Offline EEG-Based Driver Drowsiness Estimation Using Enhanced Batch-Mode Active Learning (EBMAL) for Regression

TL;DR

This paper introduces EBMAL, a novel active learning method for offline regression tasks in BCI, specifically improving driver drowsiness estimation from EEG signals by selecting more reliable and diverse samples.

Contribution

The paper presents a new enhanced batch-mode active learning approach for regression, tailored for offline BCI applications, demonstrating improved sample selection and regression accuracy.

Findings

EBMAL outperforms baseline active learning in regression accuracy.

Effective in selecting diverse and representative EEG samples.

Applicable to various offline regression problems beyond BCI.

Abstract

There are many important regression problems in real-world brain-computer interface (BCI) applications, e.g., driver drowsiness estimation from EEG signals. This paper considers offline analysis: given a pool of unlabeled EEG epochs recorded during driving, how do we optimally select a small number of them to label so that an accurate regression model can be built from them to label the rest? Active learning is a promising solution to this problem, but interestingly, to our best knowledge, it has not been used for regression problems in BCI so far. This paper proposes a novel enhanced batch-mode active learning (EBMAL) approach for regression, which improves upon a baseline active learning algorithm by increasing the reliability, representativeness and diversity of the selected samples to achieve better regression performance. We validate its effectiveness using driver drowsiness estimation from EEG signals. However, EBMAL is a general approach that can also be applied to many other offline regression problems beyond BCI.