Adaptive Semi-Supervised Training of P300 ERP-BCI Speller System with Minimum Calibration Effort

TL;DR

This paper introduces an adaptive semi-supervised training framework for P300 ERP-BCI spellers that reduces calibration effort and improves spelling efficiency, especially with limited labeled data, by employing an EM-GMM algorithm.

Contribution

It proposes a novel semi-supervised adaptive training method that enhances BCI speller performance with minimal calibration data, outperforming traditional benchmarks in some cases.

Findings

9 out of 15 participants exceeded 0.7 accuracy

7 participants showed better performance with the adaptive method

The framework improves spelling efficiency with limited labeled data

Abstract

A P300 ERP-based Brain-Computer Interface (BCI) speller is an assistive communication tool. It searches for the P300 event-related potential (ERP) elicited by target stimuli, distinguishing it from the neural responses to non-target stimuli embedded in electroencephalogram (EEG) signals. Conventional methods require a lengthy calibration procedure to construct the binary classifier, which reduced overall efficiency. Thus, we proposed a unified framework with minimum calibration effort such that, given a small amount of labeled calibration data, we employed an adaptive semi-supervised EM-GMM algorithm to update the binary classifier. We evaluated our method based on character-level prediction accuracy, information transfer rate (ITR), and BCI utility. We applied calibration on training data and reported results on testing data. Our results indicate that, out of 15 participants, 9 participants exceed the minimum character-level accuracy of 0.7 using either on our adaptive method or the benchmark, and 7 out of these 9 participants showed that our adaptive method performed better than the benchmark. The proposed semi-supervised learning framework provides a practical and efficient alternative to improve the overall spelling efficiency in the real-time BCI speller system, particularly in contexts with limited labeled data.