Fatigue Detection Based on Multimodal Fusion Neural Network

It has been proved to be an effective method to judge whether the driver is in a state of fatigue based on the change of EEG characteristics. However, the accuracy of fatigue detection of EEG signals using traditional machine learning methods alone is still low. Therefore, a neural network method based on multimodal fusion of EEG and prefrontal electrooculogram is proposed, and the training is conducted by using SEED-VIG, a public data set of Shanghai Jiaotong University. The experimental results show that multimodal fusion has a better recognition effect for fatigue detection than single mode, and its accuracy rate reaches 98.3%, which is helpful to promote the application of fatigue detection system based on EEG in driver's driving process.