A comparative analysis of emotion recognition from EEG signals using temporal features and hyperparameter-tuned machine learning techniques

Classifying emotions based on EEG signals is really important for enhancing our interactions with computers, monitoring mental health and creating applications in affective computing field. This study explores improving emotion recognition performance by applying traditional machine learning classif...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:MethodsX Ročník 15; s. 103468
Hlavní autoři: Hasan, Rabita, Islam, Sheikh Md. Rabiul
Médium: Journal Article
Jazyk:angličtina
Vydáno: Netherlands Elsevier B.V 01.12.2025
Elsevier
Témata:
ISSN:2215-0161, 2215-0161
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Classifying emotions based on EEG signals is really important for enhancing our interactions with computers, monitoring mental health and creating applications in affective computing field. This study explores improving emotion recognition performance by applying traditional machine learning classifiers and boosting techniques to EEG data from the DEAP dataset. To categorize emotional states, we used four classifiers: K-Nearest Neighbors (KNN), Support Vector Machine (SVM), XGBoost and Gradient Boosting. Differential entropy and Higuchi's fractal dimension are two important time-domain parameters that we extracted after applying a segmentation technique to capture the temporal interdependence of EEG data. These features were selected for their ability to reflect intricate neural dynamics associated with emotional processing. A five-fold cross-validation procedure was applied to estimate the model's performance and hyperparameter tuning was conducted to optimize classifier efficiency. XGBoost achieved the highest accuracy 89 % for valence and 88 % for arousal demonstrating its superior performance. Furthermore, cross-subject evaluation on the SEED dataset reinforced the approach’s robustness, where XGBoost achieved 86 % accuracy using HFD and 84 % using DE. These results emphasize the effectiveness of combining advanced feature extraction methods with boosting algorithms for EEG-based emotion recognition, offering promising directions for the development of real-world emotion-aware systems. The key findings of this research are as follows:•Differential Entropy and Higuchi’s Fractal Dimension proved effective in capturing emotional brain dynamics•XGBoost outperformed other classifiers in both DEAP and SEED datasets•The proposed method demonstrates robustness across subject variations and datasets [Display omitted]
AbstractList Classifying emotions based on EEG signals is really important for enhancing our interactions with computers, monitoring mental health and creating applications in affective computing field. This study explores improving emotion recognition performance by applying traditional machine learning classifiers and boosting techniques to EEG data from the DEAP dataset. To categorize emotional states, we used four classifiers: K-Nearest Neighbors (KNN), Support Vector Machine (SVM), XGBoost and Gradient Boosting. Differential entropy and Higuchi's fractal dimension are two important time-domain parameters that we extracted after applying a segmentation technique to capture the temporal interdependence of EEG data. These features were selected for their ability to reflect intricate neural dynamics associated with emotional processing. A five-fold cross-validation procedure was applied to estimate the model's performance and hyperparameter tuning was conducted to optimize classifier efficiency. XGBoost achieved the highest accuracy 89 % for valence and 88 % for arousal demonstrating its superior performance. Furthermore, cross-subject evaluation on the SEED dataset reinforced the approach's robustness, where XGBoost achieved 86 % accuracy using HFD and 84 % using DE. These results emphasize the effectiveness of combining advanced feature extraction methods with boosting algorithms for EEG-based emotion recognition, offering promising directions for the development of real-world emotion-aware systems. The key findings of this research are as follows:•Differential Entropy and Higuchi's Fractal Dimension proved effective in capturing emotional brain dynamics•XGBoost outperformed other classifiers in both DEAP and SEED datasets•The proposed method demonstrates robustness across subject variations and datasets.Classifying emotions based on EEG signals is really important for enhancing our interactions with computers, monitoring mental health and creating applications in affective computing field. This study explores improving emotion recognition performance by applying traditional machine learning classifiers and boosting techniques to EEG data from the DEAP dataset. To categorize emotional states, we used four classifiers: K-Nearest Neighbors (KNN), Support Vector Machine (SVM), XGBoost and Gradient Boosting. Differential entropy and Higuchi's fractal dimension are two important time-domain parameters that we extracted after applying a segmentation technique to capture the temporal interdependence of EEG data. These features were selected for their ability to reflect intricate neural dynamics associated with emotional processing. A five-fold cross-validation procedure was applied to estimate the model's performance and hyperparameter tuning was conducted to optimize classifier efficiency. XGBoost achieved the highest accuracy 89 % for valence and 88 % for arousal demonstrating its superior performance. Furthermore, cross-subject evaluation on the SEED dataset reinforced the approach's robustness, where XGBoost achieved 86 % accuracy using HFD and 84 % using DE. These results emphasize the effectiveness of combining advanced feature extraction methods with boosting algorithms for EEG-based emotion recognition, offering promising directions for the development of real-world emotion-aware systems. The key findings of this research are as follows:•Differential Entropy and Higuchi's Fractal Dimension proved effective in capturing emotional brain dynamics•XGBoost outperformed other classifiers in both DEAP and SEED datasets•The proposed method demonstrates robustness across subject variations and datasets.
Classifying emotions based on EEG signals is really important for enhancing our interactions with computers, monitoring mental health and creating applications in affective computing field. This study explores improving emotion recognition performance by applying traditional machine learning classifiers and boosting techniques to EEG data from the DEAP dataset. To categorize emotional states, we used four classifiers: K-Nearest Neighbors (KNN), Support Vector Machine (SVM), XGBoost and Gradient Boosting. Differential entropy and Higuchi's fractal dimension are two important time-domain parameters that we extracted after applying a segmentation technique to capture the temporal interdependence of EEG data. These features were selected for their ability to reflect intricate neural dynamics associated with emotional processing. A five-fold cross-validation procedure was applied to estimate the model's performance and hyperparameter tuning was conducted to optimize classifier efficiency. XGBoost achieved the highest accuracy 89 % for valence and 88 % for arousal demonstrating its superior performance. Furthermore, cross-subject evaluation on the SEED dataset reinforced the approach's robustness, where XGBoost achieved 86 % accuracy using HFD and 84 % using DE. These results emphasize the effectiveness of combining advanced feature extraction methods with boosting algorithms for EEG-based emotion recognition, offering promising directions for the development of real-world emotion-aware systems. The key findings of this research are as follows:•Differential Entropy and Higuchi's Fractal Dimension proved effective in capturing emotional brain dynamics•XGBoost outperformed other classifiers in both DEAP and SEED datasets•The proposed method demonstrates robustness across subject variations and datasets.
Classifying emotions based on EEG signals is really important for enhancing our interactions with computers, monitoring mental health and creating applications in affective computing field. This study explores improving emotion recognition performance by applying traditional machine learning classifiers and boosting techniques to EEG data from the DEAP dataset. To categorize emotional states, we used four classifiers: K-Nearest Neighbors (KNN), Support Vector Machine (SVM), XGBoost and Gradient Boosting. Differential entropy and Higuchi's fractal dimension are two important time-domain parameters that we extracted after applying a segmentation technique to capture the temporal interdependence of EEG data. These features were selected for their ability to reflect intricate neural dynamics associated with emotional processing. A five-fold cross-validation procedure was applied to estimate the model's performance and hyperparameter tuning was conducted to optimize classifier efficiency. XGBoost achieved the highest accuracy 89 % for valence and 88 % for arousal demonstrating its superior performance. Furthermore, cross-subject evaluation on the SEED dataset reinforced the approach’s robustness, where XGBoost achieved 86 % accuracy using HFD and 84 % using DE. These results emphasize the effectiveness of combining advanced feature extraction methods with boosting algorithms for EEG-based emotion recognition, offering promising directions for the development of real-world emotion-aware systems. The key findings of this research are as follows:•Differential Entropy and Higuchi’s Fractal Dimension proved effective in capturing emotional brain dynamics•XGBoost outperformed other classifiers in both DEAP and SEED datasets•The proposed method demonstrates robustness across subject variations and datasets [Display omitted]
Classifying emotions based on EEG signals is really important for enhancing our interactions with computers, monitoring mental health and creating applications in affective computing field. This study explores improving emotion recognition performance by applying traditional machine learning classifiers and boosting techniques to EEG data from the DEAP dataset. To categorize emotional states, we used four classifiers: K-Nearest Neighbors (KNN), Support Vector Machine (SVM), XGBoost and Gradient Boosting. Differential entropy and Higuchi's fractal dimension are two important time-domain parameters that we extracted after applying a segmentation technique to capture the temporal interdependence of EEG data. These features were selected for their ability to reflect intricate neural dynamics associated with emotional processing. A five-fold cross-validation procedure was applied to estimate the model's performance and hyperparameter tuning was conducted to optimize classifier efficiency. XGBoost achieved the highest accuracy 89 % for valence and 88 % for arousal demonstrating its superior performance. Furthermore, cross-subject evaluation on the SEED dataset reinforced the approach’s robustness, where XGBoost achieved 86 % accuracy using HFD and 84 % using DE. These results emphasize the effectiveness of combining advanced feature extraction methods with boosting algorithms for EEG-based emotion recognition, offering promising directions for the development of real-world emotion-aware systems. The key findings of this research are as follows: • Differential Entropy and Higuchi’s Fractal Dimension proved effective in capturing emotional brain dynamics • XGBoost outperformed other classifiers in both DEAP and SEED datasets • The proposed method demonstrates robustness across subject variations and datasets
ArticleNumber 103468
Author Hasan, Rabita
Islam, Sheikh Md. Rabiul
Author_xml – sequence: 1
  givenname: Rabita
  orcidid: 0009-0008-7874-9544
  surname: Hasan
  fullname: Hasan, Rabita
  email: rabita.hasan@gstu.edu.bd
– sequence: 2
  givenname: Sheikh Md. Rabiul
  surname: Islam
  fullname: Islam, Sheikh Md. Rabiul
BackLink https://www.ncbi.nlm.nih.gov/pubmed/40687354$$D View this record in MEDLINE/PubMed
BookMark eNp9kc1u3CAUha0qVZOmeYBuKpbdeMKfjVFXUTRNI0Xqpl0jBl9mGBmYAo46z9CXLhOnUVdZcYHvnKt7z_vmLMQATfOR4BXBpL_erzz8XlFMu3pnvB_eNBeUkq6tn-Tsv_q8ucp5jzEmjDPC6bvmnON-EKzjF82fG2SiP-iki3sEpIOejtllFC0CH4uLASUwcRvcU21T9Gi9vkPZbSua0Zxd2KIC_hCTnpAFXeYEuRqNaHc8QDpZeyiQ2jIHGJHXZucCoAl0CovW7IL7NUP-0Ly11ROuns_L5ufX9Y_bb-3D97v725uH1nDSl1ZzkMIKIq2VQhIjpWGMbTqpdSeG3nA8wABCYEGpwSN0mLERi1H2hA9UWHbZ3C--Y9R7dUjO63RUUTv19BDTVulUnJlAdRQTQ7rO1o3xgfeS1rUOHHNONkJrXr0-L16HFE8zFOVdNjBNOkCcs2KUEYlZT_qKfnpG542H8aXxvzAqQBbApJhzAvuCEKxOmau9qpmrU-ZqybxqviwaqAt7dJBUNg6CgdHV3EqdyL2i_gvt77My
Cites_doi 10.1016/j.bbe.2020.04.005
10.1155/2017/8317357
10.1016/j.jad.2022.09.054
10.1109/TAMD.2015.2431497
10.3390/computers9040095
10.1109/TAFFC.2017.2712143
10.3390/informatics7010006
10.1145/2818740
10.1016/j.jvcir.2019.102672
10.3390/app142311323
10.1109/T-AFFC.2011.15
10.1016/j.chb.2016.08.029
10.1109/ACCESS.2021.3051281
10.1088/1361-6579/ab310a
10.1016/j.eswa.2022.118025
10.1016/j.compeleceng.2018.09.022
10.1007/s00779-017-1072-7
10.1186/1758-2946-6-10
10.1080/10255842.2022.2143714
10.1007/s00521-015-2149-8
10.1109/ACCESS.2018.2855194
ContentType Journal Article
Copyright 2025
2025 The Authors. Published by Elsevier B.V.
Copyright_xml – notice: 2025
– notice: 2025 The Authors. Published by Elsevier B.V.
DBID 6I.
AAFTH
AAYXX
CITATION
NPM
7X8
DOA
DOI 10.1016/j.mex.2025.103468
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
PubMed
MEDLINE - Academic
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
PubMed


Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2215-0161
ExternalDocumentID oai_doaj_org_article_5201c155f406484692221840441b7aa4
40687354
10_1016_j_mex_2025_103468
S2215016125003139
Genre Journal Article
GroupedDBID 0R~
4.4
457
53G
5VS
6I.
AAEDT
AAEDW
AAFTH
AAFWJ
AAHBH
AAIKJ
AALRI
AAXUO
AAYWO
ABMAC
ACGFS
ACVFH
ADBBV
ADCNI
ADEZE
ADRAZ
ADVLN
AEUPX
AEXQZ
AFJKZ
AFPKN
AFPUW
AFTJW
AGHFR
AIGII
AITUG
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
AOIJS
APXCP
BCNDV
EBS
EJD
FDB
GROUPED_DOAJ
HYE
IPNFZ
IXB
KQ8
M48
M~E
OK1
RIG
ROL
RPM
SSZ
AAYXX
CITATION
NPM
7X8
ID FETCH-LOGICAL-c416t-a4e97f719ff9791c99c333b59aa5786c408e8e770722c0de5033d07d9614827f3
IEDL.DBID DOA
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001532775200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2215-0161
IngestDate Fri Oct 03 12:32:49 EDT 2025
Mon Jul 21 19:32:02 EDT 2025
Thu Jul 24 02:10:27 EDT 2025
Thu Nov 27 01:02:54 EST 2025
Sat Aug 09 17:30:47 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Feature extraction
EEG signals
Boosted EEG Emotion Classification Using Differential Entropy and Higuchi's Fractal Dimension
Emotion classification
Machine learning
DEAP dataset
Language English
License This is an open access article under the CC BY license.
2025 The Authors. Published by Elsevier B.V.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c416t-a4e97f719ff9791c99c333b59aa5786c408e8e770722c0de5033d07d9614827f3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0009-0008-7874-9544
OpenAccessLink https://doaj.org/article/5201c155f406484692221840441b7aa4
PMID 40687354
PQID 3231903616
PQPubID 23479
ParticipantIDs doaj_primary_oai_doaj_org_article_5201c155f406484692221840441b7aa4
proquest_miscellaneous_3231903616
pubmed_primary_40687354
crossref_primary_10_1016_j_mex_2025_103468
elsevier_sciencedirect_doi_10_1016_j_mex_2025_103468
PublicationCentury 2000
PublicationDate December 2025
2025-12-00
2025-Dec
20251201
2025-12-01
PublicationDateYYYYMMDD 2025-12-01
PublicationDate_xml – month: 12
  year: 2025
  text: December 2025
PublicationDecade 2020
PublicationPlace Netherlands
PublicationPlace_xml – name: Netherlands
PublicationTitle MethodsX
PublicationTitleAlternate MethodsX
PublicationYear 2025
Publisher Elsevier B.V
Elsevier
Publisher_xml – name: Elsevier B.V
– name: Elsevier
References Mehreen, Anwar, Haseeb, Majid, Ullah (bib0009) 2019; 20
Piana, Stagliano, Odone, Camurri (bib0003) 2016; 6
Nawaz, Cheah, Nisar, Yap (bib0029) 2020; 40
Rahman, Sarkar, Hossain, Moni (bib0011) 2022; 207
Koelstra (bib0026) 2012; 3
Gannouni, Aledaily, Belwafi, Aboalsamh (bib0007) 2022; 319
Nawaz, Nisar, Voon (bib0019) Jul. 2018; 6
Qayyum, Majid, Haq, Anwar (bib0008) 2019
Bhatti, Majid, Anwar, Khan (bib0024) 2016; 65
Chen, Ju, Yuan, Elhoseny, Ren, Fan, Chen (bib0023) 2018; 72
Alhalaseh, Alasasfeh (bib0017) Nov. 2020; 9
Alves, Melo, Cerri, de Freitas, Adamatti, de Aguiar (bib0033) 2024; 37
Khateeb, Anwar, Alnowami (bib0025) 2021; 9
Hasan, Islam, Khan (bib0012) 2024
Valderas, Bolea, Laguna, Bailon, Vallverdu (bib0005) 2019
Kajal, Fioravanti, Elshahabi, Ruiz, Sitaram, Braun (bib0006) 2020; 222
Hancer, Subasi (bib0016) 2023
Miranda, Canabal, Garcia, Lopez-Ongil (bib0004) 2018; 2208
Yuvaraj, Thagavel, Thomas, Fogarty, Ali (bib0028) 2023; 23
Fang, Yang, Zhang, Liu, Tao (bib0020) 2020
Menezes (bib0014) 2017; 21
Yang, Wu, Fu, Chen (bib0027) 2018; 11307
Zhuang, Zeng, Tong, Zhang, Zhang, Yan (bib0034) Aug. 2017; 2017
Gonzalez, Yoo, Elfadel (bib0022) July 2019
Krstajic, Buturovic, Leahy, Thomas (bib0031) 2014; 6
Alreshidi, Ullah (bib0002) 2020; 7
Veeramallu (bib0015) 2019
Mohamed, Jusas (bib0010) 2024; 14
(bib0032) 2021
Liu, Meng, Li, Zhang, Qin, Nandi (bib0030) 2018; 30
Vanitha, krishnan (bib0013) 2018; 23
Zheng, Lu (bib0035) Sep. 2015; 7
Zheng, Zhu, Lu (bib0021) 2019; 10
Zhang, Huang, Gao (bib0001) 2017; 20
Z. Mohammadi et al., “Wavelet based emotion recognition structure using EEG signal”, Springer, pp. 1987–1993, 2017.
Khateeb (10.1016/j.mex.2025.103468_bib0025) 2021; 9
Zhuang (10.1016/j.mex.2025.103468_bib0034) 2017; 2017
Fang (10.1016/j.mex.2025.103468_bib0020) 2020
10.1016/j.mex.2025.103468_bib0018
Zheng (10.1016/j.mex.2025.103468_bib0035) 2015; 7
Rahman (10.1016/j.mex.2025.103468_bib0011) 2022; 207
Alves (10.1016/j.mex.2025.103468_bib0033) 2024; 37
Valderas (10.1016/j.mex.2025.103468_bib0005) 2019
Chen (10.1016/j.mex.2025.103468_bib0023) 2018; 72
Krstajic (10.1016/j.mex.2025.103468_bib0031) 2014; 6
Alhalaseh (10.1016/j.mex.2025.103468_bib0017) 2020; 9
Gannouni (10.1016/j.mex.2025.103468_bib0007) 2022; 319
Vanitha (10.1016/j.mex.2025.103468_bib0013) 2018; 23
Bhatti (10.1016/j.mex.2025.103468_bib0024) 2016; 65
Hasan (10.1016/j.mex.2025.103468_bib0012) 2024
Veeramallu (10.1016/j.mex.2025.103468_bib0015) 2019
Mohamed (10.1016/j.mex.2025.103468_bib0010) 2024; 14
Piana (10.1016/j.mex.2025.103468_bib0003) 2016; 6
Koelstra (10.1016/j.mex.2025.103468_bib0026) 2012; 3
Zhang (10.1016/j.mex.2025.103468_bib0001) 2017; 20
Mehreen (10.1016/j.mex.2025.103468_bib0009) 2019; 20
(10.1016/j.mex.2025.103468_bib0032) 2021
Gonzalez (10.1016/j.mex.2025.103468_bib0022) 2019
Yang (10.1016/j.mex.2025.103468_bib0027) 2018; 11307
Menezes (10.1016/j.mex.2025.103468_bib0014) 2017; 21
Nawaz (10.1016/j.mex.2025.103468_bib0029) 2020; 40
Hancer (10.1016/j.mex.2025.103468_bib0016) 2023
Zheng (10.1016/j.mex.2025.103468_bib0021) 2019; 10
Kajal (10.1016/j.mex.2025.103468_bib0006) 2020; 222
Alreshidi (10.1016/j.mex.2025.103468_bib0002) 2020; 7
Nawaz (10.1016/j.mex.2025.103468_bib0019) 2018; 6
Liu (10.1016/j.mex.2025.103468_bib0030) 2018; 30
Miranda (10.1016/j.mex.2025.103468_bib0004) 2018; 2208
Qayyum (10.1016/j.mex.2025.103468_bib0008) 2019
Yuvaraj (10.1016/j.mex.2025.103468_bib0028) 2023; 23
References_xml – volume: 6
  start-page: 5
  year: 2014
  end-page: 20
  ident: bib0031
  article-title: Cross-validation pitfalls when selecting and assessing regression and classification models
  publication-title: J. Cheminform.
– volume: 222
  year: 2020
  ident: bib0006
  publication-title: Involvement of Top-Down Networks in the Perception of Facial emotions: A magnetoencephalographic Investigation
– year: July 2019
  ident: bib0022
  article-title: EEG-based emotion detection using unsupervised transfer learning
  publication-title: Proceedings of the 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
– start-page: 3
  year: 2019
  end-page: 9
  ident: bib0015
  article-title: EEG based automatic emotion recognition using EMD and RF classifier
  publication-title: 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)
– volume: 7
  start-page: 1
  year: 2020
  end-page: 16
  ident: bib0002
  article-title: Facial emotion recognition using hybrid features
  publication-title: Informatics
– volume: 11307
  start-page: 436
  year: 2018
  end-page: 446
  ident: bib0027
  article-title: Continuous convolutional neural network with 3D input for EEG-based emotion recognition
  publication-title: Springer
– volume: 37
  year: 2024
  ident: bib0033
  article-title: A machine learning pipeline for emotion recognition based on brain topographic maps derived from electroencephalogram signals
  publication-title: 2024 International FLAIRS Conference Proceedings
– year: 2019
  ident: bib0005
  article-title: Mutual information between heart rate variability and respiration for emotion characterization
  publication-title: Physiol. Meas
– volume: 20
  start-page: 5121
  year: 2019
  end-page: 5128
  ident: bib0009
  article-title: A hybrid scheme for drowsiness detection using wearable sensors
  publication-title: IEEE Sens. J
– volume: 6
  start-page: 45195
  year: Jul. 2018
  end-page: 45211
  ident: bib0019
  article-title: The effect of music on Human brain: frequency domain and time series analysis using electroencephalogram
  publication-title: IEEe Access.
– reference: Z. Mohammadi et al., “Wavelet based emotion recognition structure using EEG signal”, Springer, pp. 1987–1993, 2017.
– volume: 21
  start-page: 1007
  year: 2017
  end-page: 1018
  ident: bib0014
  article-title: Towards emotion recognition for virtual environments: an evaluation of EEG features on bench-mark dataset
  publication-title: Pers. Ubiquitous Comput.
– year: 2019
  ident: bib0008
  article-title: Generation of personalized video summaries by detecting viewer’s emotion using eeg
  publication-title: J. Vis. Commun. Image Represent
– volume: 72
  start-page: 385
  year: 2018
  end-page: 395
  ident: bib0023
  article-title: Emotion recognition using empirical mode decomposition and approximation entropy
  publication-title: Comput. Electr. Eng.
– year: 2021
  ident: bib0032
  article-title: What is the benefit of k-fold cross-validation?
  publication-title: Cross Validated Stack Exch.
– volume: 20
  start-page: 1574
  year: 2017
  end-page: 1592
  ident: bib0001
  article-title: Speech emotion recognition using deep CNN and discriminant temporal pyramid matching
  publication-title: IEEE Trans. Multimed
– volume: 65
  start-page: 270
  year: 2016
  end-page: 278
  ident: bib0024
  article-title: Human emotion recognition and analysis in response to audio music using brain signals
  publication-title: Comput. Hum. Behav.
– volume: 30
  start-page: 5
  year: 2018
  end-page: 18
  ident: bib0030
  article-title: Emotion detection from EEG recordings based on supervised and unsupervised dimension reduction
  publication-title: Concurr. Comput.: Pract. Exp.
– volume: 207
  start-page: 118028
  year: 2022
  end-page: 118040
  ident: bib0011
  article-title: EEG-based emotion analysis using non-linear features and ensemble learning approaches
  publication-title: Expert Syst. Appl.
– volume: 14
  start-page: 11323
  year: 2024
  end-page: 11335
  ident: bib0010
  article-title: Developing innovative feature extraction techniques from the emotion recognition field on motor imagery using brain–computer interface EEG signals
  publication-title: Appl. Sci.
– volume: 6
  start-page: 3
  year: 2016
  end-page: 33
  ident: bib0003
  article-title: Adaptive body gesture representation for automatic emotion recognition
  publication-title: ACM Trans. Interact. Intell. Syst.
– volume: 9
  start-page: 97
  year: Nov. 2020
  ident: bib0017
  article-title: Machine-learning-based emotion recognition system using EEG signals
  publication-title: Computers
– volume: 23
  year: 2023
  ident: bib0028
  article-title: Comprehensive analysis of feature extraction methods for emotion recognition from multichannel EEG recordings
  publication-title: Sensors
– volume: 7
  start-page: 162
  year: Sep. 2015
  end-page: 175
  ident: bib0035
  article-title: ‘Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks,’’
  publication-title: IEEE Trans. Aut. Ment. Dev.
– volume: 319
  start-page: 420
  year: 2022
  end-page: 430
  ident: bib0007
  article-title: EEG based emotion detection using ensemble classification and asymmetric brain activity
  publication-title: J. Affect. Disord.
– volume: 3
  start-page: 18
  year: 2012
  end-page: 31
  ident: bib0026
  article-title: DEAP: a database for emotion analysis; using physiological signals
  publication-title: IEEE Trans. Affect Comput.
– volume: 2208
  start-page: 25
  year: 2018
  end-page: 32
  ident: bib0004
  article-title: Embedded emotion recognition: autonomous multimodal affective IOTs
  publication-title: Proc. Cyber-Phys. Syst. Workshop
– volume: 23
  year: 2018
  ident: bib0013
  article-title: Time-frequency analysis of EEG for improved classification of emotion
  publication-title: Int. J. Biomed. Eng. Technol.
– year: 2023
  ident: bib0016
  article-title: EEG-based emotion recognition using dual tree complex wavelet transform and random subspace ensemble classifier
  publication-title: Comput. Methods Biomech. Biomed. Eng.: Imaging Vis.
– volume: 9
  year: 2021
  ident: bib0025
  article-title: Multi-domain feature fusion for emotion classification using DEAP dataset
  publication-title: IEEe Access.
– start-page: 1
  year: 2024
  end-page: 6
  ident: bib0012
  article-title: Machine Learning Techniques for Brain Stroke Analysis and Prediction
  publication-title: IEEE International Conference on Signal Processing, Information, Communication & Systems (SPICSCON)
– volume: 40
  start-page: 915
  year: 2020
  end-page: 930
  ident: bib0029
  article-title: Comparison of different feature extraction methods for EEG-based emotion recognition
  publication-title: Biocybern. Biomed. Eng.
– volume: 10
  start-page: 420
  year: 2019
  end-page: 432
  ident: bib0021
  article-title: Identifying stable patterns over time for emotion recognition from EEG
  publication-title: IEEe Trans. Affect Comput.
– volume: 2017
  start-page: 3
  year: Aug. 2017
  end-page: 12
  ident: bib0034
  article-title: ‘Emotion recognition from EEG signals using multidimensional information in EMD domain
  publication-title: BioMed. Res. Int.
– year: 2020
  ident: bib0020
  article-title: Multi-feature input deep forest for EEG-based emotion recognition
  publication-title: Front. Neurorobot.
– volume: 40
  start-page: 915
  year: 2020
  ident: 10.1016/j.mex.2025.103468_bib0029
  article-title: Comparison of different feature extraction methods for EEG-based emotion recognition
  publication-title: Biocybern. Biomed. Eng.
  doi: 10.1016/j.bbe.2020.04.005
– volume: 23
  issue: 6–10
  year: 2018
  ident: 10.1016/j.mex.2025.103468_bib0013
  article-title: Time-frequency analysis of EEG for improved classification of emotion
  publication-title: Int. J. Biomed. Eng. Technol.
– volume: 2017
  start-page: 3
  year: 2017
  ident: 10.1016/j.mex.2025.103468_bib0034
  article-title: ‘Emotion recognition from EEG signals using multidimensional information in EMD domain
  publication-title: BioMed. Res. Int.
  doi: 10.1155/2017/8317357
– volume: 319
  start-page: 420
  year: 2022
  ident: 10.1016/j.mex.2025.103468_bib0007
  article-title: EEG based emotion detection using ensemble classification and asymmetric brain activity
  publication-title: J. Affect. Disord.
  doi: 10.1016/j.jad.2022.09.054
– volume: 7
  start-page: 162
  issue: 3
  year: 2015
  ident: 10.1016/j.mex.2025.103468_bib0035
  article-title: ‘Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks,’’
  publication-title: IEEE Trans. Aut. Ment. Dev.
  doi: 10.1109/TAMD.2015.2431497
– volume: 9
  start-page: 97
  issue: 4
  year: 2020
  ident: 10.1016/j.mex.2025.103468_bib0017
  article-title: Machine-learning-based emotion recognition system using EEG signals
  publication-title: Computers
  doi: 10.3390/computers9040095
– start-page: 1
  year: 2024
  ident: 10.1016/j.mex.2025.103468_bib0012
  article-title: Machine Learning Techniques for Brain Stroke Analysis and Prediction
– volume: 10
  start-page: 420
  issue: 3
  year: 2019
  ident: 10.1016/j.mex.2025.103468_bib0021
  article-title: Identifying stable patterns over time for emotion recognition from EEG
  publication-title: IEEe Trans. Affect Comput.
  doi: 10.1109/TAFFC.2017.2712143
– volume: 7
  start-page: 1
  issue: 1
  year: 2020
  ident: 10.1016/j.mex.2025.103468_bib0002
  article-title: Facial emotion recognition using hybrid features
  publication-title: Informatics
  doi: 10.3390/informatics7010006
– volume: 6
  start-page: 3
  year: 2016
  ident: 10.1016/j.mex.2025.103468_bib0003
  article-title: Adaptive body gesture representation for automatic emotion recognition
  publication-title: ACM Trans. Interact. Intell. Syst.
  doi: 10.1145/2818740
– volume: 20
  start-page: 5121
  issue: 15
  year: 2019
  ident: 10.1016/j.mex.2025.103468_bib0009
  article-title: A hybrid scheme for drowsiness detection using wearable sensors
  publication-title: IEEE Sens. J
– year: 2019
  ident: 10.1016/j.mex.2025.103468_bib0008
  article-title: Generation of personalized video summaries by detecting viewer’s emotion using eeg
  publication-title: J. Vis. Commun. Image Represent
  doi: 10.1016/j.jvcir.2019.102672
– volume: 23
  issue: 920
  year: 2023
  ident: 10.1016/j.mex.2025.103468_bib0028
  article-title: Comprehensive analysis of feature extraction methods for emotion recognition from multichannel EEG recordings
  publication-title: Sensors
– year: 2020
  ident: 10.1016/j.mex.2025.103468_bib0020
  article-title: Multi-feature input deep forest for EEG-based emotion recognition
  publication-title: Front. Neurorobot.
– volume: 11307
  start-page: 436
  year: 2018
  ident: 10.1016/j.mex.2025.103468_bib0027
  article-title: Continuous convolutional neural network with 3D input for EEG-based emotion recognition
  publication-title: Springer
– year: 2019
  ident: 10.1016/j.mex.2025.103468_bib0022
  article-title: EEG-based emotion detection using unsupervised transfer learning
– volume: 2208
  start-page: 25
  year: 2018
  ident: 10.1016/j.mex.2025.103468_bib0004
  article-title: Embedded emotion recognition: autonomous multimodal affective IOTs
  publication-title: Proc. Cyber-Phys. Syst. Workshop
– volume: 222
  year: 2020
  ident: 10.1016/j.mex.2025.103468_bib0006
– volume: 14
  start-page: 11323
  issue: 11
  year: 2024
  ident: 10.1016/j.mex.2025.103468_bib0010
  article-title: Developing innovative feature extraction techniques from the emotion recognition field on motor imagery using brain–computer interface EEG signals
  publication-title: Appl. Sci.
  doi: 10.3390/app142311323
– volume: 3
  start-page: 18
  issue: 1
  year: 2012
  ident: 10.1016/j.mex.2025.103468_bib0026
  article-title: DEAP: a database for emotion analysis; using physiological signals
  publication-title: IEEE Trans. Affect Comput.
  doi: 10.1109/T-AFFC.2011.15
– volume: 20
  start-page: 1574
  year: 2017
  ident: 10.1016/j.mex.2025.103468_bib0001
  article-title: Speech emotion recognition using deep CNN and discriminant temporal pyramid matching
  publication-title: IEEE Trans. Multimed
– volume: 65
  start-page: 270
  year: 2016
  ident: 10.1016/j.mex.2025.103468_bib0024
  article-title: Human emotion recognition and analysis in response to audio music using brain signals
  publication-title: Comput. Hum. Behav.
  doi: 10.1016/j.chb.2016.08.029
– volume: 9
  year: 2021
  ident: 10.1016/j.mex.2025.103468_bib0025
  article-title: Multi-domain feature fusion for emotion classification using DEAP dataset
  publication-title: IEEe Access.
  doi: 10.1109/ACCESS.2021.3051281
– year: 2021
  ident: 10.1016/j.mex.2025.103468_bib0032
  article-title: What is the benefit of k-fold cross-validation?
  publication-title: Cross Validated Stack Exch.
– year: 2019
  ident: 10.1016/j.mex.2025.103468_bib0005
  article-title: Mutual information between heart rate variability and respiration for emotion characterization
  publication-title: Physiol. Meas
  doi: 10.1088/1361-6579/ab310a
– volume: 207
  start-page: 118028
  year: 2022
  ident: 10.1016/j.mex.2025.103468_bib0011
  article-title: EEG-based emotion analysis using non-linear features and ensemble learning approaches
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2022.118025
– volume: 72
  start-page: 385
  year: 2018
  ident: 10.1016/j.mex.2025.103468_bib0023
  article-title: Emotion recognition using empirical mode decomposition and approximation entropy
  publication-title: Comput. Electr. Eng.
  doi: 10.1016/j.compeleceng.2018.09.022
– start-page: 3
  year: 2019
  ident: 10.1016/j.mex.2025.103468_bib0015
  article-title: EEG based automatic emotion recognition using EMD and RF classifier
– volume: 21
  start-page: 1007
  issue: 6
  year: 2017
  ident: 10.1016/j.mex.2025.103468_bib0014
  article-title: Towards emotion recognition for virtual environments: an evaluation of EEG features on bench-mark dataset
  publication-title: Pers. Ubiquitous Comput.
  doi: 10.1007/s00779-017-1072-7
– volume: 6
  start-page: 5
  issue: 1
  year: 2014
  ident: 10.1016/j.mex.2025.103468_bib0031
  article-title: Cross-validation pitfalls when selecting and assessing regression and classification models
  publication-title: J. Cheminform.
  doi: 10.1186/1758-2946-6-10
– year: 2023
  ident: 10.1016/j.mex.2025.103468_bib0016
  article-title: EEG-based emotion recognition using dual tree complex wavelet transform and random subspace ensemble classifier
  publication-title: Comput. Methods Biomech. Biomed. Eng.: Imaging Vis.
  doi: 10.1080/10255842.2022.2143714
– volume: 37
  year: 2024
  ident: 10.1016/j.mex.2025.103468_bib0033
  article-title: A machine learning pipeline for emotion recognition based on brain topographic maps derived from electroencephalogram signals
– ident: 10.1016/j.mex.2025.103468_bib0018
  doi: 10.1007/s00521-015-2149-8
– volume: 30
  start-page: 5
  issue: 1
  year: 2018
  ident: 10.1016/j.mex.2025.103468_bib0030
  article-title: Emotion detection from EEG recordings based on supervised and unsupervised dimension reduction
  publication-title: Concurr. Comput.: Pract. Exp.
– volume: 6
  start-page: 45195
  year: 2018
  ident: 10.1016/j.mex.2025.103468_bib0019
  article-title: The effect of music on Human brain: frequency domain and time series analysis using electroencephalogram
  publication-title: IEEe Access.
  doi: 10.1109/ACCESS.2018.2855194
SSID ssj0001343142
Score 2.3332765
Snippet Classifying emotions based on EEG signals is really important for enhancing our interactions with computers, monitoring mental health and creating applications...
SourceID doaj
proquest
pubmed
crossref
elsevier
SourceType Open Website
Aggregation Database
Index Database
Publisher
StartPage 103468
SubjectTerms Boosted EEG Emotion Classification Using Differential Entropy and Higuchi's Fractal Dimension
DEAP dataset
EEG signals
Emotion classification
Feature extraction
Machine learning
Title A comparative analysis of emotion recognition from EEG signals using temporal features and hyperparameter-tuned machine learning techniques
URI https://dx.doi.org/10.1016/j.mex.2025.103468
https://www.ncbi.nlm.nih.gov/pubmed/40687354
https://www.proquest.com/docview/3231903616
https://doaj.org/article/5201c155f406484692221840441b7aa4
Volume 15
WOSCitedRecordID wos001532775200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2215-0161
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001343142
  issn: 2215-0161
  databaseCode: DOA
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2215-0161
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001343142
  issn: 2215-0161
  databaseCode: M~E
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT-MwEB4t1WrFBcGyj_KSV-KEFG0Sp3F8LKjAYVvtAVBvluM4LGjboj4QJ_4Af5oZ2yndw8KFSxVVrTPyjPPNZD5_Bji01J3LbBKVnN5WaV1GssR1lea4yqlqTt1emKtfYjAohkP5e-WoL-KEeXlgP3E_O4hQBkGvRuTJECwlAhpVJQjjpdDaKYFi1rNSTLm3KxyBMUubNqYjdI3sA9aDaYf2mWckrboCRE6v_x88-l--6XDndBM2QsLIut7QLfhgx5_hUz-0xLfhqcvMi4I300FkhE1qZv0RPWxJEsJr2k7Cer0zRsQNDD1GxPdrFhSq_rLaOqXPGQ5UsT9YpE5p6BGRZqL5Ap_JbOTol5aF8ybov0EGdvYFLk97FyfnUThhITKYiM0jnVkpapHIupZCJkZKwzkvO1JrXMm5yeLCFlaIWKSpiStLPc8qFpX08qE1_wqt8WRsvwNLSNVG51VV4MRrmRZlqk1cF1XOjcYHRxuOmulWd15IQzUMs1uFvlHkG-V904Zjcsjyh6SB7b7AyFAhMtRbkdGGrHGnCumETxNwqJvX7v2jcb3CpUb9Ez22k8VMccyFJSJ-krfhm4-JpYVoQyF4J9t5D8t3YZ0M8qyZPWjNpwu7Dx_N_fxmNj2ANTEsDly842f_sfcMmaQBSw
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+comparative+analysis+of+emotion+recognition+from+EEG+signals+using+temporal+features+and+hyperparameter-tuned+machine+learning+techniques&rft.jtitle=MethodsX&rft.au=Hasan%2C+Rabita&rft.au=Islam%2C+Sheikh+Md.+Rabiul&rft.date=2025-12-01&rft.issn=2215-0161&rft.eissn=2215-0161&rft.volume=15&rft.spage=103468&rft_id=info:doi/10.1016%2Fj.mex.2025.103468&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_mex_2025_103468
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2215-0161&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2215-0161&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2215-0161&client=summon