Electroencephalogram emotion recognition method based on parallel sequence channel mapping network

An emotion recognition and network technology, applied in the field of EEG emotion recognition, can solve problems such as insufficient spatiotemporal information and low efficiency

Active Publication Date: 2021-02-19
TIANJIN UNIV
View PDF12 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention provides an EEG emotion recognition method based on Parallel Sequence-ChannelProjection Convolutional Neural Network (PSCP-Net), and the present invention effectively solves the problems of insufficient spatiotemporal information and low efficiency in the process of feature extraction , see the description below:

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
  • Electroencephalogram emotion recognition method based on parallel sequence channel mapping network
  • Electroencephalogram emotion recognition method based on parallel sequence channel mapping network
  • Electroencephalogram emotion recognition method based on parallel sequence channel mapping network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] Embodiments of the present invention provide a method for EEG emotion recognition based on a parallel sequence channel mapping network, such as figure 1 As shown, the method includes the following steps:

[0031] 101: Preprocessing

[0032] The sampling frequency was reduced from 512Hz to 128Hz, and EOG artifacts were removed with ICA (Independent Component Analysis). Use a 4.0-45.0Hz band-pass filter to filter out noise. The preprocessed EEG data for each subject consisted of 40 trials with corresponding labels. Each trial contained 60 s of the emotional signal and 3 s of the pre-trial baseline signal.

[0033] 102: Baseline filtering

[0034] The embodiment of the present invention provides a baseline filter, which can filter out the baseline signal with relatively severe fluctuations, and retain the stable baseline signal for baseline removal (use the emotion signal to subtract the baseline signal to obtain a difference signal, and use it as network input) .

...

Embodiment 2

[0045] The scheme in embodiment 1 is further introduced below in conjunction with specific calculation formulas and examples, see the following description for details:

[0046] 201: Baseline filtering

[0047] Baselining the data can help the network to fit better. The DEAP database (well known to those skilled in the art, which will not be described in detail in the embodiment of the present invention) each trial contains a 3-second baseline signal, a 60-second emotional signal, and 32 EEG channels. The model takes the difference signal between the emotion signal and the baseline signal instead of the emotion signal as input. In order to amplify this difference, a baseline noise filter is designed to remove the volatile baseline signal. The specific working principle is as follows:

[0048] First, take the 3-second baseline signal from the first EEG channel and convert it into a key-value pair (Key, Value). Key is used to record the initial sequence of sampling points, and...

Embodiment 3

[0087] Below in conjunction with concrete experiment, the scheme in embodiment 1 and 2 is carried out feasibility verification, see the following description for details:

[0088] In this experiment, EEG data from the DEAP dataset were used for analysis. The DEAP dataset consists of data from 32 healthy participants (50% female) with an average age of 26.9 years. Each subject watched 40 60-second music videos. At the end of each video, a self-assessment of the degree of valence, arousal, dominance and liking is given on a continuous scale between 1 and 9. This experiment only uses the data of valence and arousal. Each video contained 60 s of the emotional signal and 3 s of the pre-trial baseline signal. Set 5 as the threshold and classify the videos into 2 categories according to the scores. The task is then transformed into two binary classification problems, high / low valence and high / low arousal.

[0089] As shown in Table 1, the average accuracy of this method on valen...

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 electroencephalogram emotion recognition method based on a parallel sequence channel mapping network, and the method comprises the following steps: downsampling EEG data ofa subject, removing EOG artifacts and noises, and obtaining a baseline signal and an emotion signal after preprocessing; constructing a baseline filter for screening a stable baseline signal from thebaseline signals, and subtracting the stable baseline signal from the emotion signal to obtain a difference signal as an input sample of the network; randomly selecting samples of the same emotion ineach training batch by adopting an online data enhancement mode, and randomly exchanging data on uncertain number of corresponding channels; constructing an electroencephalogram emotion recognition network composed of a time flow sub-network, a space flow sub-network and a fusion classification block; and extracting human electroencephalogram features according to the electroencephalogram emotionrecognition network, wherein the electroencephalogram features comprise time and space features. The problems of insufficient space-time information and low efficiency in the feature extraction process are effectively solved.

Description

technical field [0001] The invention relates to the field of EEG emotion recognition, in particular to an EEG emotion recognition method based on a parallel sequence channel mapping network. Background technique [0002] With the in-depth development of computer science, more and more scholars are investing in the field of emotion research, trying to make computers recognize emotions like humans. Previous sentiment analysis has mainly focused on facial expressions and spoken dialogue. However, both facial expressions and conversational communication can be controlled by humans subjectively. In order to obtain accurate real-time emotions of the subject, physiological signals play an important role. Physiological signals such as electroencephalogram (EEG), electrooculogram (EOG), and electrocardiogram (ECG) are spontaneously generated by the human body and have strong unforgeability. Therefore, physiological signals are more objective and reliable in capturing the true emoti...

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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F2218/08G06F2218/12G06F18/2415G06F18/25
Inventor 沈丽丽赵伟侯春萍
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap