EEG-Based Detection of Driver Emergency Braking Intention for Brain-Controlled Vehicles

Teng, Teng; Bi, Luzheng; Liu, Yili

doi:10.1109/tits.2017.2740427

Cited by 72 publications

(59 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the training mode, 20-min 8-channel EEG and IMU data are captured during the simulated driving task. In contrast to [22], the training data are collected by sliding the window along the data length, in the same manner as online testing. The analyzed window is set as 1 s, and the step size is varied to investigate its effects on the system performance.…”

Section: Methodsmentioning

confidence: 99%

“…In several previous studies [18,22], there was a lack of information regarding how to accurately label the training data in cases where time should be carefully considered. According to [27], ERD starts before the actual movement approximately 150 ms before the electromyography (EMG) onset.…”

Section: Methodsmentioning

confidence: 99%

“…Another study [17] demonstrated that neurophysiological correlates of emergency braking occur approximately 130 ms earlier than corresponding behavioral responses related to the actual braking event. Furthermore, according to [22], emergency braking intentions can be detected approximately 420 ms after the onset of an emergency stimulus. Therefore, in this study, we explore the neurophysiological response within 1 s before the executed braking event.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Detection of Driver Braking Intention Using EEG Signals During Simulated Driving

Nguyen

Chung

2019

Sensors

View full text Add to dashboard Cite

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.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Detection of Driver Braking Intention Using EEG Signals During Simulated Driving

Nguyen

Chung

2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Four types of distraction are clarified by the NHTSA, which are the visual distraction, auditory distraction, biomechanical distraction, and cognitive distraction [38]. To understand the driver behaviors, most of the studies require capturing the driver status information, such as the head pose [14], eye gaze [9], hand motion [15], foot dynamics [16], and even the physiological signals [17] [18].…”

Section: B Related Workmentioning

confidence: 99%

Driver Activity Recognition for Intelligent Vehicles: A Deep Learning Approach

Xing

Wang

Cao

et al. 2019

IEEE Trans. Veh. Technol.

280

111

View full text Add to dashboard Cite

Driver decisions and behaviors are essential factors that can affect the driving safety. To understand the driver behaviors, a driver activities recognition system is designed based on the deep convolutional neural networks (CNN) in this study. Specifically, seven common driving activities are identified, which are the normal driving, right mirror checking, rear mirror checking, left mirror checking, using in-vehicle radio device, texting, and answering the mobile phone, respectively. Among these activities, the first four are regarded as normal driving tasks, while the rest three are classified into the distraction group. The experimental images are collected using a low-cost camera, and ten drivers are involved in the naturalistic data collection. The raw images are segmented using the Gaussian mixture model (GMM) to extract the driver body from the background before training the behavior recognition CNN model. To reduce the training cost, transfer learning method is applied to fine tune the pre-trained CNN models. Three different pre-trained CNN models, namely, AlexNet, GoogLeNet, and ResNet50 are adopted and evaluated. The detection results for the seven tasks achieved an average of 81.6% accuracy using the AlexNet, 78.6% and 74.9% accuracy using the GoogLeNet and ResNet50, respectively. Then, the CNN models are trained for the binary classification task and identify whether the driver is being distracted or not. The binary detection rate achieved 91.4% accuracy, which shows the advantages of using the proposed deep learning approach. Finally, the real-world application are analysed and discussed. Index Terms-Driver Behaviour, driver distraction, convolutional neural network, transfer learning. I. INTRODUCTION A. Motivations D RIVER is in the center of the Road-Vehicle-Driver (RVD) loop. Driver decision and behaviors are the major aspects that can affect driving safety. It is reported that more

show abstract

“…As presented in the presentation segment about the ABS and Other wellbeing highlights, Studies and Invention thought of more highlights to upgrade the ABS or stopping mechanisms [10,11]. What they had done, they had presented…”

Section: Introductionmentioning

confidence: 99%

A Study on Vehicle’s Braking Control under Unknown Road Conditions

Patnaik¹,

Tjprc²

2019

IJMPERD

View full text Add to dashboard Cite

This review paper audit and talks about the four-wheel slowing mechanism which is autonomous for enhanced vehicle dependability and tire-street grating is obscure. Vehicle's security ought to be ensured for the vehicle to be steady under obscure street conditions. Braking is that vital part in a car without which a car can't be made or can't keep running on streets. Certain tests and reproductions made through PC programming demonstrates that solidness can be kept up under different conditions. The innovation talked about is generally utilized in vehicles to enhance the solace and wellbeing.

show abstract

EEG-Based Detection of Driver Emergency Braking Intention for Brain-Controlled Vehicles

Cited by 72 publications

References 38 publications

Detection of Driver Braking Intention Using EEG Signals During Simulated Driving

Detection of Driver Braking Intention Using EEG Signals During Simulated Driving

Driver Activity Recognition for Intelligent Vehicles: A Deep Learning Approach

A Study on Vehicle’s Braking Control under Unknown Road Conditions

Contact Info

Product

Resources

About