EEG signals, explicit information processing is crucial to lessen computational complexity in BCI systems. This study proposes an innovative method based on brain region-specific channel selection and multi-domain feature fusion to improve classification accuracy. The novelty of the proposed approach lies in region-based channel selection, where EEG channels are grouped according to their functional relevance to distinct brain regions. By selecting channels based on specific regions involved in motor imagery (MI) tasks, this technique eliminates irrelevant channels, reducing data dimensionality and improving computational efficiency. This also ensures that the extracted features are more reflective of the brain actual activity related to motor tasks. Three distinct feature extraction methods Common Spatial Pattern (CSP), Fuzzy C-means clustering, and Tangent Space Mapping (TSM), are applied to each group of channels based on their brain region. Each method targets different characteristics of the EEG signal: CSP focuses on spatial patterns, Fuzzy C means identifies clusters within the data, and TSM captures non-linear patterns in the signal. The combined feature vector is used to classify motor imagery tasks (left hand, right hand, and right foot) using Support Vector Machine (SVM). The proposed method was validated on publicly available benchmark EEG datasets (IVA and I) from the BCI competition III and IV. The results show that the approach outperforms existing methods, achieving classification accuracies of 90.77% and 84.50% for datasets IVA and I, respectively.

Figures (11)

• Figure 1: Electroencephalography (EEG) of subject aw from channel C1 of BCI competition III IVA Dataset.
• Figure 2: Electroencephalography (EEG) of subject a from channel C1 of BCI competition IV-1 Dataset.
• Figure 3: BCI Competition III-IVA dataset timing sequence.
• Figure 4: BCI competition IV I dataset timing sequence.
• Figure 5: Block diagram of the proposed architecture