$k$-AdaptEEGCS: Adaptive Threshold Based Automatic EEG Channel Selection

Abstract

Electroencephalography (EEG) channel selection is crucial for improving the accuracy and efficiency of EEG-based brain-computer interfaces (BCI) and cognitive state monitoring systems. This research identifies the most informative EEG channels that provide maximum discriminative power for specific tasks or applications. However, the availability of multiple electrodes can lead to data redundancy and increased computational complexity. In addition, selecting suboptimal channels may result in poor signal quality and reduced classification accuracy. A method called $k$ -adaptEEGCS is proposed in this study to address these challenges. $k$ -adaptEEGCS utilizes a similarity-metric-based approach to measure the similarity of EEG channels within each cluster and identify the best EEG channels using an adaptive threshold. The results show that $k$ -adaptEEGCS improves classification accuracy and reduces channel selection time in specific EEG groups compared to using all EEG channels. Furthermore, the efficacy and superiority of $k$ -adaptEEGCS are demonstrated through an analysis of BCI competition datasets; the average accuracy and channel reduction rate achieved is 93.09% and 67%.