Deep learning for electroencephalography emotion recognition

Hesamoddin Pourrostami; Mohammad M. AlyanNezhadi; Mousa Nazari; Shahab S. Band; Amir Mosavi; Hesamoddin Pourrostami; Mohammad M. AlyanNezhadi; Mousa Nazari; Shahab S. Band; Amir Mosavi

doi:10.3934/publichealth.2025041

AIMS Public Health

2025, Volume 12, Issue 3: 812-834. doi: 10.3934/publichealth.2025041

Previous Article Next Article

Research article

Deep learning for electroencephalography emotion recognition

1.
Department of Computer Science, University of Science and Technology of Mazandaran, Behshahr, Iran
2.
Department of Information Management, International Graduate School of Artificial Intelligence, National Yunlin University of Science and Technology, Douliu, Taiwan
3.
John Von Neumann Faculty of Informatics, Obuda University, Budapest, Hungary
4.
Institute of the Information Society, Ludovika University of Public Service, Budapest, Hungary
5.
Abylkas Saginov Karaganda Technical University, Karaganda, Kazakhstan
6.
Faculty of Economics and Informatics, Univerzita J. Selyeho Komarom, Slovakia

Received: 15 April 2025 Revised: 10 June 2025 Accepted: 02 July 2025 Published: 06 August 2025

This study presents an Electroencephalography (EEG) emotion recognition using a long short-term memory (LSTM)-based method. Our proposed method selects window sizes and overlaps to divide the EEG data into segments, which optimally captures subtle signal changes. A Bidirectional LSTM (BiLSTM) layer is added to standard LSTM layers to better detect forward and backward patterns in the data. By using this dual-layer setup, we aim to improve both the feature extraction and the classification accuracy. The model was tested on the Database for Emotion Analysis using Physiological signals (DEAP) dataset and showed acceptable accuracy across emotional dimensions: arousal (94.0%), liking (98.9%), dominance (95.3%), and valence (99.6%). Our results suggest that the model better supports emotion recognition and has potential for mental health monitoring and adaptive therapy.
- emotion recognition,
- electroencephalography,
- human-computer interaction,
- machine learning,
- artificial intelligence,
- big data,
- data science,
- applied AI
Citation: Hesamoddin Pourrostami, Mohammad M. AlyanNezhadi, Mousa Nazari, Shahab S. Band, Amir Mosavi. Deep learning for electroencephalography emotion recognition[J]. AIMS Public Health, 2025, 12(3): 812-834. doi: 10.3934/publichealth.2025041

Related Papers:

Abstract

This study presents an Electroencephalography (EEG) emotion recognition using a long short-term memory (LSTM)-based method. Our proposed method selects window sizes and overlaps to divide the EEG data into segments, which optimally captures subtle signal changes. A Bidirectional LSTM (BiLSTM) layer is added to standard LSTM layers to better detect forward and backward patterns in the data. By using this dual-layer setup, we aim to improve both the feature extraction and the classification accuracy. The model was tested on the Database for Emotion Analysis using Physiological signals (DEAP) dataset and showed acceptable accuracy across emotional dimensions: arousal (94.0%), liking (98.9%), dominance (95.3%), and valence (99.6%). Our results suggest that the model better supports emotion recognition and has potential for mental health monitoring and adaptive therapy.

Authors' contributions

Hesamoddin Pourrostami contributed to the conceptualization, methodology, and data curation. Mohammad M. AlyanNezhadi was responsible for software implementation, formal analysis, and validation. Mousa Nazari contributed to project administration and original draft preparation. Shahab S. Band provided supervision and contributed to review and editing. Amir Mosavi contributed to supervision and manuscript review. All authors read and approved the final version of the manuscript.

Conflict of interest

Shahab S. Band is an editorial board member for AIMS Public Health. He was not involved in the editorial review or the decision to publish this article. All authors declare that there are no competing interests.

References

[1]	Kamble KS, Sengupta J (2023) A comprehensive survey on emotion recognition based on electroencephalograph (EEG) signals. Multimed Tools Appl 82: 27269-27304. https://doi.org/10.1007/s11042-023-14489-9
[2]	Wang X, Ren Y, Luo Z, et al. (2023) Deep learning-based EEG emotion recognition: Current trends and future perspectives. Front Psychol 14: 1126994. https://doi.org/10.3389/fpsyg.2023.1126994
[3]	Yu C, Wang M (2022) Survey of emotion recognition methods using EEG information. Cogn Robot 2: 132-146. https://doi.org/10.1016/j.cogr.2022.06.001
[4]	Zhang Y, Wang XA, Jiang W, et al. (2025) An Efficient and Secure Data Audit Scheme for Cloud-Based EHRs with Recoverable and Batch Auditing. Comput Mater Contin 83: p1533. https://doi.org/10.32604/cmc.2025.062910
[5]	Pepa L, Spalazzi L, Capecci M, et al. (2023) Automatic Emotion Recognition in Clinical Scenario: A Systematic Review of Methods. IEEE Trans Affect Comput 14: 1675-1695. https://doi.org/10.1109/TAFFC.2021.3128787
[6]	Fei Z, Yang E, Li DU, et al. (2020) Deep convolution network based emotion analysis towards mental health care. Neurocomputing 388: 212-227. https://doi.org/10.1016/j.neucom.2020.01.034
[7]	Tang L, Yuan P, Zhang D (2023) Emotional Experience during Human-Computer Interaction: A Survey. Int J Hum Comput Interact 40: 1845-1855. https://doi.org/10.1080/10447318.2023.2259710
[8]	Mohammadpour M, Nezhadi MMA, Hashemi SMR, et al. (2017) Music emotion recognition based on Wigner-Ville distribution feature extraction. IEEE : 0012-0016. https://doi.org/10.1109/KBEI.2017.8324963
[9]	Chunawale A, Bedekar DM (2020) Human Emotion Recognition using Physiological Signals: A Survey. MatSciRN: Other Biomaterials (Topic) . https://doi.org/10.2139/ssrn.3645402
[10]	Joy E, Joseph RB, Lakshmi MB, et al. (2021) Recent Survey on Emotion Recognition Using Physiological Signals. 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS) 1: 1858-1863. https://doi.org/10.1109/ICACCS51430.2021.9441999
[11]	Mert A, Akan A (2018) Emotion recognition based on time-frequency distribution of EEG signals using multivariate synchrosqueezing transform. Digit Signal Process 81: 106-115. https://doi.org/10.1016/j.dsp.2018.07.003
[12]	Chaddad A, Wu Y, Kateb R, et al. (2023) Electroencephalography Signal Processing: A Comprehensive Review and Analysis of Methods and Techniques. Sensors (Basel) 23: 6434. https://doi.org/10.3390/s23146434
[13]	Badajena JC, Sethi S, Dash SK, et al. (2023) A survey on EEG-based neurophysiological research for emotion recognition. CCF Trans Pervasive Comp Interact 5: 333-349. https://doi.org/10.1007/s42486-023-00129-6
[14]	Wang Y, Zhang B, Di L (2024) Research Progress of EEG-Based Emotion Recognition: A Survey. ACM Comput Surv 56: 1-49. https://doi.org/10.1145/3666002
[15]	Alarcão SM, Fonseca MJ (2019) Emotions Recognition Using EEG Signals: A Survey. IEEE Trans Affect Comput 10: 374-393. https://doi.org/10.1109/TAFFC.2017.2714671
[16]	Avola D, Cascio M, Cinque L, et al. (2022) Image Analysis and Processing – ICIAP 2022. Cham: Lecture Notes in Computer Science, Springer. https://doi.org/10.1007/978-3-031-06427-2_28
[17]	Gaddanakeri RD, Naik MM, Kulkarni S, et al. (2024) Analysis of EEG Signals in the DEAP Dataset for Emotion Recognition using Deep Learning Algortihms. 2024 IEEE 9th International Conference for Convergence in Technology (I2CT) : 1-7. https://doi.org/10.1109/I2CT61223.2024.10543369
[18]	Tao W, Li C, Song R, et al. (2023) EEG-based emotion recognition via channel-wise attention and self attention. IEEE Trans Affect Comput 14: 382-393. https://doi.org/10.1109/TAFFC.2020.3025777
[19]	Yuvaraj S, Franklin JV, Prakash V, et al. (2023) A Survey on Human Face Emotion Recognition using Machine Learning Models. 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS) 1: 1993-1996. https://doi.org/10.1109/ICACCS57279.2023.10112955
[20]	Yaacob M, Gunawan TS, Abu Bakar MIF, et al. (2024) Accurate EEG-Based Emotion Recognition using LSTM and BiLSTM Networks. 2024 IEEE 10th International Conference on Smart Instrumentation, Measurement and Applications (ICSIMA) : 13-18. https://doi.org/10.1109/ICSIMA62563.2024.10675567
[21]	Du X, Ma C, Zhang G, et al. (2022) An efficient LSTM network for emotion recognition from multichannel EEG signals. IEEE Trans Affect Comput 13: 1528-1540. https://doi.org/10.1109/TAFFC.2020.3013711
[22]	Sharma D, Kumar R, Jain A (2022) Breast cancer prediction based on neural networks and extra tree classifier using feature ensemble learning. Meas Sens 24: 100560. https://doi.org/10.1016/j.measen.2022.100560
[23]	Wibawa AD, Fatih N, Pamungkas Y, et al. (2022) Time and Frequency Domain Feature Selection Using Mutual Information for EEG-based Emotion Recognition. IEEE : 19-24. https://doi.org/10.23919/EECSI56542.2022.9946522
[24]	Nath D, Singh M, Sethia D, et al. (2020) An efficient approach to eeg-based emotion recognition using lstm network. IEEE : 88-92. https://doi.org/10.1109/CSPA48992.2020.9068691
[25]	Jiang W, Zhang Y, Han H, et al. (2025) Fuzzy ensemble-based federated learning for EEG-based emotion recognition in Internet of Medical Things. J Ind Inf Integr 44: 100789. https://doi.org/10.1016/j.jii.2025.100789
[26]	Saha PK, Rahman MA, Alam MK, et al. (2021) Common spatial pattern in frequency domain for feature extraction and classification of multichannel EEG signals. SN Comput Sci 2: 149. https://doi.org/10.1007/s42979-021-00586-9
[27]	Theresia DK, Ana D, Faqih A, et al. (2019) The back-propagation neural network classification of EEG signal using time frequency domain feature extraction. IEEE : 1-4. https://doi.org/10.1109/QIR.2019.8898288
[28]	Ahmad FK, Tuaimah ATN (2021) A comparative analysis of time-frequency feature extraction techniques for large scale electroencephalogram data. Int J 10: 14-24. https://doi.org/10.30534/ijatcse/2021/031012021
[29]	Alhagry S, Fahmy AA, El-Khoribi RA (2017) Emotion Recognition based on EEG using LSTM Recurrent Neural Network. Int J Adv Comput Sci Appl 8: 355-358. https://doi.org/10.14569/IJACSA.2017.081046
[30]	Pandey P, Seeja KR (2019) Subject independent emotion recognition from EEG using VMD and deep learning. J King Saud Univ Comput Inf Sci 34: 1730-1738. https://doi.org/10.1016/j.jksuci.2019.11.003
[31]	Song T, Zheng W, Song P, et al. (2018) EEG emotion recognition using dynamical graph convolutional neural networks. IEEE Trans Affect Comput 11: 532-541. https://doi.org/10.1109/TAFFC.2018.2817622
[32]	Feng X, Cong P, Dong L, et al. (2024) Channel attention convolutional aggregation network based on video-level features for EEG emotion recognition. Cogn Neurodyn 18: 1689-1707. https://doi.org/10.1007/s11571-023-10034-4
[33]	Algarni M, Saeed F, Al-Hadhrami T, et al. (2022) Deep learning-based approach for emotion recognition using electroencephalography (EEG) signals using bi-directional long short-term memory (Bi-LSTM). Sensors 22: 2976. https://doi.org/10.3390/s22082976
[34]	Chakravarthi B, Ng SC, Ezilarasan M, et al. (2022) EEG-based emotion recognition using hybrid CNN and LSTM classification. Front Comput Neurosci 16: 1019776. https://doi.org/10.3389/fncom.2022.1019776
[35]	Pauli MP, Pohl C, Golz M (2022) Optimal EEG Segmentation for Microsleep Detection Based on Machine Learning. Curr Dir Biomed Eng 8: 749-752. https://doi.org/10.1515/cdbme-2022-1191
[36]	Sharma R, Pachori RB, Sircar P (2020) Automated emotion recognition based on higher order statistics and deep learning algorithm. Biomed Signal Process Control 58: 101867. https://doi.org/10.1016/j.bspc.2020.101867
[37]	Cui H, Liu A, Zhang X, et al. (2020) EEG-based emotion recognition using an end-to-end regional-asymmetric convolutional neural network. Knowl Based Syst 205: 106243. https://doi.org/10.1016/j.knosys.2020.106243
[38]	Li M, Xu H, Liu X, et al. (2018) Emotion recognition from multichannel EEG signals using K-nearest neighbor classification. Technol Health Care 26: 509-519. https://doi.org/10.3233/THC-174836
[39]	Koelstra S, Muhl C, Soleymani M, et al. (2011) Deap: A database for emotion analysis; using physiological signals. IEEE Trans Affect Comput 3: 18-31. https://doi.org/10.1109/T-AFFC.2011.15
[40]	Zheng WL, Lu BL (2015) Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks. IEEE Trans Auton Ment Dev 7: 162-175. https://doi.org/10.1109/TAMD.2015.2431497
[41]	Duan RN, Zhu JY, Lu BL (2013) Differential entropy feature for EEG-based emotion classification. IEEE : 81-84. https://doi.org/10.1109/NER.2013.6695876
[42]	Gupta R, Laghari KuR, Falk TH (2016) Relevance vector classifier decision fusion and EEG graph-theoretic features for automatic affective state characterization. Neurocomputing 174: 875-884. https://doi.org/10.1016/j.neucom.2015.09.085
[43]	Garg A, Kapoor A, Bedi AK, et al. (2019) Merged LSTM Model for emotion classification using EEG signals. 2019 International Conference on Data Science and Engineering (ICDSE) : 139-143. https://doi.org/10.1109/ICDSE47409.2019.8971484
[44]	Topic A, Russo M (2021) Emotion recognition based on EEG feature maps through deep learning network. Eng Sci Technol Int J 24: 1442-1454. https://doi.org/10.1016/j.jestch.2021.03.012
[45]	Huang D, Chen S, Liu C, et al. (2021) Differences first in asymmetric brain: A bi-hemisphere discrepancy convolutional neural network for EEG emotion recognition. Neurocomputing 448: 140-151. https://doi.org/10.1016/j.neucom.2021.03.105
[46]	Kamble KS, Sengupta J (2022) Ensemble Machine Learning-Based Affective Computing for Emotion Recognition Using Dual-Decomposed EEG Signals. IEEE Sens J 22: 2496-2507. https://doi.org/10.1109/JSEN.2021.3135953
[47]	Zhang G, Yu M, Liu YJ, et al. (2023) SparseDGCNN: Recognizing Emotion From Multichannel EEG Signals. IEEE Trans Affect Comput 14: 537-548. https://doi.org/10.1109/TAFFC.2021.3051332
[48]	Li R, Ren C, Ge Y, et al. (2023) MTLFuseNet: a novel emotion recognition model based on deep latent feature fusion of EEG signals and multi-task learning. Knowl Based Syst 276: 110756. https://doi.org/10.1016/j.knosys.2023.110756
[49]	Jha SK, Suvvari S, Kumar M (2024) EEG-based emotion recognition: An in-depth analysis using DEAP and SEED Dataset. IEEE : 1816-1821. https://doi.org/10.23919/INDIACom61295.2024.10498398
[50]	Zhang H, Zuo T, Chen Z, et al. (2024) Evolutionary ensemble learning for EEG-based cross-subject emotion recognition. IEEE J Biomed Health Inform 28: 3872-3881. https://doi.org/10.1109/JBHI.2024.3384816
[51]	Wang Y, Wu Q, Wang S, et al. (2024) MI-EEG: Generalized model based on mutual information for EEG emotion recognition without adversarial training. Expert Syst Appl 244: 122777. https://doi.org/10.1016/j.eswa.2023.122777
[52]	Cheng C, Liu W, Feng L, et al. (2024) Dense graph convolutional with joint cross-attention network for multimodal emotion recognition. IEEE Trans Comput Soc Syst 11: 6672-6683. https://doi.org/10.1109/TCSS.2024.3412074
[53]	Liu S, Wang Z, An Y, et al. (2024) DA-CapsNet: A multi-branch capsule network based on adversarial domain adaption for cross-subject EEG emotion recognition. Knowl Based Syst 283: 111137. https://doi.org/10.1016/j.knosys.2023.111137
[54]	Shi S, Liu W (2025) Interactive multi-agent convolutional broad learning system for EEG emotion recognition. Expert Syst Appl 260: 125420. https://doi.org/10.1016/j.eswa.2024.125420
[55]	Li X, Song D, Zhang P, et al. (2018) Exploring EEG features in cross-subject emotion recognition. Front Neurosci 12: 162. https://doi.org/10.3389/fnins.2018.00162
[56]	Gupta V, Chopda MD, Pachori RB (2018) Cross-subject emotion recognition using flexible analytic wavelet transform from EEG signals. IEEE Sens J 19: 2266-2274. https://doi.org/10.1109/JSEN.2018.2883497
[57]	Yang F, Zhao X, Jiang W, et al. (2019) Multi-method fusion of cross-subject emotion recognition based on high-dimensional EEG features. Front Comput Neurosci 13: 53. https://doi.org/10.3389/fncom.2019.00053
[58]	Li P, Liu H, Si Y, et al. (2019) EEG based emotion recognition by combining functional connectivity network and local activations. IEEE Trans Biomed Eng 66: 2869-2881. https://doi.org/10.1109/TBME.2019.2897651
[59]	Wei C, Chen L, Song Z, et al. (2020) EEG-based emotion recognition using simple recurrent units network and ensemble learning. Biomed Signal Process Control 58: 101756. https://doi.org/10.1016/j.bspc.2019.101756
[60]	Cimtay Y, Ekmekcioglu E (2020) Investigating the use of pretrained convolutional neural network on cross-subject and cross-dataset EEG emotion recognition. Sensors 20: 2034. https://doi.org/10.3390/s20072034
[61]	Asghar MZ, Subhan F, Imran M, et al. (2020) Performance evaluation of supervised machine learning techniques for efficient detection of emotions from online content. Comput Mater Continua 63: 1093-1118. https://doi.org/10.32604/cmc.2020.07709
[62]	Wang F, Wu S, Zhang W, et al. (2020) Emotion recognition with convolutional neural network and EEG-based EFDMs. Neuropsychologia 146: 107506. https://doi.org/10.1016/j.neuropsychologia.2020.107506
[63]	Zhong P, Di Wang CM (2022) EEG-Based Emotion Recognition Using Regularized Graph Neural Networks. IEEE Trans Affect Comput 13: 1290-1301. https://doi.org/10.1109/TAFFC.2020.2994159
[64]	Shen X, Gan R, Wang K, et al. (2025) Dynamic-Attention-based EEG State Transition Modeling for Emotion Recognition. IEEE T Affect Comput . https://doi.org/10.1109/TAFFC.2025.3593630
[65]	Fernandes JVMR, Alexandria ARd, Marques JAL, et al. (2024) Emotion detection from EEG signals using machine deep learning models. Bioengineering 11: 782. https://doi.org/10.3390/bioengineering11080782
[66]	Marianna Koctúrová, Jozef Juhár (2021) EEG-based speech activity detection. Acta Polytech Hung 18: 65-77. https://doi.org/10.12700/APH.18.1.2021.1.5

Reader Comments

Your name:*

Email:*
© 2025 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)