Positive and Negative Emotion Classification Based on Multi-channel

Fangfang Long; Shanguang Zhao; Xin Wei; Siew Cheok Ng; Xiaoli Ni; Aiping Chi; Peng Fang; Weigang Zeng; Bokun Wei

doi:10.3389/fnbeh.2021.720451

Positive and Negative Emotion Classification Based on Multi-channel

Fangfang Long
, Shanguang Zhao
, Xin Wei
, Siew Cheok Ng
, Xiaoli Ni
, Aiping Chi
, Peng Fang
, Weigang Zeng
, Bokun Wei

School of Humanities and Social Science

Research output: Contribution to journal › Article › peer-review

9 Scopus citations

Abstract

The EEG features of different emotions were extracted based on multi-channel and forehead channels in this study. The EEG signals of 26 subjects were collected by the emotional video evoked method. The results show that the energy ratio and differential entropy of the frequency band can be used to classify positive and negative emotions effectively, and the best effect can be achieved by using an SVM classifier. When only the forehead and forehead signals are used, the highest classification accuracy can reach 66%. When the data of all channels are used, the highest accuracy of the model can reach 82%. After channel selection, the best model of this study can be obtained. The accuracy is more than 86%.

Original language	English
Article number	720451
Journal	Frontiers in Behavioral Neuroscience
Volume	15
DOIs	https://doi.org/10.3389/fnbeh.2021.720451
State	Published - 26 Aug 2021

Keywords

EEG
back propagation neural network
decision tree
emotion classification
k-nearest neighbor
support vector machine

Access to Document

10.3389/fnbeh.2021.720451

Cite this

@article{3d5f24e611d547f6a8a26d462dfabf9f,

title = "Positive and Negative Emotion Classification Based on Multi-channel",

abstract = "The EEG features of different emotions were extracted based on multi-channel and forehead channels in this study. The EEG signals of 26 subjects were collected by the emotional video evoked method. The results show that the energy ratio and differential entropy of the frequency band can be used to classify positive and negative emotions effectively, and the best effect can be achieved by using an SVM classifier. When only the forehead and forehead signals are used, the highest classification accuracy can reach 66\%. When the data of all channels are used, the highest accuracy of the model can reach 82\%. After channel selection, the best model of this study can be obtained. The accuracy is more than 86\%.",

keywords = "EEG, back propagation neural network, decision tree, emotion classification, k-nearest neighbor, support vector machine",

author = "Fangfang Long and Shanguang Zhao and Xin Wei and Ng, \{Siew Cheok\} and Xiaoli Ni and Aiping Chi and Peng Fang and Weigang Zeng and Bokun Wei",

note = "Publisher Copyright: {\textcopyright} Copyright {\textcopyright} 2021 Long, Zhao, Wei, Ng, Ni, Chi, Fang, Zeng and Wei.",

year = "2021",

month = aug,

day = "26",

doi = "10.3389/fnbeh.2021.720451",

language = "英语",

volume = "15",

journal = "Frontiers in Behavioral Neuroscience",

issn = "1662-5153",

publisher = "Frontiers Media SA",

}

TY - JOUR

T1 - Positive and Negative Emotion Classification Based on Multi-channel

AU - Long, Fangfang

AU - Zhao, Shanguang

AU - Wei, Xin

AU - Ng, Siew Cheok

AU - Ni, Xiaoli

AU - Chi, Aiping

AU - Fang, Peng

AU - Zeng, Weigang

AU - Wei, Bokun

PY - 2021/8/26

Y1 - 2021/8/26

N2 - The EEG features of different emotions were extracted based on multi-channel and forehead channels in this study. The EEG signals of 26 subjects were collected by the emotional video evoked method. The results show that the energy ratio and differential entropy of the frequency band can be used to classify positive and negative emotions effectively, and the best effect can be achieved by using an SVM classifier. When only the forehead and forehead signals are used, the highest classification accuracy can reach 66%. When the data of all channels are used, the highest accuracy of the model can reach 82%. After channel selection, the best model of this study can be obtained. The accuracy is more than 86%.

AB - The EEG features of different emotions were extracted based on multi-channel and forehead channels in this study. The EEG signals of 26 subjects were collected by the emotional video evoked method. The results show that the energy ratio and differential entropy of the frequency band can be used to classify positive and negative emotions effectively, and the best effect can be achieved by using an SVM classifier. When only the forehead and forehead signals are used, the highest classification accuracy can reach 66%. When the data of all channels are used, the highest accuracy of the model can reach 82%. After channel selection, the best model of this study can be obtained. The accuracy is more than 86%.

KW - EEG

KW - back propagation neural network

KW - decision tree

KW - emotion classification

KW - k-nearest neighbor

KW - support vector machine

UR - https://www.scopus.com/pages/publications/85114612479

U2 - 10.3389/fnbeh.2021.720451

DO - 10.3389/fnbeh.2021.720451

M3 - 文章

AN - SCOPUS:85114612479

SN - 1662-5153

VL - 15

JO - Frontiers in Behavioral Neuroscience

JF - Frontiers in Behavioral Neuroscience

M1 - 720451

ER -

Positive and Negative Emotion Classification Based on Multi-channel

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this