FNIRS emotion recognition method and system based on graph network and adaptive denoising
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
An emotion recognition and adaptive technology, applied in the field of human-machine signal recognition, can solve the problems of low temporal or spatial resolution, high cost of acquisition equipment, and susceptibility to interference, etc., achieve strong generalization ability, avoid manual participation and experience analysis , to overcome the effect of limited dimensions
Pending Publication Date: 2022-03-22
SOUTH CHINA UNIV OF TECH
View PDF10 Cites 1 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
At the same time, the limitations of this method are gradually revealed, such as: low temporal or spatial resolution, high cost of acquisition equipment, susceptible to interference, inconvenient to carry, etc.
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0072] A fNIRS emotion recognition method based on a graph network and adaptive denoising, suitable for the emotion recognition task of an fNIRS acquisition device, mainly includes an external emotion stimulation step, an fNIRS acquisition step, an fNIRS adaptive denoising step, and an fNIRS emotion recognition step.
[0073] In the external emotional stimulation step, the external emotional stimulation material adopts videos of six emotional label types of anger, disgust, fear, happiness, sadness, and surprise, and the user induces emotions by watching the video.
[0074] Such as Figure 4 As shown in the fNIRS acquisition steps, the fNIRS acquisition device consists of a multi-channel dual-wavelength near-infrared continuous wave transmitting-receiving source.
[0075] First, the user wears the fNIRS acquisition device to collect and record the changes in light intensity of different optodes before and after emission-reception in real time.
[0076] Let the single-channel l...
Embodiment 2
[0098] A fNIRS emotion recognition system based on graph network and adaptive denoising, including:
[0099] fNIRS acquisition module: use fNIRS acquisition equipment to continuously collect the change of light intensity before and after emission-reception, convert the change of light intensity into the change of absorbance, and further obtain the relative change of oxygenated hemoglobin and deoxygenated hemoglobin concentration;
[0100] fNIRS adaptive denoising network module: used to obtain pure signals;
[0101] fNIRS Dynamic Graph Attention Emotion Recognition Network Module: Output emotion labels based on pure signals.
Embodiment 3
[0103] A computer device includes a memory, a processor, and a computer program stored on the memory and operable on the processor, and the processor implements the steps of the fNIRS emotion recognition method when executing the computer program.
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
Login to view more
Abstract
The invention discloses an fNIRS emotion recognition method and system based on a graph network and adaptive denoising, and the method comprises the steps: enabling fNIRS collection equipment to continuously collect the variable quantity of light intensity before and after transmitting-receiving, converting the variable quantity of the light intensity into the change of absorbance, and further obtaining the relative variable quantity of the concentration of oxyhemoglobin and the concentration of deoxidized hemoglobin; de-noising is carried out through a self-adaptive de-noising network model to obtain a pure signal, an input signal of the self-adaptive de-noising network model is the relative variation of the concentration of the oxyhemoglobin and the concentration of the deoxidized hemoglobin obtained in the previous step, and an output signal of the self-adaptive de-noising network model is the relative variation data of the concentration of the pure oxyhemoglobin and the concentration of the deoxidized hemoglobin; mapping of graph nodes is carried out in combination with probe and channel characteristics, brain topology restoration is carried out by using a graph network, and emotion tags are output in a classified manner through a dynamic graph attention emotion recognition network model. The problems that a brain-computer interface is complex to wear, difficult to operate and the like in practical application at present are solved.
Description
technical field [0001] The invention relates to the field of human-machine signal recognition, in particular to a fNIRS emotion recognition method and system based on graph network and adaptive denoising. Background technique [0002] Emotion affects people's cognitive and behavioral activities, and is also an important factor affecting mental health. Emotion recognition, as a research hotspot, can be divided into non-physiological signals and physiological signals. As traditional physiological index detection methods, EEG, EEG and functional magnetic resonance have made some progress in emotion recognition. At the same time, the limitations of such methods are gradually revealed, such as: low temporal or spatial resolution, high cost of acquisition equipment, susceptible to interference, and inconvenient to carry. [0003] In recent years, with the development of near-infrared technology and the upgrading of acquisition equipment, Functional Near-Infrared Spectroscopy (fN...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more