Depth neural network multi-source data fusion method using micro-expression multi-input information

Abstract

The invention discloses a depth neural network multi-source data fusion method using micro-expression multi-input information. A deep neural network learning architecture combining micro-expression and multi-input information is used to reconstruct the characteristic weights of a specific affective analysis model through unsupervised greedy layer-by-layer training method for multi-source data in front of affective computation, and then the values are transferred to the hidden layer to reconstruct the original input data. In order to obtain the true expression of emotional characteristics, thebidirectional data layer and the hidden layer are iterated many times. Through the top-level data eigenvector fusion, high-precision heterogeneous multi-dimensional data fusion target information is formed. The invention provides a sparse coding based on the SAE structure, which reduces the dimension of the high-dimensional physiological feature vector through the bottom-up sparse coding theory, so that fewer over-complete physiological feature data base vectors can accurately represent the original high-dimensional feature.

Description

technical field [0001] The invention belongs to the field of emotional calculation and judgment, and in particular relates to a deep neural network multi-source data fusion method combining micro-expression multi-input information. Background technique [0002] In the current affective computing, methods such as data feature extraction, classification, and regression can be used as a single sensor recognition cognition, or a shallow structure. Its limitation is that the ability to recognize target features is limited in the case of limited sensor units. For complex target recognition And the generalization ability of classification problems is subject to certain restrictions. Contents of the invention [0003] In order to overcome the shortcomings of the above-mentioned prior art, the present invention provides a deep neural network multi-source data fusion method that combines micro-expression and multi-input information. [0004] The technical scheme adopted in the pres...

AI Technical Summary

Problems solved by technology

[0002] In the current affective computing, methods such as data feature extraction, classification, and regression can be used as a single sensor recognition cognition, or a shallow structure. Its limitation is that the ability to recognize target features is limited in the case of limited sensor units. For complex target recognition And the generalization ability of the classification problem is subject to certain constraints

Images