A fatigue detection method based on multi-information fusion

Abstract

The invention discloses a fatigue detection method on the basis of multi-information fusion. Physiological monitoring indexes including respiratory rates, finger electric conductivity and finger temperatures are imported, and fatigue states can be classified by means of sample entropy estimation by the aid of LS-SVM (least square-support vector machines) after four physiological features are extracted. The fatigue detection method has the advantages that the diversified physiological indexes including heart rates, skin electric conductivity, skin temperatures and the respiratory rates are usedas features, and accordingly the fatigue detection accuracy can be improved; LS-SVM classifiers with high classification speeds are used, accordingly, quick classification ability effects can be guaranteed, and the classification accuracy and speediness are important fatigue detection indexes.

Description

technical field [0001] The invention belongs to the technical field of intelligent detection, and in particular relates to a fatigue detection method based on multi-information fusion. Background technique [0002] Mental fatigue is a sub-health state. With the increase of working time and intensity, workers will feel distracted and work efficiency will decrease. For some occupations such as drivers or operators, it may even cause fatal injuries. Consequences, so fatigue detection has been a hot research direction. [0003] Fatigue detection can be divided into two types: subjective evaluation and objective evaluation. The subjective method is mainly through questionnaires and self-evaluation scales, which have delays and inaccuracies, while the objective method is mainly based on data such as physiological signals and behavioral expression characteristics. Assess the state of fatigue, in which physiological signals mainly include electrocardiogram (ECG), electroencephalogr...

AI Technical Summary

Problems solved by technology

EEG has the problem of inconvenient wearing of sensors, and the measured data are easily affected by myoelectricity and oculoelectricity. Heart rate variability (HRV) is a method to measure the degree of continuous heart rate change. It was found that there is a strong correlation with mental fatigue. At the same time, finger temperature and finger conductivity can reflect the degree of tension of the worker, and the breathing rate will also change with the increase of the pressure of the tested person

Images