Mental workload detection method and device

Abstract

An embodiment of the present invention provides a mental load detection method and device, the method comprising: acquiring physiological signals of the subject to be measured; inputting the physiological signals into a preset temporal convolutional network model, and according to the temporal convolutional network model The output result is to obtain the mental load type of the subject to be tested; wherein, the physiological signal includes an EEG signal, and the temporal convolutional network model is obtained after training according to the physiological signal sample with the mental load type label. Since the physiological signal is input to the preset temporal convolutional network model, the preset temporal convolutional network model is obtained after training based on physiological signal samples with mental load type, and can output the recognition result of mental load type, so the detection process is fast It is accurate, has less calculation consumption, and can automatically remove redundant information by using the temporal convolutional network model.

Description

technical field [0001] The invention relates to the field of mental load identification, in particular to a mental load detection method and device. Background technique [0002] In the past ten years, mental workload detection has gradually become a research hotspot in academia and industry. Moderate mental load can improve work efficiency, while excessive mental load can affect human health and cause major safety accidents. Therefore, the detection of mental load is crucial to mental health. [0003] The traditional mental load test requires the subject to fill in the scale, which is too subjective and relies on the honesty of the subject. The mental load recognition method based on physiological signal measurement is of great significance. The current physiological signal fusion mental load detection method mainly includes the following steps: artificially define the characteristics of different physiological signals; use feature engineering to realize information fusio...

AI Technical Summary

Problems solved by technology

[0004] The effect of the current mental load detection method based on physiological signals depends entirely on the effectiveness of artificially defined features, and manually defined features cannot consider redundant information between different physiological signals, so the accuracy of the above method is poor

Images