Unlock instant, AI-driven research and patent intelligence for your innovation.

EEG analysis method for depression based on sparse low-rank tensor decomposition

A technology of tensor decomposition and analysis method, applied in the field of intelligent pattern recognition, to achieve the effect of ensuring generalization ability and improving decomposition efficiency

Active Publication Date: 2022-04-08
HANGZHOU DIANZI UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, there are few literatures on ERP analysis of patients with depression based on tensor, which needs further research and analysis

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
  • EEG analysis method for depression based on sparse low-rank tensor decomposition
  • EEG analysis method for depression based on sparse low-rank tensor decomposition
  • EEG analysis method for depression based on sparse low-rank tensor decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] In order to analyze the ERP components of depression patients more objectively and comprehensively, the present invention mainly improves the ERP analysis method. The present invention uses tensor as the basic data structure to store ERP data. Making full use of the low-rank and sparse characteristics of ERP tensor, SLraTucker decomposition is proposed to decompose ERP tensor to extract multi-domain features of ERP tensor, and use Support Vector Machine (SVM) to identify depression ERP Samples, observe the comparison of the static active brain regions of the two groups of people under different emotional stimuli; figure 2 shown; Finally, the dynamic ERP components were extracted by adding a sliding time window, and the differences in the active brain regions of the two groups of people after being emotionally stimulated were dynamically analyzed.

[0045] The specific flow chart of the EEG analysis method for depression based on tensor decomposition is as follows: fi...

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 an EEG analysis method for depression based on sparse low-rank tensor decomposition. The specific steps are as follows: firstly, the complex Morlet wavelet transform is used to extract the time-frequency features of the EEG signal, and it is constructed into a sample tensor according to the order of the channels; secondly, according to the low-rank and sparse characteristics of the sample tensor, SLraTucker is proposed to decompose and extract the sample tensor The multi-domain features are used to classify and identify two groups of people with depression (MDDs) and healthy controls (HCs). In order to further study the similarities and differences between the active brain regions of the two groups of people when they receive different emotional stimuli, the present invention analyzes the differences between the static and dynamic active brain regions of the two groups of people. The SLraTucker decomposition method proposed in this experiment can effectively extract multi-domain features in EEG signals, and accurately and objectively diagnose and analyze depression, so that patients or doctors can better understand the condition and timely treat or prevent it.

Description

technical field [0001] The invention relates to an analysis method for depression EEG signals by using low-rank sparse tensor decomposition, especially for analyzing static and dynamic active brain regions under different emotional stimuli based on EEG signals of depression patients, which belongs to the intelligent mode Identify technical areas. Background technique [0002] Major Depressive Disorder (MDD) is a serious emotional and psychological disorder mental illness. In the past two years, the reported incidence of depression has been increasing year by year, and the age of onset is also tending to be younger. EEG signals contain important information about brain activity, and the research on the active brain regions of MDD patients and the objective diagnosis of depression based on EEG signals have been confirmed to be effective and feasible. [0003] Electroencephalogram (Electroencephalogram, EEG) is a neurophysiological signal collected in a non-invasive way. In th...

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): A61B5/369A61B5/372A61B5/378A61B5/00
CPCA61B5/369A61B5/372A61B5/7203A61B5/725A61B5/7235A61B5/7253A61B5/378
Inventor 高云园黄金诚张卷卷金可滢何韦聪
Owner HANGZHOU DIANZI UNIV