An Online Data Visualization Feedback Protocol for Motor Imagery-Based BCI Training

Abstract

Brain–computer interface (BCI) has developed rapidly over the past two decades, mainly due to advancements in machine learning. Subjects must learn to modulate their brain activities to ensure a successful BCI. Feedback training is a practical approach to this learning process; however, the commonly used classifier-dependent approaches have inherent limitations such as the need for calibration and a lack of continuous feedback over long periods of time. This paper proposes an online data visualization feedback protocol that intuitively reflects the EEG distribution in Riemannian geometry in real time. Rather than learning a hyperplane, the Riemannian geometry formulation allows iterative learning of prototypical covariance matrices that are translated into visualized feedback through diffusion map process. Ten subjects were recruited for MI-BCI (motor imagery-BCI) training experiments. The subjects learned to modulate their sensorimotor rhythm to centralize the points within one category and to separate points belonging to different categories. The results show favorable overall training effects in terms of the class distinctiveness and EEG feature discriminancy over a 3-day training with 30% learners. A steadily increased class distinctiveness in the last three sessions suggests that the advanced training protocol is effective. The optimal frequency band was consistent during the 3-day training, and the difference between subjects with good or low MI-BCI performance could be clearly observed. We believe that the proposed feedback protocol has promising application prospect.

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

“…Subjects could confirm the results of imagery task by the information of color and location in the brain topography, and it could have a positive effect on their task performance. The next trial started after subject's feedback (Zoefel et al, 2011;Boe et al, 2014;Duan et al, 2021). To allow the subjects to concentrate on the experimental tasks, we designed the tasks to be administered when the subjects felt fully prepared.…”

Riemannian geometry-based metrics to measure and reinforce user performance changes during brain-computer interface user training

“…As such, these metrics neither integrate new data nor reflect changes in user performance as new trials are attempted. Duan et al ( 2021 ) rendered these metrics in conjunction with diffusion maps to provide a visual representation of the relative similarities and differences of recent trials to users during online training.…”

Evaluation of Real-Time Endogenous Brain-Computer Interface Developed Using Ear-Electroencephalography

“…MA showed relatively strong ERS in α- and β-bands and widespread ERD in a high frequency band (γ-band), which were similar to observations made in our previous studies ( Choi et al, 2018 ; Choi and Hwang, 2019 ). Interestingly, the ERD/ERS pattern of MA became more dominant with the passage of time; from a neurophysiological viewpoint, this can be attributed to learning through real-time feedback in the online experiment, which led to better facilitation of brain activity ( Duan et al, 2021 ). The ERD/ERS pattern of WA somewhat overlapped with that of MA in terms of α- and β-ERS with γ-ERD, but was also different from MA (e.g., relatively stronger θ- and α-ERS and shorter period of γ-ERD compared with MA).…”