GAN-based EEG Forecasting for Attaining Driving Operations

Abstract

In the domain of connected vehicles or advanced driver assistance systems, electroencephalogram (EEG) data is measured in vehicles and used for applications in driver safety. These analysis modules are designed to detect abnormal driver states such as drowsiness, fatigue, and dangerous driving by using EEG data in real-time on edge devices since these conditions reflect a driver’s current cognitive state. However, there are few approaches to forecasting EEG data to prevent dangerous driving in advance using recent deep learning techniques. In this paper, we propose a novel generative adversarial network (W-GAN) which aims to forecast EEGs as a multivariate multi-step times series data. It consists of dilated causal convolutional layers to maintain EEG characteristics. We also propose a new performance measure reflecting the reproducibility of frequency components which confirms the feasibility of the forecasted EEG data. We conducted an experiment to evaluate our proposed model using EEG analysis research data. In the experiment, it was shown that our model outperformed several deep learning models in reproducibility of both EEG waveform and frequency components.