EEG-based affective state recognition from human brain signals by using Hjorth-activity

Raja Majid Mehmood; Muhammad Bilal; S. Vimal; Seong Whan Lee

doi:10.1016/j.measurement.2022.111738

EEG-based affective state recognition from human brain signals by using Hjorth-activity

Raja Majid Mehmood, Muhammad Bilal, S. Vimal, Seong Whan Lee

Department of Artificial Intelligence

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

7 Citations (Scopus)

Abstract

EEG-based emotion recognition enables investigation of human brain activity, which is recognized as an important factor in brain-computer interface. In recent years, several methods have been studied to find optimal features from brain signals. The main limitation of existing studies is that either they consider very few emotion classes or they employ a large feature set. To overcome these issues, we propose a novel Hjorth-feature-based emotion recognition model. Unlike other methods, our proposed method explores a wider set of emotion classes in the arousal-valence domain. To reduce the dimension of the feature set, we employ Hjorth parameters (HPs) and analyze the parameters in the frequency domain. At the same time, our study was focused to maintain the accuracy of emotion recognition for four emotional classes. The average accuracy was approximately 69%, 76%, 85%, 59%, and 87% for DEAP, SEED-IV, DREAMER, SELEMO, and ASCERTAIN, respectively. Results show that the features from HP activity with random forest outperforms all the classic methods of EEG-based emotion recognition.

Original language	English
Article number	111738
Journal	Measurement: Journal of the International Measurement Confederation
Volume	202
DOIs	https://doi.org/10.1016/j.measurement.2022.111738
Publication status	Published - 2022 Oct

Bibliographical note

Funding Information:
This work was supported by Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) [No. 2019-0-00079, Department of Artificial Intelligence, Korea University] and [No. 2017-0-00451, Development of BCI based Brain and Cognitive Computing Technology for Recognizing User’s Intentions using Deep Learning]. This work has also supported by the Xiamen University Malaysia Research Fund (XMUMRF) (Grant No: XMUMRF/2022-C9/IECE/0035).

Publisher Copyright:
© 2022

Keywords

ASCERTAIN
Affective state
DEAP
DREAMER
EEG
Emotion recognition
SEED-IV
SELEMO

ASJC Scopus subject areas

Instrumentation
Electrical and Electronic Engineering

Access to Document

10.1016/j.measurement.2022.111738

Cite this

@article{ae28ff6d99394979a0a1a6b37410fdde,

title = "EEG-based affective state recognition from human brain signals by using Hjorth-activity",

abstract = "EEG-based emotion recognition enables investigation of human brain activity, which is recognized as an important factor in brain-computer interface. In recent years, several methods have been studied to find optimal features from brain signals. The main limitation of existing studies is that either they consider very few emotion classes or they employ a large feature set. To overcome these issues, we propose a novel Hjorth-feature-based emotion recognition model. Unlike other methods, our proposed method explores a wider set of emotion classes in the arousal-valence domain. To reduce the dimension of the feature set, we employ Hjorth parameters (HPs) and analyze the parameters in the frequency domain. At the same time, our study was focused to maintain the accuracy of emotion recognition for four emotional classes. The average accuracy was approximately 69%, 76%, 85%, 59%, and 87% for DEAP, SEED-IV, DREAMER, SELEMO, and ASCERTAIN, respectively. Results show that the features from HP activity with random forest outperforms all the classic methods of EEG-based emotion recognition.",

keywords = "ASCERTAIN, Affective state, DEAP, DREAMER, EEG, Emotion recognition, SEED-IV, SELEMO",

author = "Mehmood, {Raja Majid} and Muhammad Bilal and S. Vimal and Lee, {Seong Whan}",

note = "Funding Information: This work was supported by Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) [No. 2019-0-00079, Department of Artificial Intelligence, Korea University] and [No. 2017-0-00451, Development of BCI based Brain and Cognitive Computing Technology for Recognizing User{\textquoteright}s Intentions using Deep Learning]. This work has also supported by the Xiamen University Malaysia Research Fund (XMUMRF) (Grant No: XMUMRF/2022-C9/IECE/0035). Publisher Copyright: {\textcopyright} 2022",

year = "2022",

month = oct,

doi = "10.1016/j.measurement.2022.111738",

language = "English",

volume = "202",

journal = "Measurement: Journal of the International Measurement Confederation",

issn = "0263-2241",

publisher = "Elsevier",

}

TY - JOUR

T1 - EEG-based affective state recognition from human brain signals by using Hjorth-activity

AU - Mehmood, Raja Majid

AU - Bilal, Muhammad

AU - Vimal, S.

AU - Lee, Seong Whan

N1 - Funding Information: This work was supported by Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) [No. 2019-0-00079, Department of Artificial Intelligence, Korea University] and [No. 2017-0-00451, Development of BCI based Brain and Cognitive Computing Technology for Recognizing User’s Intentions using Deep Learning]. This work has also supported by the Xiamen University Malaysia Research Fund (XMUMRF) (Grant No: XMUMRF/2022-C9/IECE/0035). Publisher Copyright: © 2022

PY - 2022/10

Y1 - 2022/10

N2 - EEG-based emotion recognition enables investigation of human brain activity, which is recognized as an important factor in brain-computer interface. In recent years, several methods have been studied to find optimal features from brain signals. The main limitation of existing studies is that either they consider very few emotion classes or they employ a large feature set. To overcome these issues, we propose a novel Hjorth-feature-based emotion recognition model. Unlike other methods, our proposed method explores a wider set of emotion classes in the arousal-valence domain. To reduce the dimension of the feature set, we employ Hjorth parameters (HPs) and analyze the parameters in the frequency domain. At the same time, our study was focused to maintain the accuracy of emotion recognition for four emotional classes. The average accuracy was approximately 69%, 76%, 85%, 59%, and 87% for DEAP, SEED-IV, DREAMER, SELEMO, and ASCERTAIN, respectively. Results show that the features from HP activity with random forest outperforms all the classic methods of EEG-based emotion recognition.

AB - EEG-based emotion recognition enables investigation of human brain activity, which is recognized as an important factor in brain-computer interface. In recent years, several methods have been studied to find optimal features from brain signals. The main limitation of existing studies is that either they consider very few emotion classes or they employ a large feature set. To overcome these issues, we propose a novel Hjorth-feature-based emotion recognition model. Unlike other methods, our proposed method explores a wider set of emotion classes in the arousal-valence domain. To reduce the dimension of the feature set, we employ Hjorth parameters (HPs) and analyze the parameters in the frequency domain. At the same time, our study was focused to maintain the accuracy of emotion recognition for four emotional classes. The average accuracy was approximately 69%, 76%, 85%, 59%, and 87% for DEAP, SEED-IV, DREAMER, SELEMO, and ASCERTAIN, respectively. Results show that the features from HP activity with random forest outperforms all the classic methods of EEG-based emotion recognition.

KW - ASCERTAIN

KW - Affective state

KW - DEAP

KW - DREAMER

KW - EEG

KW - Emotion recognition

KW - SEED-IV

KW - SELEMO

UR - http://www.scopus.com/inward/record.url?scp=85138441095&partnerID=8YFLogxK

U2 - 10.1016/j.measurement.2022.111738

DO - 10.1016/j.measurement.2022.111738

M3 - Article

AN - SCOPUS:85138441095

SN - 0263-2241

VL - 202

JO - Measurement: Journal of the International Measurement Confederation

JF - Measurement: Journal of the International Measurement Confederation

M1 - 111738

ER -

EEG-based affective state recognition from human brain signals by using Hjorth-activity

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this