Relative Power Correlates With the Decoding Performance of Motor Imagery Both Across Time and Subjects

Abstract

One of the most significant challenges in the application of brain-computer interfaces (BCI) is the large performance variation, which often occurs over time or across users. Recent evidence suggests that the physiological states may explain this performance variation in BCI, however, the underlying neurophysiological mechanism is unclear. In this study, we conducted a seven-session motor-imagery (MI) experiment on 20 healthy subjects to investigate the neurophysiological mechanism on the performance variation. The classification accuracy was calculated offline by common spatial pattern (CSP) and support vector machine (SVM) algorithms to measure the MI performance of each subject and session. Relative Power (RP) values from different rhythms and task stages were used to reflect the physiological states and their correlation with the BCI performance was investigated. Results showed that the alpha band RP from the supplementary motor area (SMA) within a few seconds before MI was positively correlated with performance. Besides, the changes of RP between task and pre-task stage from theta, alpha, and gamma band were also found to be correlated with performance both across time and subjects. These findings reveal a neurophysiological manifestation of the performance variations, and would further provide a way to improve the BCI performance.

Reducing the Calibration Time in Somatosensory BCI by Using Tactile ERD

“…Both imagined movement and imagined sensation are covert mental tasks, which are inherently internal and difficult to observe and measure when no external cue is applied. This causes a wide range of performance variations [33], [34], with relatively poor performance even when training across weeks [35]- [37].…”

Neurofeedback Training of Alpha Relative Power Improves the Performance of Motor Imagery Brain-Computer Interface

“…Further, some researchers found that lower resting-state alpha-band relative power (RP) may indicate poor MI performers (Ahn et al, 2013;Kwon et al, 2020). Our previous study suggests that the positive correlation between alpha-band RP and MI-BCI performance was consistent in inter-subject and inter-session analysis, especially over the frontal lobes (Zhou et al, 2021). These results indicate that the strength of alpha rhythm in the resting state might reflect an unstable cognitive state, which results in the variation of MI-BCI performance.…”

“…Our previous study showed no obvious MI-BCI performance improvement across six runs in 1 day or even across seven sessions in multiple days without feedback (Zhou et al, 2021), suggesting that subjects found it difficult to regulate their brain rhythms to successfully reach the expected output without feedback. In this study, MI-BCI performance was significantly improved after alpha NFT, especially between left-hand and right-hand MI tasks.…”

“…Alpha-band RP has been proved to be a promising stable neurophysiological indicator for MI-BCI performance in our previous work (Zhou et al, 2021). However, few studies have used alpha-band RP as the target signal of NFT.…”

“…MI-BCI performance refers to the ability of subjects to control an MI-BCI system and is generally assessed through decoding accuracies. MI-BCI performance shows a significant intra-and inter-subject variability (Ahn and Jun, 2015;Saha and Baumert, 2020;Zhou et al, 2021), which impedes its wide adoption for BCI applications. Understanding the neural mechanisms behind such variability is a promising approach that will aid in solving the problem (Xu et al, 2021).…”