Improving Motor Imagery-Based Brain-Computer Interface Performance Based on Sensory Stimulation Training: An Approach Focused on Poorly Performing Users

Abstract

The motor imagery (MI)-based brain-computer interface (BCI) is an intuitive interface that provides control over computer applications directly from brain activity. However, it has shown poor performance compared to other BCI systems such as P300 and SSVEP BCI. Thus, this study aimed to improve MI-BCI performance by training participants in MI with the help of sensory inputs from tangible objects (i.e., hard and rough balls), with a focus on poorly performing users. The proposed method is a hybrid of training and imagery, combining motor execution and somatosensory sensation from a ball-type stimulus. Fourteen healthy participants participated in the somatosensory-motor imagery (SMI) experiments (within-subject design) involving EEG data classification with a three-class system (signaling with left hand, right hand, or right foot). In the scenario of controlling a remote robot to move it to the target point, the participants performed MI when faced with a three-way intersection. The SMI condition had a better classification performance than did the MI condition, achieving a 68.88% classification performance averaged over all participants, which was 6.59% larger than that in the MI condition (p < 0.05). In poor performers, the classification performance in SMI was 10.73% larger than in the MI condition (62.18% vs. 51.45%). However, good performers showed a slight performance decrement (0.86%) in the SMI condition compared to the MI condition (80.93% vs. 81.79%). Combining the brain signals from the motor and somatosensory cortex, the proposed hybrid MI-BCI system demonstrated improved classification performance, this phenomenon was predominant in poor performers (eight out of nine subjects). Hybrid MI-BCI systems may significantly contribute to reducing the proportion of BCI-inefficiency users and closing the performance gap with other BCI systems.

Subject-Dependent Artifact Removal for Enhancing Motor Imagery Classifier Performance under Poor Skills

“…In all performance metrics, we show their testing set values of the mean ± standard deviation averaged across two different evaluating strategies: (i) Global assessment by averaging over the whole set of individuals; (ii) Group-level assessment by averaging over a concrete category of subjects. Namely, we are interested in evaluating the effectiveness of the suggested preprocessing methodology for enhancing the classifier performance of the so-called inefficiency individuals [ 51 ].…”

Studies to Overcome Brain–Computer Interface Challenges

“…Over the past decades, there have been lots of BCI studies. They were usually focused on the methods to improve the prediction accuracy [5,8,23,[30][31][32], raise the number of commands [12,33], increase the information transfer rate (ITR) [34][35][36][37][38], or reduce the training efforts [7,30,34,39]. To enhance the prediction accuracy, new classification algorithms [30,40,41] or feature extraction methods have been proposed [31,32,42].…”

“…The motor cortex's alpha wave (8~13 Hz) and beta wave (13~30 Hz) will increase or decrease according to the movement intention. For example, when users want to move their hands or feet, the power of alpha and beta waves decreases on the corresponding motor cortex [2,[5][6][7][8]. Therefore, the BCI system can predict a left hand, a right hand, or feet movement intention using power change of the brain area.…”

The Effects of Sensory Threshold Somatosensory Electrical Stimulation on Users With Different MI-BCI Performance

“…Although past studies have shown that the guidance based on somatosensory afference contributes to the improvement of BCI performance, somatosensory afference guidance does not appear to be effective for all subjects. Park et al reported that BCI illiterate subjects achieve significantly higher MI-BCI classification accuracy when subjects are asked to perform the somatosensory-motor imagery, but BCI literate subjects experience a slight decrease in classification performance (Park et al, 2021). In addition, Kaiser et al showed that cortical effects of BCI training are only found in BCI illiterate subjects but not in BCI literate subjects (Kaiser et al, 2011).…”