EEG emotion detection review

Lars Rune Christensen; Mohamed Ahmed  Abdullah

doi:10.1109/CIBCB.2018.8404976

EEG emotion detection review

Lars Rune Christensen, Mohamed Ahmed Abdullah

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

EEG (Electroencephalography) allows to elicit the mental state of the user, which in turn reveals the user emotion, which is an important factor in HMI (Human Machine Interaction). Researchers across the globe are developing new techniques to increase the EEG accuracy by using different signal processing, statistics, and machine learning techniques in this work we will discuss the most common techniques that can yield to better results, along with discussing the common experiment steps to classify the emotion, starting from collecting the signal, and extracting the features and select the best feature to classify the emotions. Along with highlighting some standing problems in field and potential growth areas.

Original language	English
Title of host publication	2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)
Publisher	IEEE
Publication date	2018
ISBN (Print)	978-1-5386-1400-6
ISBN (Electronic)	978-1-5386-1399-3
DOIs	https://doi.org/10.1109/CIBCB.2018.8404976 https://doi.org/10.1109/CIBCB.2018.8404976
Publication status	Published - 2018

Keywords

EEG-based emotion recognition
Human-Machine Interaction
Signal Processing
Feature Extraction
Machine Learning in Neuroscience

Access to Document

10.1109/CIBCB.2018.8404976Licence: Unspecified
10.1109/CIBCB.2018.8404976

Cite this

@inproceedings{b368588b9db74c41a08b20b7a850d2d4,

title = "EEG emotion detection review",

abstract = "EEG (Electroencephalography) allows to elicit the mental state of the user, which in turn reveals the user emotion, which is an important factor in HMI (Human Machine Interaction). Researchers across the globe are developing new techniques to increase the EEG accuracy by using different signal processing, statistics, and machine learning techniques in this work we will discuss the most common techniques that can yield to better results, along with discussing the common experiment steps to classify the emotion, starting from collecting the signal, and extracting the features and select the best feature to classify the emotions. Along with highlighting some standing problems in field and potential growth areas.",

keywords = "EEG-based emotion recognition, Human-Machine Interaction, Signal Processing, Feature Extraction, Machine Learning in Neuroscience",

author = "Christensen, {Lars Rune} and Abdullah, {Mohamed Ahmed}",

year = "2018",

doi = "10.1109/CIBCB.2018.8404976",

language = "English",

isbn = "978-1-5386-1400-6",

booktitle = "2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - EEG emotion detection review

AU - Christensen, Lars Rune

AU - Abdullah , Mohamed Ahmed

PY - 2018

Y1 - 2018

N2 - EEG (Electroencephalography) allows to elicit the mental state of the user, which in turn reveals the user emotion, which is an important factor in HMI (Human Machine Interaction). Researchers across the globe are developing new techniques to increase the EEG accuracy by using different signal processing, statistics, and machine learning techniques in this work we will discuss the most common techniques that can yield to better results, along with discussing the common experiment steps to classify the emotion, starting from collecting the signal, and extracting the features and select the best feature to classify the emotions. Along with highlighting some standing problems in field and potential growth areas.

AB - EEG (Electroencephalography) allows to elicit the mental state of the user, which in turn reveals the user emotion, which is an important factor in HMI (Human Machine Interaction). Researchers across the globe are developing new techniques to increase the EEG accuracy by using different signal processing, statistics, and machine learning techniques in this work we will discuss the most common techniques that can yield to better results, along with discussing the common experiment steps to classify the emotion, starting from collecting the signal, and extracting the features and select the best feature to classify the emotions. Along with highlighting some standing problems in field and potential growth areas.

KW - EEG-based emotion recognition

KW - Human-Machine Interaction

KW - Signal Processing

KW - Feature Extraction

KW - Machine Learning in Neuroscience

U2 - 10.1109/CIBCB.2018.8404976

DO - 10.1109/CIBCB.2018.8404976

M3 - Article in proceedings

SN - 978-1-5386-1400-6

BT - 2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)

PB - IEEE

ER -

EEG emotion detection review

Abstract

Keywords

Access to Document

Fingerprint

Cite this