Detection of Driver Braking Intention Using EEG Signals During Simulated Driving.

Trung-Hau Nguyen,Wan-Young Chung

doi:10.3390/s19132863

Abstract

In this work, we developed a novel system to detect the braking intention of drivers in emergency situations using electroencephalogram (EEG) signals. The system acquired eight-channel EEG and motion-sensing data from a custom-designed EEG headset during simulated driving. A novel method for accurately labeling the training data during an extremely short period after the onset of an emergency stimulus was introduced. Two types of features, including EEG band power-based and autoregressive (AR)-based, were investigated. It turned out that the AR-based feature in combination with artificial neural network classifier provided better detection accuracy of the system. Experimental results for ten subjects indicated that the proposed system could detect the emergency braking intention approximately 600 ms before the onset of the executed braking event, with high accuracy of 91%. Thus, the proposed system demonstrated the feasibility of developing a brain-controlled vehicle for real-world applications.

Highlights

In the past decade, brain–computer interface (BCI) has emerged as a potential technology for decoding neural activities into commands by using electroencephalogram (EEG) signals
The training set consists of ~1100 samples (4 folds) whereas the validation set consists of ~280 samples (1 fold) according to 5-fold cross-validation method. These results indicated the discriminative capability of the dataset into two groups “normal driving” and “braking intention”
We developed a novel system using EEG signals for detecting the emergency braking

Summary

Introduction

Brain–computer interface (BCI) has emerged as a potential technology for decoding neural activities into commands by using electroencephalogram (EEG) signals. This new technology allows paralyzed people to communicate using their minds. Many researchers have focused on developing BCI systems to improve the quality of life of disabled people. EEG signals have been used to develop driving-assistance systems Most of these studies have focused on using EEG signals to monitor physical conditions or mental states of the driver, e.g., drowsiness [9,10] or mental workload [11,12], as an effort to reduce traffic accidents

Objectives

Methods

Results

Conclusion