摘要

Anxiety is a kind of extremely negative emotion, and long-term anxiety is the cause of many serious physical and mental diseases. In daily life, real-time and accurate detection of anxiety state is conducive to block the physical and mental hazards of anxiety timely. Anxiety detection based on autonomic nervous patterns has achieved high-detection precision in certain scenes. However, motion interferes with anxiety detection in arbitrary scenes of daily life, leading to the false report of anxiety. This paper designed four different intensities of motions to analyze the autonomic nervous activity of typical motion states, found out the motion states with similar autonomic nervous patterns to the anxiety status, and identified the motion interference that would cause false detection of anxiety state. A multi-modal real-time anxiety detection system was built in this paper. The ability of the above system to detect motion interference and exclude false anxiety status was validated both in the laboratory and in real life scenarios.