Study On Fatigue Detection Based On Wearable Electrocardiograph

Mental fatigue is a key cause of many chronic diseases,but it’s difficult to measure and quantify.This paper proposed a promising method to detect mental fatigue state with smart wearable ECG device and explained the internal cause of diligent brain workers’ mental fatigue.In order to explore the relationship between heart rate variability(HRV)and mental fatigue,this paper designed a mental fatigue experiment and extracted 9 HRV indicators from ECG data.First,the Mann Whitney U test was used to analyze the significance of HRV indicators,and then Random Forest methods were used in the importance evaluation of HRV indicators.Therefore,six indicators,namely,the NN.mean,PNN50,rMSSD,TP,LF and VLF were important for mental fatigue detection.In the HRV-based mental fatigue detection,four machine learning algorithms were used to build classifiers that automatically detected the fatigue state.The best performance was achieved by KNN,which had a CV accuracy of 75.5% under the HRV combination of NN.mean,TP and LF.In the empirical study of the cause of mental fatigue,this paper proposed a theoretical model of negative emotions as a mediator to adjust the occupational delay satisfaction-mental fatigue effect,and used the stepwise regression,ANOVA analysis to verify the model.The result shows that the occupational delay satisfaction(ODS)of mental workers has a significant positive impact on mental fatigue;the negative emotions of work have a partial mediating effect on ODS and mental fatigue;exercise is a reverse moderator between negative emotions and mental fatigue.