Research Article
AIMSafe: EEG-Based Driver Behavior Understanding via Attention and Incremental Learning Mechanisms
@INPROCEEDINGS{10.1007/978-3-031-63992-0_16, author={Landu Jiang and Cheng Luo and Tao Gu and Kezhong Lu and Dian Zhang}, title={AIMSafe: EEG-Based Driver Behavior Understanding via Attention and Incremental Learning Mechanisms}, proceedings={Mobile and Ubiquitous Systems: Computing, Networking and Services. 20th EAI International Conference, MobiQuitous 2023, Melbourne, VIC, Australia, November 14--17, 2023, Proceedings, Part II}, proceedings_a={MOBIQUITOUS PART 2}, year={2024}, month={7}, keywords={Driving Safety Driver Education Wearable Sensing EEG Smart computing}, doi={10.1007/978-3-031-63992-0_16} }- Landu Jiang
Cheng Luo
Tao Gu
Kezhong Lu
Dian Zhang
Year: 2024
AIMSafe: EEG-Based Driver Behavior Understanding via Attention and Incremental Learning Mechanisms
MOBIQUITOUS PART 2
Springer
DOI: 10.1007/978-3-031-63992-0_16
Abstract
In this paper, we proposeAIMSafe, an electroencephalographic (EEG) based system that studies driver in-vehicle behaviors leveragingAttention networks andIncremental learningMechanism for roadSafety. Instead of using predefined classes, we categorize driver in-vehicle activities into different risk levels - a stronger motion may have a higher chance of unsafe driving. More specifically, we first employ a CNN based model to distinguish two basic activities - 1. normal driving and 2. unsafe driving. Moreover,AIMSafealso leverages smartphone IMU sensors generating soft hints that helps automatically label EEG data on road. We then adopt class-incremental learning to rank other Out-of-Distribution (OOD) driver activities (safe to unsafe) based on the Mahalanobis distance. A modified Squeeze-and-Excitation (SE) block is also used to adaptively select effective EEG electrodes for improving the system efficiency. Evaluation results (involving 11 males and 4 females) show thatAIMSafecould achieve a detection accuracy over 95% on unsafe driving activities using only 4 electrodes.
