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

A deep neural network, multi-source data technology, applied in the field of affective computing judgment, can solve the problems of single sensor recognition and cognition, generalization ability restriction, limited target feature recognition ability, etc., to achieve easy classification or prediction, and fast information processing speed. , the effect of improving the accuracy

Inactive Publication Date: 2019-01-11
SHENYANG CONTAIN ELECTRONICS SCI & TECH CO LTD
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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 t...

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Depth neural network multi-source data fusion method using micro-expression multi-input information
  • Depth neural network multi-source data fusion method using micro-expression multi-input information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The following is attached with the manual figure 1 , 2 The present invention is further described in detail.

[0019] A deep neural network multi-source data fusion method that combines micro-expression and multi-input information, comprising the following steps:

[0020] 1) The deep learning architecture based on the DBM network uses the Bayesian belief network DBM near the underlying mass data, that is, the directed graph model, there is no link between nodes in the layer, and the restricted Boltzmann machine DBN is used in the farthest part , by combining DBM and DBN, increasing the number of hidden layers to obtain DBM; DBM is a probabilistic generative model, and the generative model is to establish a joint distribution between massive data and features; the bottom layer of DBM is composed of multiple DBN layers; these networks Is "restricted" to a data layer and a hidden layer, there is a connection between the layers, but there is no connection between the unit...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/00G06K9/62G06N3/04
CPCG06V40/10G06N3/045G06F18/253
Inventor 关庆阳童心毕连城靳跃苏展锋周国林鞠明刚
Owner SHENYANG CONTAIN ELECTRONICS SCI & TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap