Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Computer classification polygraph recognition method based on fmri small world brain network

A recognition method and brain network technology, applied in the field of computer classification and polygraph recognition based on fMRI small-world brain network, achieves the effect of low calculation cost and good generalization performance

Active Publication Date: 2022-05-03
SICHUAN UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although functional magnetic resonance imaging studies of brain functional networks have only appeared in recent years, most studies of brain network characteristics cannot be directly used as brain imaging classifications of lying

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
  • Computer classification polygraph recognition method based on fmri small world brain network
  • Computer classification polygraph recognition method based on fmri small world brain network
  • Computer classification polygraph recognition method based on fmri small world brain network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] Embodiment 1: see figure 1 , a kind of computer classification polygraph recognition method based on fMRI small-world brain network, comprises the following steps:

[0056] (1) Obtain the functional magnetic resonance image data of the subject;

[0057] (11) Select N subjects, among which N1 subjects are used as training samples, and N2 subjects are used as test samples, and N=N1+N2, N1>>N2;

[0058] (12) Collect the fMRI images of N1 training samples under the lying and honest cognitive experiments, and perform preprocessing to obtain the preprocessed fMRI images, and the fMRI images are accompanied by labels corresponding to lying and honesty category;

[0059] (13) For N2 samples to be tested, collect fMRI images of their brains, and perform preprocessing to obtain preprocessed fMRI images;

[0060] (2) Construct the subject's binary matrix;

[0061] For each subject, the preprocessed fMRI images were mapped to the 90 brain regions of the anatomically automatical...

Embodiment 2

[0074] Example 2, see figure 1 , this embodiment is further supplemented on the basis of embodiment 1.

[0075] In the step (1), the preprocessing is: perform temporal layer correction; perform head movement correction to remove motion artifacts; standardize the functional image to the EPI template that comes with SPM, and use the half-maximum width FWHM of 8mm to perform spatial smoothing on the data , and finally use a high-pass filter with a cutoff frequency of 1 / 128Hz to filter out the low-frequency noise of the signal.

[0076] The step (2) threshold range meets the following conditions:

[0077] First, call the corrcoef function in MATLAB to complete the calculation of the Pearson correlation coefficient. The minimum value of the threshold range can keep the corresponding Pearson correlation coefficient calculated by the corrcoef function with a significant p<0.05, and exclude the corresponding ones that are not significant Pearson correlation coefficient;

[0078] Se...

Embodiment 3

[0092] Embodiment 3: see figure 1 , Fig. 2, in order to verify the classification accuracy rate of a computerized polygraph recognition method based on fMRI small-world brain network mentioned in the present invention, we analyzed the fMRI images of 36 subjects with known category labels and The method was tested using leave-one-out cross-validation. The leave-one-out approach is based on a single measurement technique architecture (see figure 1 ) as the core but involves multiple measurements in a cycle, the description of the operation process is as follows:

[0093] (1) Preprocess the fMRI images of the subject: perform time layer correction; perform head movement correction to remove motion artifacts; normalize the functional image to the EPI template that comes with SPM, and use 8mm half-maximum width FWHM to process the data Spatial smoothing, and finally a high-pass filter with a cutoff frequency of 1 / 128Hz is used to filter out the low-frequency noise of the signal t...

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 computerized polygraph recognition method based on the fMRI small-world brain network. The method first obtains the preprocessed fMRI image of the subject, then constructs the binary matrix of the subject, and then constructs the binary matrix For the corresponding small-world brain function network, use the singular value decomposition feature mapping method to extract the features of the small-world brain function network to obtain feature data, and then send the feature data of the subjects as training samples to the least squares support vector machine Perform training to obtain the trained classifier; finally use the trained classifier to classify and identify the feature data of the sample to be tested. The method of the present invention proposes a method for extracting characteristic data from the small world brain network by using the singular value decomposition feature map, and using it to train the least square support vector machine classifier. It abandons the data feature types used by the existing classifiers in the past and optimizes It is a new attempt to use this method to realize polygraph recognition.

Description

technical field [0001] The invention relates to a polygraph detection method, in particular to a fMRI small-world brain network computer classification polygraph recognition method. Background technique [0002] Cheating / lying is an interesting linguistic, psychological and social behavior of humans. Identifying the hallmarks of deception using neuroimaging techniques is crucial to reveal the complex cognitive mechanisms underlying lies. Advances in noninvasive measurement of brain activity to date have shown potential in probing brain networks to reveal neuropsychiatric diseases and disorders. In particular fMRI, including resting state fMRI, has been an ideal candidate for the study of different cognitive brain networks. Also, functional connectivity analysis of the brain using fMRI data has been described using a variety of techniques and approaches. Although functional magnetic resonance imaging studies of brain functional networks have only appeared in recent years, ...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06V10/774G06V10/764G06K9/62
CPCG06V2201/03G06F18/24G06F18/214
Inventor 张江陈华富
Owner SICHUAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com