Abstract
Fatigue driving (FD) is one of the main causes of traffic accidents. Traditionally, machine learning technologies such as back propagation neural network (BPNN) and support vector machine (SVM) are popularly used for fatigue driving detection. However, the BPNN exhibits slow convergence speed and many adjustable parameters, while it is difficult to train large-scale samples in the SVM. In this paper, we develop extreme learning machine (ELM)-based FD detection method to avoid the above disadvantages. Further, since the randomness of the weight and biases between the input layer and the hidden layer of the ELM will influence its generalization performance, we further apply a differential evolution ELM (DE-ELM) method to the analysis of the driver’s respiration and heartbeat signals, which can effectively judge the driver fatigue state. Moreover, not only will the Doppler radar and smart bracelet be used to obtain the driver respiration and heartbeat signals, but also the sample database required for the experiment will be established through extensive signal collections. Experimental results show that the DE-ELM has a better performance on driver’s fatigue level detection than the traditional ELM and SVM.
Highlights
With the rapid development of automobile technology, car ownership has increased rapidly over the past decades
Traffic accidents caused by fatigue driving (FD) account for 20–30% of all traffic accidents, which indicates that FD is a major cause of traffic accidents [3]
Leading the degraded generalization the and weights and biases optimized level in this paper. to Further studies on determiningperformance, the fatigue level the selection of are input feature via thewill
Summary
With the rapid development of automobile technology, car ownership has increased rapidly over the past decades. Cheng et al collected the videos of 21 participants’ faces and extract many features including number of yawns, blink rate, statistics of blink duration, closing speed, reopening speed and so on, for establishing an FD assessment model [27] These methods are only applicable to the FD late stage, when the driver’s facial changes are obvious and the driving behavior changes have reached a very dangerous stage. After obtaining a large amount of data through the above methods, they need to be well processed for better determining the driver’s fatigue level. The machine learning-based implementation method is to train a large amount of driving data obtained from the laboratory and the road, which is called a data-driven algorithm [29].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
