Post-Adaptation Effects in a Motor Imagery Brain-Computer Interface Online Coadaptive Paradigm

Jose Diogo Cunha,Serafeim Perdikis,Reinhold Scherer,Sebastian Halder

doi:10.1109/access.2021.3064226

Jose Diogo Cunha, Serafeim Perdikis + Show 2 more

Open Access

https://doi.org/10.1109/access.2021.3064226

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2021
Citations: 54	License type: CC BY 4.0

Affiliation: University of Essex, Graz University of Technology

Abstract

Online coadaptive training has been successfully employed to enable people to control motor imagery (MI)-based brain-computer interfaces (BCIs), allowing to completely skip the lengthy and demotivating open-loop calibration stage traditionally applied before closed-loop control. However, practical reasons may often dictate to eventually switch off decoder adaptation and proceed with BCI control under a fixed BCI model, a situation that remains rather unexplored. This work studies the existence and magnitude of potential post-adaptation effects on system performance, subject learning and brain signal modulation stability in a state-of-the-art, coadaptive training regime inspired by a game-like design. The results extracted in a cohort of 20 able-bodied individuals reveal that ceasing classifier adaptation after three runs (approx. 30 min) of a single-session training protocol had no significant impact on any of the examined BCI control and learning aspects in the remaining two runs (about 20 min) with a fixed classifier. Fifteen individuals achieved accuracies that are better than chance level and allowed them to successfully execute the given task. These findings alleviate a major concern regarding the applicability of coadaptive MI BCI training, thus helping to further establish this training approach and allow full exploitation of its benefits.

Highlights

Brain-computer interfaces (BCI) based on the detection and identification of electroencephalographic (EEG) sensorimotor rhythms (SMRs), which are elicited by imagined or attempted movements [1], are popular for providing the possibility of spontaneous interaction by noninvasive means
1) BCI PERFORMANCES Table 1 illustrates the single-sample classification accuracy, the trial-wise accuracy, the trial hit percentage and the total number of collected stars
The main finding is that stopping machine adaptation has no significant consequences for any of the variables of interest examined, namely, BCI performance, the ability of subjects to elicit the anticipated EEG activity through motor imagery (MI), or the stability of SMR modulation

Summary

Introduction

Brain-computer interfaces (BCI) based on the detection and identification of electroencephalographic (EEG) sensorimotor rhythms (SMRs), which are elicited by imagined or attempted movements [1], are popular for providing the possibility of spontaneous interaction by noninvasive means. Coadaptive BCIs, where the decoder parameters [28] and/or–less commonly–the features extracted from brain signals to be processed by the decoder [29]–[31] are recalculated on-thefly during real-time, closed-loop BCI operation have been proven able to reduce performance instability by tracking and adapting to non-stationarity effects present in brain signals [16], [27]–[30], [32]–[38] This literature has often implied that decoder adaptation subserving online BCI control may pose a remedy for the problem of non-universal accessibility (often termed ‘‘BCI illiteracy’’ [34]), when subjects do not exhibit the desired modulation of SMRs to be exploited by the BCI.

Methods

Results

Conclusion