Abstract
Electroencephalography (EEG)-based driving fatigue detection has gained increasing attention recently due to the non-invasive, low-cost, and potable nature of the EEG technology, but it is still challenging to extract informative features from noisy EEG signals for driving fatigue detection. Radial basis function (RBF) neural network has drawn lots of attention as a promising classifier due to its linear-in-the-parameters network structure, strong non-linear approximation ability, and desired generalization property. The RBF network performance heavily relies on network parameters such as the number of the hidden nodes, number of the center vectors, width, and output weights. However, global optimization methods that directly optimize all the network parameters often result in high evaluation cost and slow convergence. To enhance the accuracy and efficiency of EEG-based driving fatigue detection model, this study aims to develop a two-level learning hierarchy RBF network (RBF-TLLH) which allows for global optimization of the key network parameters. Experimental EEG data were collected, at both fatigue and alert states, from six healthy participants in a simulated driving environment. Principal component analysis was first utilized to extract features from EEG signals, and the proposed RBF-TLLH was then employed for driving status (fatigue vs. alert) classification. The results demonstrated that the proposed RBF-TLLH approach achieved a better classification performance (mean accuracy: 92.71%; area under the receiver operating curve: 0.9199) compared to other widely used artificial neural networks. Moreover, only three core parameters need to be determined using the training datasets in the proposed RBF-TLLH classifier, which increases its reliability and applicability. The findings demonstrate that the proposed RBF-TLLH approach can be used as a promising framework for reliable EEG-based driving fatigue detection.
Highlights
Driving fatigue is a typical mental and physical concern that weakens the driver’s ability to control the vehicle (Li Z. et al, 2017)
The overall structure for the proposed EEG-based fatigue classification framework is shown in Figure 1, which consists of five steps: (1) EEG data collection during a simulated driving environment, (2) raw data pre-processing and segmentation, (3) dimensionality reduction and feature extraction using principal component analysis (PCA); (4) classification using the Radial basis function (RBF) network, and (5) performance evaluation
The results show that the RBF-two-level learning hierarchy (TLLH) classifier achieves the highest accuracy for all the subjects in classifying the fatigue vs. alert states, with the mean value of 92.71 ± 6.26%
Summary
Driving fatigue is a typical mental and physical concern that weakens the driver’s ability to control the vehicle (Li Z. et al, 2017). (Akerstedt et al, 2005; Hsieh and Tai, 2013), and (3) physiological approach that makes use of bio-signals associated with driving fatigue, such as electrooculography (EOG) to measure the movement of the eye (Hu and Zheng, 2009; Picot et al, 2012), electrocardiography (ECG) to detect heart rate variability (Jung et al, 2014), electroencephalography (EEG) to assess brain state (Huang et al, 2016; Ma et al, 2019, 2020), and electromyography (EMG) to measure muscle activity (Sikander and Anwar, 2019). EOG, ECG, surface EMG, and EEG have all been explored as physiological measures for driving fatigue detection, with specific advantages and disadvantages to each other (Sikander and Anwar, 2019). EEG signal retrieval through multiple electrodes is highly susceptible to noise from external factors, and it is critical to extract informative features from noisy EEG signals for a successful driving fatigue detection application
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
