Using facial and Electroencephalogram(EEG)features to identify the driver's fatigue state and provide fatigue reminders can effectively reduce the probability of accidents.To solve the problem of low recognition accuracy of single facial features or EEG features,a fatigue recognition method based on the fusion of EEG and facial features is proposed.Firstly,the time-domain,frequency-domain,nonlinear features and facial features of the EEG signal are extracted,and feature splicing is performed through feature layer information fusion.To improve the speed of facial feature recognition,an improved YOLOv5_mobilenet model is proposed.On this basis,the accuracy of the fused features after splicing is detected through six major machine learning models,and accuracy,F1_score,precision,and recall are selected for analysis and evaluation.The proposed method is validated using a publicly available dataset,and the results show that the improved YOLOv5_mobilenet model outperforms existing models in all feature performances.The evaluation results of different machine learning models show that recognition with fused features performs better than single fatigue feature recognition.Therefore,it is feasible to use fused features based on EEG and facial feature splicing for driving fatigue recognition.
关键词
脑电信号特征/面部图像特征/特征融合/疲劳识别/机器学习
Key words
EEG signal features/facial image features/feature fusion/fatigue recognition/machine learning
维普
万方数据