期刊
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
卷 25, 期 3, 页码 693-700出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JBHI.2020.3008229
关键词
Fatigue; Electroencephalography; Electrodes; Nonhomogeneous media; Informatics; Vehicles; Physiology; Multilayer network; EEG signals; driving fatigue
类别
资金
- National Natural Science Foundation of China [61922062, 61873181]
The study focuses on driving fatigue detection using EEG signals, finding that the RDMB network plays a crucial role in the detection process and achieves high accuracy through key sub-network extraction and feature vector construction.
Fatigue driving has attracted a great deal of attention for its huge influence on automobile accidents. Recognizing driving fatigue provides a primary but significant way for addressing this problem. In this paper, we first conduct the simulated driving experiments to acquire the EEG signals in alert and fatigue states. Then, for multi-channel EEG signals without pre-processing, a novel rhythm-dependent multilayer brain network (RDMB network) is developed and analyzed for driving fatigue detection. We find that there exists a significant difference between alert and fatigue states from the view of network science. Further, key sub-RDMB network based on closeness centrality are extracted. We calculate six network measures from the key sub-RDMB network and construct feature vectors to classify the alert and fatigue states. The results show that our method can respectively achieve the average accuracy of 95.28% (with sample length of 5 s), 90.25% (2 s), and 87.69% (1 s), significantly higher than compared methods. All these validate the effectiveness of RDMB network for reliable driving fatigue detection via EEG.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据