Mental stress detection method and device based on transfer learning

Abstract

The invention provides a psychological stress detection method and device based on transfer learning. The method comprises the following steps: acquiring a multi-modal physiological signal of a user and preprocessing the multi-modal physiological signal; inputting the preprocessed multi-modal physiological signal of the user to a pressure detection migration model to obtain a pressure level of the user output by the pressure detection migration model; wherein the pressure detection migration model comprises a feature extractor and a pressure classifier, the pressure detection migration model is obtained by adversarial training with a domain discriminator, the feature extractor is used for extracting depth features and fusing the depth features with artificial time-frequency domain features, and the pressure classifier is used for classifying pressure levels of a user; the domain discriminator is used for discriminating whether the sample data belongs to a source domain or a target domain. According to the method, pressure detection knowledge suitable for large-scale crowds is migrated to at least quantity of target group pressure detection tasks, and a more convenient and accurate solution is provided for establishing personalized models of different groups.

Description

technical field [0001] The invention relates to the technical field of information processing, in particular to a method and device for detecting psychological stress based on transfer learning. Background technique [0002] Stress monitoring is one of the key links in healthcare. Stress affects people's cognitive behavior and decision-making, and has a significant impact on people's work efficiency. Long-term excessive stress and negative emotions may even cause harm to people's physical and mental health. In particular, some special occupational groups (such as policemen, doctors, drivers, etc.) are vulnerable to acute stress stimuli in the working environment, and monitoring their reaction to stress stimuli is conducive to ensuring their physical and mental health and work safety. Physiological signals commonly used for stress detection include Electrodermal Activity (EDA), Photoplethysmography (PPG), Skin Temperature (Skin Temperature, ST), respiration, and Electroencep...

AI Technical Summary

Problems solved by technology

[0006] The present invention provides a psychological stress detection method and device based on transfer learning, which is used to solve the problem of pressure detection deviation caused by ignoring the difference between the model training group and the target group to be tested in the prior art and not combining the two characteristics for analysis larger defect

Images