Emotion recognition method fusing multi-modal physiological signal features and related device

By employing an end-to-end deep learning architecture for multimodal physiological signal feature recognition, this method addresses the shortcomings of traditional feature extraction and multimodal fusion, achieving highly efficient emotion recognition and improving recognition accuracy and robustness.

CN122320546APending Publication Date: 2026-07-03XI AN JIAOTONG UNIV
0 Cites 0 Cited by

Patent Information

Application Number
CN202610393699.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-27
Publication Date
2026-07-03

AI Technical Summary

Technical Problem

In emotion recognition, existing technologies struggle to capture the details of physiological waveforms and fine-grained temporal patterns using traditional time-frequency domain features. Furthermore, multimodal signal fusion neglects deep nonlinear correlations, resulting in insufficient recognition accuracy.

Method used

An end-to-end deep learning architecture is constructed, employing multi-scale perception, attention, and gating mechanisms to extract and fuse local features from ECG and pulse signals respectively, and to improve recognition accuracy through global temporal information fusion.

Benefits of technology

It significantly improves the accuracy and robustness of emotion recognition, simplifies application deployment complexity, and enhances the comprehensiveness and stability of emotion monitoring.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides an emotion recognition method fusing multi-modal physiological signal features and a related device, and the method comprises the following steps: segmenting an obtained original electrocardiosignal and an original pulse signal of a to-be-detected object, and obtaining an electrocardiosignal segment sequence and a pulse signal segment sequence; respectively carrying out feature extraction on the electrocardiosignal fragment sequence and the pulse signal fragment sequence to obtain an electrocardiosignal local feature sequence and a pulse local feature sequence; fusing the electrocardio local feature sequence and the pulse local feature sequence to obtain a fused feature sequence; performing global time sequence information fusion on the obtained fusion feature sequence to obtain a global feature sequence; obtaining an emotion recognition prediction result based on the obtained global feature sequence; according to the invention, through an end-to-end deep learning architecture, refined feature extraction and dynamic interaction fusion of multi-modal physiological signals are realized, and the accuracy and robustness of emotion recognition are effectively improved.
Need to check novelty before this filing date? Find Prior Art