Motor and Cognitive Imagery Detection from MEG Signals Using Wavelet-Based Common Spatial Pattern Analysis.

Abstract

Brain-computer interface (BCI) technology supports the interactions of individuals with severe neuromuscular limitations with their environment. This work presents a classification approach for distinguishing motor imagery (MI) from speech-related cognitive imagery (CI) such as word generation and arithmetic subtraction, using magnetoencephalography (MEG) signals. Differentiating MI and CI/SI processes is relevant for expanding command diversity in hybrid BCI systems and for clarifying the distinct neural mechanisms underlying motor versus verbal-semantic processing. Although a large proportion of noninvasive BCI studies focus on MI, this distinction has received relatively limited attention, particularly in MEG-based approaches. Making this distinction is important for increasing command diversity in hybrid BCI systems and for improving the understanding of neural mechanisms associated with motor and verbal-semantic processing. Tasks from an open-access MEG dataset were analyzed across six binary pairs (H-F, H-W, H-S, F-W, F-S, W-S). MEG signals were processed using two frequency-separation strategies: a broad-band configuration (FSB-1: 8-14[Formula: see text]Hz and 14-30[Formula: see text]Hz) and a narrow-band configuration (FSB-2: six sub-bands between 8 and 32[Formula: see text]Hz). Time-frequency features were extracted using continuous wavelet transform (CWT), and spatial features via the common spatial pattern (CSP) method. Feature selection followed a two-stage procedure: (i) t-test ranking to obtain a shared feature set for all task pairs; and (ii) subject- and task-specific optimization of feature number. The initial evaluation based on the shared feature set showed that the FSB-2/CWT approach yielded better classification accuracies compared to FSB-1/CWT (H-F: 56%, H-W: 71%, H-S: 66% versus 54%, 68%, 64%). With subject- and task-adaptive optimization, additional improvements were observed. Accuracies increased to 60%, 72%, and 69% for FSB-1, and to 63%, 75%, and 71% for FSB-2, for H-F, H-W, and H-S, respectively. Overall, the findings indicate that the proposed CWT[Formula: see text]CSP framework, particularly when combined with adaptive feature optimization, offers an interpretable analysis approach that can contribute to MI-CI discrimination in MEG-based BCI systems under limited data conditions.