An EEG Channel Selection Framework for Driver Drowsiness Detection via Interpretability Guidance

被引:0
|
作者
Zhou, Xinliang [1 ]
Lin, Dan [2 ]
Jia, Ziyu [3 ,4 ]
Xiao, Jiaping [5 ]
Liu, Chenyu [1 ]
Zhai, Liming [2 ]
Liu, Yang [1 ]
机构
[1] Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore 639798, Singapore
[2] Nanyang Technol Univ, Continental NTU Corp Lab, 50 Nanyang Ave, Singapore 639798, Singapore
[3] Chinese Acad Sci, Inst Automat, Brainnetome Ctr, Beijing 100190, Peoples R China
[4] Univ Chinese Acad Sci, Beijing 100190, Peoples R China
[5] Nanyang Technol Univ, Sch Mech & Aerosp Engn, Singapore 639798, Singapore
来源
2023 45TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY, EMBC | 2023年
基金
新加坡国家研究基金会;
关键词
Driver Drowsiness Detection; Channel Selection; EEG and Interpretability; NEURAL-NETWORK;
D O I
10.1109/EMBC40787.2023.10341126
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Drowsy driving has a crucial influence on driving safety, creating an urgent demand for driver drowsiness detection. Electroencephalogram (EEG) signal can accurately reflect the mental fatigue state and thus has been widely studied in drowsiness monitoring. However, the raw EEG data is inherently noisy and redundant, which is neglected by existing works that just use single-channel EEG data or full-head channel EEG data for model training, resulting in limited performance of driver drowsiness detection. In this paper, we are the first to propose an Interpretability-guided Channel Selection (ICS) framework for the driver drowsiness detection task. Specifically, we design a two-stage training strategy to progressively select the key contributing channels with the guidance of interpretability. We first train a teacher network in the first stage using full-head channel EEG data. Then we apply the class activation mapping (CAM) to the trained teacher model to highlight the high-contributing EEG channels and further propose a channel voting scheme to select the top N contributing EEG channels. Finally, we train a student network with the selected channels of EEG data in the second stage for driver drowsiness detection. Experiments are designed on a public dataset, and the results demonstrate that our method is highly applicable and can significantly improve the performance of cross-subject driver drowsiness detection.
引用
收藏
页数:5
相关论文
共 50 条
  • [21] A wearable EEG based driver drowsiness detection and alert system for accident prevention
    Chandran, A. V. S.
    Radhakrishnan, D. A.
    EPILEPSIA, 2023, 64 : 253 - 253
  • [22] A context-aware EEG headset system for early detection of driver drowsiness
    Department of Electronic Engineering, Pukyong National University, Busan
    608-737, Korea, Republic of
    Sensors, 8 (20873-20893):
  • [23] Driver drowsiness estimation using EEG signals with a dynamical encoder–decoder modeling framework
    Sadegh Arefnezhad
    James Hamet
    Arno Eichberger
    Matthias Frühwirth
    Anja Ischebeck
    Ioana Victoria Koglbauer
    Maximilian Moser
    Ali Yousefi
    Scientific Reports, 12
  • [24] An Integrated Manual and Autonomous Driving Framework based on Driver Drowsiness Detection
    Sheng, Weihua
    Ou, Yongsheng
    Duy Tran
    Tadesse, Eyosiyas
    Liu, Meiqin
    Yan, Gangfeng
    2013 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2013, : 4376 - 4381
  • [25] A compact and interpretable convolutional neural network for cross-subject driver drowsiness detection from single-channel EEG
    Cui, Jian
    Lan, Zirui
    Liu, Yisi
    Li, Ruilin
    Li, Fan
    Sourina, Olga
    Muller-Wittig, Wolfgang
    METHODS, 2022, 202 : 173 - 184
  • [26] Simultaneous Eye Blink Characterization and Elimination From Low-Channel Prefrontal EEG Signals Enhances Driver Drowsiness Detection
    Shahbakhti, Mohammad
    Beiramvand, Matin
    Rejer, Izabela
    Augustyniak, Piotr
    Broniec-Wojcik, Anna
    Wierzchon, Michal
    Marozas, Vaidotas
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2022, 26 (03) : 1001 - 1012
  • [27] Automated Driver Drowsiness Detection from Single-Channel EEG Signals Using Convolutional Neural Networks and Transfer Learning
    Ghadami, Ali
    Mohammadzadeh, Mohammad
    Taghimohammadi, Mohammadreza
    Taheri, Alireza
    2022 IEEE 25TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC), 2022, : 4068 - 4073
  • [28] EEG-Based Driver Drowsiness Detection Using the Dynamic Time Dependency Method
    Zhang, Haolan
    Zhao, Qixin
    Lee, Sanghyuk
    Dowens, Margaret G.
    BRAIN INFORMATICS, 2019, 11976 : 39 - 47
  • [29] Driver Drowsiness Detection via a Hierarchical Temporal Deep Belief Network
    Weng, Ching-Hua
    Lai, Ying-Hsiu
    Lai, Shang-Hong
    COMPUTER VISION - ACCV 2016 WORKSHOPS, PT III, 2017, 10118 : 117 - 133
  • [30] Heart Rate Variability-Based Driver Drowsiness Detection and Its Validation With EEG
    Fujiwara, Koichi
    Abe, Erika
    Kamata, Keisuke
    Nakayama, Chikao
    Suzuki, Yoko
    Yamakawa, Toshitaka
    Hiraoka, Toshihiro
    Kano, Manabu
    Sumi, Yukiyoshi
    Masuda, Fumi
    Matsuo, Masahiro
    Kadotani, Hiroshi
    IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2019, 66 (06) : 1769 - 1778