Optimizing the Channel Selection and Classification Accuracy in EEG-Based BCI

Abstract

Multichannel EEG is generally used in brain-computer interfaces (BCIs), whereby performing EEG channel selection 1) improves BCI performance by removing irrelevant or noisy channels and 2) enhances user convenience from the use of lesser channels. This paper proposes a novel sparse common spatial pattern (SCSP) algorithm for EEG channel selection. The proposed SCSP algorithm is formulated as an optimization problem to select the least number of channels within a constraint of classification accuracy. As such, the proposed approach can be customized to yield the best classification accuracy by removing the noisy and irrelevant channels, or retain the least number of channels without compromising the classification accuracy obtained by using all the channels. The proposed SCSP algorithm is evaluated using two motor imagery datasets, one with a moderate number of channels and another with a large number of channels. In both datasets, the proposed SCSP channel selection significantly reduced the number of channels, and outperformed existing channel selection methods based on Fisher criterion, mutual information, support vector machine, common spatial pattern, and regularized common spatial pattern in classification accuracy. The proposed SCSP algorithm also yielded an average improvement of 10% in classification accuracy compared to the use of three channels (C3, C4, and Cz).

Artificial Neural Network Classification of Motor‐Related EEG: An Increase in Classification Accuracy by Reducing Signal Complexity

“…In addition, Tam et al [51] achieved highest average accuracy rate of 90% for 8 channels using a spatial filtering method. It is worth mentioning that Arvaneh et al [52] proposed a novel sparse common spatial pattern (SCSP) algorithm for optimization and obtained SVM-based classification accuracy of 81.63% using 13 channels.…”

EEG Analysis for Cognitive Failure Detection in Driving Using Type-2 Fuzzy Classifiers

“…The AAR parameters being of low dimensions require no feature selection. However, PSD and DWT [46] features used in MP and ME having large dimensions require reducing features using a feature selection algorithm. Let, Then the aim of the proposed feature selection algorithm is to select d<<D number of features in a manner such that it satisfies the following two objectives jointly.…”

Estimation of Brain Connectivity during Motor Imagery Tasks using Noise-Assisted Multivariate Empirical Mode Decomposition

“…Additionally, multichannel EEG configuration delays the use of the wearable BCI devices due to the inconvenience of donning it. In terms of the real-time BCI, selecting the least number of channels is important to reduce the computational complexity [24]. Of the 64 EEG channels, the 12 shown in Fig.…”

“…MIbased BCI systems can be a novel interaction option for those with motor disabilities because they do not require voluntary muscle control [4]. The physiological basis for such an MI paradigm is the mu (8)(9)(10)(11)(12) and beta rhythms (18)(19)(20)(21)(22)(23)(24)(25) in the EEG, which are found in the motor cortex region of the brain when subjects imagine movement of their hands or fingers [5]. Currently, bandpass filters, such as infinite impulse response (IIR) filters, are often used to extract the power features in the frequency bands relevant to MI tasks [1].…”