Calibration-Free Driver Drowsiness Classification based on Manifold-Level Augmentation

TL;DR

This paper introduces a calibration-free driver drowsiness classification framework using manifold-level augmentation of EEG features, enhancing generalization and accessibility of brain-computer interfaces for road safety.

Contribution

It proposes a novel manifold-level augmentation method that improves EEG-based drowsiness classification without calibration, advancing domain generalization in BCI applications.

Findings

Manifold-level augmentation significantly improves classification accuracy.

Deeper models with smaller kernels enhance generalization.

The framework enables calibration-free driver drowsiness detection.

Abstract

Drowsiness reduces concentration and increases response time, which causes fatal road accidents. Monitoring drivers' drowsiness levels by electroencephalogram (EEG) and taking action may prevent road accidents. EEG signals effectively monitor the driver's mental state as they can monitor brain dynamics. However, calibration is required in advance because EEG signals vary between and within subjects. Because of the inconvenience, calibration has reduced the accessibility of the brain-computer interface (BCI). Developing a generalized classification model is similar to domain generalization, which overcomes the domain shift problem. Especially data augmentation is frequently used. This paper proposes a calibration-free framework for driver drowsiness state classification using manifold-level augmentation. This framework increases the diversity of source domains by utilizing features. We experimented with various augmentation methods to improve the generalization performance. Based on the results of the experiments, we found that deeper models with smaller kernel sizes improved generalizability. In addition, applying an augmentation at the manifold-level resulted in an outstanding improvement. The framework demonstrated the capability for calibration-free BCI.