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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


