Emotion recognition system and method based on breathing components in pulse signals

Abstract

The invention discloses an emotion recognition system and method based on breathing components in pulse signals. The emotion recognition method comprises the following steps that the pulse signals ofa human body are obtained based on simple and convenient modes such as photoelectric sensing; ensemble empirical mode decomposition is performed on the acquired pulse signals, and an obtained intrinsic mode function is reconstructed to extract respiration signals; feature screening is performed on time domain features, frequency domain features and entropy features extracted from the respiration signals by adopting significant differences, and weights are distributed to screened features by adopting a random forest Gini index to construct a feature subset; and the feature subset is input intoa pre-trained random forest classifier, and an emotion recognition result is output. The emotion classification precision and accuracy are effectively improved, the recognition result is output to a terminal device, early warning is conducted on a negative emotion, and therefore remote emotion monitoring is achieved.

Description

technical field [0001] The invention relates to the technical field of signal recognition, in particular to an emotion recognition system and method based on breathing components in pulse signals. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Emotion refers to the psychological and physiological state produced by different feelings, thoughts and behaviors, and is a general term for a variety of subjective cognitive experiences. The continuous development of today's social economy has made social competition increasingly fierce and the pace of life has accelerated. More and more people are in a state of tension for a long time, under great mental pressure, and even suffer from anxiety, depression, mania, etc. mental illness. Emotions also have a certain impact on the physical health of the human body, especially on the cardiopulmonary f...

AI Technical Summary

Problems solved by technology

However, the acquisition of respiratory signals is more cumbersome than the acquisition of pulse signals. In clinical applications, the acquisition of respiratory signals mostly uses professional detection devices and sensing technologies, or obtains the respiratory information of subjects through thoracic movement and other methods.

Due to the complexity of traditional breathing detection devices, real-time emotional monitoring directly based on breathing signals, especially remote monitoring operated by non-professionals, has become difficult to achieve

Images