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

Emotional recognition feature extracting method based on electroencephalogram signal of dual-tree complex wavelet

A dual-tree complex wavelet and EEG signal technology, applied in medical science, sensors, diagnostic recording/measurement, etc., can solve problems such as deliberate camouflage, reduce individual differences, overcome poor anti-aliasing, and better classification and recognition The effect of the result

Inactive Publication Date: 2017-12-01
NANJING UNIV OF POSTS & TELECOMM
View PDF12 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although these characteristics are obvious and easy to obtain, they can be deliberately camouflaged

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
  • Emotional recognition feature extracting method based on electroencephalogram signal of dual-tree complex wavelet
  • Emotional recognition feature extracting method based on electroencephalogram signal of dual-tree complex wavelet
  • Emotional recognition feature extracting method based on electroencephalogram signal of dual-tree complex wavelet

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in detail, and concrete implementation is as follows:

[0053] figure 1 The flow chart of EEG feature extraction mainly includes the following steps:

[0054] (1) Use dual-tree complex wavelet transform to decompose the preprocessed signal into different frequency bands, and extract useful signals for reconstruction.

[0055] (2) Using phase information and sample entropy to extract features of reconstructed signals in different frequency bands.

[0056] (3) Input the extracted features into the support vector machine to identify different emotions.

[0057] The detailed description of each step is as follows:

[0058] Step 1, decompose and reconstruct the signal by dual-tree complex wavelet

[0059] In order to realize the dual-tree complex wavelet transform, the Q-Shift dual-tree filter proposed by Kingsbury is adopted, which is a cluster of orthogonal discrete fil...

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 emotional recognition research method based on an electroencephalogram signal of dual-tree complex wavelet. Decomposition and reconstitution of dual-tree complex wavelet transform are adopted to calculate phase information and sample entropy value of different wavebands of the electroencephalogram signal, and the two features serve as feature vectors of different emotions to be input into an SVM classifier, so that three emotions of calmness, pleasure and sadness are recognized effectively. The results show that the defect that discrete wavelet transform is poor in aliasing resistance and high in translation sensitivity is overcome through dual-tree complex wavelet transform, the extracted feature vectors has a good classifying recognition result, and new thoughts are provided for later researching of emotional recognition of the electroencephalogram signal.

Description

technical field [0001] The invention belongs to the field of electroencephalogram signal processing, and relates to an electroencephalogram signal feature extraction method of dual-tree complex wavelet transform. In particular, it relates to a research method for emotion recognition based on EEG signals. Background technique [0002] Emotions are physical and mental states that result from a combination of feelings, thoughts, and behaviors. The quality of emotions affects human behaviors such as learning, memory and decision-making to varying degrees. In daily life, emotions affect our lives all the time. Studies have shown that long-term negative emotions will lead to low work efficiency, lack of passion in life, and what's more, it will affect people's physiological functions and reduce the body's immunity. With such a high pressure of life in today's society, it is very necessary to intervene appropriately when negative emotions are found. On the one hand, artificial ...

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): A61B5/0476
CPCA61B5/7225A61B5/725A61B5/7264A61B5/369
Inventor 徐欣汤明宏
Owner NANJING UNIV OF POSTS & TELECOMM
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