Covariate Shift Estimation based Adaptive Ensemble Learning for Handling Non-Stationarity in Motor Imagery related EEG-based Brain-Computer Interface

TL;DR

This paper introduces a covariate shift estimation integrated adaptive ensemble learning method to improve EEG-based brain-computer interface performance amidst non-stationarity, demonstrating significant accuracy improvements over existing methods.

Contribution

It presents a novel covariate shift detection and adaptive ensemble updating approach for MI EEG classification, addressing non-stationarity more efficiently than prior passive schemes.

Findings

Significantly improved MI classification accuracy.

Effective detection of covariate shifts in EEG features.

Outperforms state-of-the-art passive and active schemes.

Abstract

The non-stationary nature of electroencephalography (EEG) signals makes an EEG-based brain-computer interface (BCI) a dynamic system, thus improving its performance is a challenging task. In addition, it is well-known that due to non-stationarity based covariate shifts, the input data distributions of EEG-based BCI systems change during inter- and intra-session transitions, which poses great difficulty for developments of online adaptive data-driven systems. Ensemble learning approaches have been used previously to tackle this challenge. However, passive scheme based implementation leads to poor efficiency while increasing high computational cost. This paper presents a novel integration of covariate shift estimation and unsupervised adaptive ensemble learning (CSE-UAEL) to tackle non-stationarity in motor-imagery (MI) related EEG classification. The proposed method first employs an exponentially weighted moving average model to detect the covariate shifts in the common spatial pattern features extracted from MI related brain responses. Then, a classifier ensemble was created and updated over time to account for changes in streaming input data distribution wherein new classifiers are added to the ensemble in accordance with estimated shifts. Furthermore, using two publicly available BCI-related EEG datasets, the proposed method was extensively compared with the state-of-the-art single-classifier based passive scheme, single-classifier based active scheme and ensemble based passive schemes. The experimental results show that the proposed active scheme based ensemble learning algorithm significantly enhances the BCI performance in MI classifications.