Capsule Attention for Multimodal EEG-EOG Representation Learning with Application to Driver Vigilance Estimation

TL;DR

This paper introduces a novel multimodal deep learning architecture with capsule attention for real-time driver vigilance estimation using EEG and EOG signals, outperforming existing methods and providing insights into brain region contributions.

Contribution

The paper proposes a capsule attention mechanism integrated with LSTM for improved multimodal EEG-EOG vigilance estimation, achieving state-of-the-art performance.

Findings

Outperforms baseline methods in vigilance estimation accuracy

Capsule attention enhances focus on salient features

Effective across different frequency bands and brain regions

Abstract

Driver vigilance estimation is an important task for transportation safety. Wearable and portable brain-computer interface devices provide a powerful means for real-time monitoring of the vigilance level of drivers to help with avoiding distracted or impaired driving. In this paper, we propose a novel multimodal architecture for in-vehicle vigilance estimation from Electroencephalogram and Electrooculogram. To enable the system to focus on the most salient parts of the learned multimodal representations, we propose an architecture composed of a capsule attention mechanism following a deep Long Short-Term Memory (LSTM) network. Our model learns hierarchical dependencies in the data through the LSTM and capsule feature representation layers. To better explore the discriminative ability of the learned representations, we study the effect of the proposed capsule attention mechanism including the number of dynamic routing iterations as well as other parameters. Experiments show the robustness of our method by outperforming other solutions and baseline techniques, setting a new state-of-the-art. We then provide an analysis on different frequency bands and brain regions to evaluate their suitability for driver vigilance estimation. Lastly, an analysis on the role of capsule attention, multimodality, and robustness to noise is performed, highlighting the advantages of our approach.