Journal
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
Volume 71, Issue -, Pages -Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIM.2022.3214265
Keywords
Electrocardiography; Fatigue; Vehicles; Wheels; Generators; Electrodes; Heart rate variability; Driving fatigue; electrocardiography (ECG); RR intervals; Generative adversarial network (GAN); fuzzy convolution neural network (FCNN)
Funding
- Key-Area Research and Development Program of Guangdong Province [2020B010166006]
- National Natural Science Foundation of China [6217022520, 61973126, 61863028, 81660299, 61503177]
- Innovation Team of the Modern Agriculture Industry Technology System in Guangdong Province [2019KJ139]
- Chinese Institute of Electronics (CIE)-Tencent Robotics X Rhino-Bird Focused Research Program
Ask authors/readers for more resources
Driving fatigue is a significant factor in traffic accidents. Researchers have proposed a non-interference fatigue detection system that utilizes an electrocardiogram (ECG) acquisition device embedded in the steering wheel. By collecting the driver's ECG signals through their palm, the system can analyze tiredness after preprocessing. The system consists of a simulation generation module based on a cycle-generative adversarial network (CycleGAN) and a fatigue detection module based on a fuzzy convolution neural network (FCNN). Experimental results demonstrate the stability and accuracy of the proposed fatigue detection model.
Driving fatigue is an important factor leading to traffic accidents. For this reason, we propose a non-interference fatigue detection system, which consists of a steering wheel embedded with an electrocardiogram (ECG) acquisition device and an ECG fatigue detection model. By holding the steering wheel with the driver's palm, the system can collect their ECG signals and transmit them to the fatigue detection model for tiredness analysis after preprocessing. In particular, the proposed ECG fatigue detection model is composed of a simulation generation module based on a cycle-generative adversarial network (CycleGAN) and a fatigue detection module based on a fuzzy convolution neural network (FCNN). The acquired palm signal is fed into the simulation generation module to generate a clearer chest-like signal, thereby improving the final task performance. In addition, a new FCNN is posed to analyze the simulated chest signal to focus on the time variation and ignore the specificity of the ECG signal, therefore increasing the robustness of the system. The experimental results show that the proposed fatigue detection model has good stability and accuracy.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available