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
  • [1] Driver Drowsiness Detection Using Single-Channel Dry EEG
    Song, Xiaomu
    Yoon, Suk-Chung
    Rex, Eric
    Nieves, Jason
    Moretz, Caleb
    2017 IEEE SIGNAL PROCESSING IN MEDICINE AND BIOLOGY SYMPOSIUM (SPMB), 2017,
  • [2] Driver Drowsiness Detection Using EEG and EOG with an Attention-CNN Framework
    Qiu, Shuo
    Liu, Danqing
    Qin, Yanjun
    Tao, Xiaoming
    2024 4TH INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATION AND ARTIFICIAL INTELLIGENCE, CCAI 2024, 2024, : 75 - 80
  • [3] Feature Selection for Driver Drowsiness Detection
    Panda, Saurav
    Kolhekar, Megha
    PROCEEDINGS OF INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND DATA ENGINEERING (ICCIDE 2018), 2019, 28 : 127 - 140
  • [4] Driver Drowsiness Detection with Commercial EEG Headsets
    Rezaee, Qazal
    Delrobaei, Mehdi
    Giveki, Ashkan
    Dayarian, Nasireh
    Haghighi, Sahar Javaher
    2022 10TH RSI INTERNATIONAL CONFERENCE ON ROBOTICS AND MECHATRONICS (ICROM), 2022, : 546 - 550
  • [5] Driver Drowsiness Detection Using EEG Features
    Hwang, Se-Hyeon
    Park, Myoungouk
    Kim, Jonghwa
    Yun, Yongwon
    Son, Joonwoo
    HCI INTERNATIONAL 2018 - POSTERS' EXTENDED ABSTRACTS, PT III, 2018, 852 : 367 - 374
  • [6] A Driver Assistance Framework based on Driver Drowsiness Detection
    Tran, Duy
    Tadesse, Eyosiyas
    Sheng, Weihua
    Sun, Yuge
    Liu, Meigin
    Zhang, Senlin
    2016 IEEE INTERNATIONAL CONFERENCE ON CYBER TECHNOLOGY IN AUTOMATION, CONTROL, AND INTELLIGENT SYSTEMS (CYBER), 2016, : 173 - 178
  • [7] A Mobile Driver Safety System: Analysis of Single-Channel EEG on Drowsiness Detection
    Lim, Chee-Keong Alfred
    Chia, Wai Chong
    Chin, Siew Wen
    2014 INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND TECHNOLOGY (ICCST), 2014,
  • [8] Driver Drowsiness Detection Using the In-Ear EEG
    Hwang, Taeho
    Kim, Miyoung
    Hong, Seunghyeok
    Park, Kwang Suk
    2016 38TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2016, : 4646 - 4649
  • [9] A zero precision loss framework for EEG channel selection: enhancing efficiency and maintaining interpretability
    Wang, Lu
    Wang, Junkongshuai
    Su, Haolong
    Zhang, Xueze
    Zhang, Lihua
    Kang, Xiaoyang
    COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING, 2024,
  • [10] Driver Drowsiness Detection Using EEG Power Spectrum Analysis
    Awais, Muhammad
    Badruddin, Nasreen
    Drieberg, Micheal
    2014 IEEE REGION 10 SYMPOSIUM, 2014, : 244 - 247