Skip to main content

Advertisement

Springer Nature Link
Log in

Self-attention-based 1DCNN model for multiclass EEG emotion classification

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

In EEG emotion recognition, there is a problem of time-consuming and laborious parameter optimization when mapping one-dimensional data to two-dimensional or three-dimensional data for processing. This paper proposes an IDCNN model based on frequency band and region attention mechanisms. Features are extracted from EEG signals, and optimal feature selection is performed using 1test. A novel 1DCNN emotion recognition model is designed based on the extracted features, providing interpretability for parameter selection and convolution operations. Finally, considering the different emotional response capabilities of the left and right brain regions, we propose a brain region attention mechanism combined with frequency band attention mechanisms to better focus on brain regions and frequency bands relevant to emotion. The proposed Self\(_{AT}\)-1DCNN model achieves average recognition rates of \(94.01 \%\) and \(93.55 \%\) in two-class experiments on valence and arousal dimensions of DEAP EEG emotion data, and an average recognition rate of \(89.38 \%\) in four-class experiments, improving by \(2.96 \%\), \(3.31 \%\), and \(7.69 \%\), respectively, compared to existing 1DCNN models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Data Availability

Publicly available datasets are used and available on request.

References

  1. Bergil E, Oral C, Ergül EU (2023) Classification of arithmetic mental task performances using EEG and ECG signals. J Supercomput 79(14):15535–15547. https://doi.org/10.1007/s11227-023-05294-0

    Article  Google Scholar 

  2. Awasthi D, Khare P, Srivastava VK (2023) Internet of medical things-based authentication for an optimized watermarking of encrypted EEG. J Supercomput 80(3):2970–3004. https://doi.org/10.1007/s11227-023-05566-9

    Article  MATH  Google Scholar 

  3. Pan D, Zheng H, Xu F, Ouyang Y, Jia Z, Wang C, Zeng H (2023) MSFR-GCN: A multi-scale feature reconstruction graph convolutional network for EEG emotion and cognition recognition. IEEE Trans Neural Syst Rehabil Eng 31:3245–3254. https://doi.org/10.1109/TNSRE.2023.3304660

    Article  MATH  Google Scholar 

  4. Jafari M, Shoeibi A, Khodatars M, Bagherzadeh S, Shalbaf A, Garcia DL, Gorriz JM, Acharya UR (2023) Emotion recognition in EEG signals using deep learning methods: A review. Comput Biol Med 165:107450. https://doi.org/10.1016/j.compbiomed.2023.107450

    Article  Google Scholar 

  5. Khushboo Singh MKA, Pandey M (2023) Subject-wise data augmentation based on balancing factor for quaternary emotion recognition through hybrid deep learning model. Biomed Signal Process Cont 86:105075. https://doi.org/10.1016/j.bspc.2023.105075

    Article  Google Scholar 

  6. Singh K, Ahirwal M, Pandey M (2022) Quaternary classification of emotions based on electroencephalogram signals using hybrid deep learning model. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-022-04495-4

    Article  MATH  Google Scholar 

  7. Prabhakar SK, Lee S-W (2022) SASDL and RBATQ: Sparse autoencoder with swarm based deep learning and reinforcement based q-learning for EEG classification. IEEE Open J Eng Med Biol 3:58–68. https://doi.org/10.1109/OJEMB.2022.3161837

    Article  MATH  Google Scholar 

  8. Zhu H, Forenzo D, He B (2022) On the deep learning models for EEG-based brain-computer interface using motor imagery. IEEE Trans Neural Syst Rehabil Eng 30:2283–2291. https://doi.org/10.1109/TNSRE.2022.3198041

    Article  MATH  Google Scholar 

  9. Wang H, Zhu X, Chen T, Li C, Song L (2023) Rethinking saliency map: A context-aware perturbation method to explain EEG-based deep learning model. IEEE Trans Biomed Eng 70(5):1462–1472. https://doi.org/10.1109/TBME.2022.3218116

    Article  MATH  Google Scholar 

  10. Guo Z, Wang J, Jing T, Fu L (2024) Investigating the interpretability of schizophrenia EEG mechanism through a 3dcnn-based hidden layer features aggregation framework. Comput Methods Progr Biomed 247:108105. https://doi.org/10.1016/j.cmpb.2024.108105

    Article  Google Scholar 

  11. Han L, Zhang X, Yin J (2024) EEG emotion recognition based on the timesnet fusion model. Appl Soft Comput 159:111635. https://doi.org/10.1016/j.asoc.2024.111635

    Article  MATH  Google Scholar 

  12. Feng L, Cheng C, Zhao M, Deng H, Zhang Y (2022) EEG-based emotion recognition using spatial-temporal graph convolutional lSTM with attention mechanism. IEEE J Biomed Health Inf 26(11):5406–5417. https://doi.org/10.1109/JBHI.2022.3198688

    Article  MATH  Google Scholar 

  13. Liu B, Guo J, Chen CLP, Wu X, Zhang T (2024) Fine-grained interpretability for EEG emotion recognition: Concat-aided grad-cam and systematic brain functional network. IEEE Trans Affect Comput 15(2):671–684. https://doi.org/10.1109/TAFFC.2023.3288885

    Article  MATH  Google Scholar 

  14. Yang C, Zhang H, Zhang S, Han X, Gao S, Gao X (2020) The spatio-temporal equalization for evoked or event-related potential detection in multichannel EEG data. IEEE Trans Biomed Eng 67(8):2397–2414. https://doi.org/10.1109/TBME.2019.2961743

    Article  MATH  Google Scholar 

  15. Majid Mehmood R, Du R, Lee HJ (2017) Optimal feature selection and deep learning ensembles method for emotion recognition from human brain EEG sensors. IEEE Access 5:14797–14806. https://doi.org/10.1109/ACCESS.2017.2724555

    Article  Google Scholar 

  16. Liu Q, Chen Y-F, Fan S-Z, Abbod MF, Shieh J-S (2017) Quasi-periodicities detection using phase-rectified signal averaging in EEG signals as a depth of anesthesia monitor. IEEE Trans Neural Syst Rehabil Eng 25(10):1773–1784. https://doi.org/10.1109/TNSRE.2017.2690449

    Article  MATH  Google Scholar 

  17. Sun C, Li H, Xu C, Ma L, Li H (2024) Adaptively optimized masking EMD for separating intrinsic oscillatory modes of nonstationary signals. IEEE Signal Process Lett 31:216–220. https://doi.org/10.1109/LSP.2023.3347146

    Article  MATH  Google Scholar 

  18. Keller SM, Beltrani S, Gschwandtner U, Meyer A, Toloraia K, Fuhr P (2021) P 38. mild cognitive impairment in patients with parkinson’s disease is characterized by a strong coupling of EEG signal complexity and band power. Clin Neurophysiol 132(8):17. https://doi.org/10.1016/j.clinph.2021.02.357

    Article  Google Scholar 

  19. Gao D, Li P, Wang M, Liang Y, Liu S, Zhou J, Wang L, Zhang Y (2024) Csf-gtnet: A novel multi-dimensional feature fusion network based on convnext-gelu- bilstm for EEG-signals-enabled fatigue driving detection. IEEE J Biomed Health Inf 28(5):2558–2568. https://doi.org/10.1109/JBHI.2023.3240891

    Article  MATH  Google Scholar 

  20. Smith AE, Chau A, Greaves D, Keage HAD, Feuerriegel D (2023) Resting EEG power spectra across middle to late life: associations with age, cognition, apoeÉ\(>4\) carriage, and cardiometabolic burden. Neurobiol Aging 130:93–102. https://doi.org/10.1016/j.neurobiolaging.2023.06.004

    Article  Google Scholar 

  21. Li H, Liao J, Wang H, Zhan CA, Yang F (2024) EEG power spectra parameterization and adaptive channel selection towards semi-supervised seizure prediction. Comput Biol Med 175:108510. https://doi.org/10.1016/j.compbiomed.2024.108510

    Article  MATH  Google Scholar 

  22. Liu G, Wen Y, Hsiao JH, Zhang D, Tian L, Zhou W (2024) EEG-based familiar and unfamiliar face classification using filter-bank differential entropy features. IEEE Trans Human-Mach Syst 54(1):44–55. https://doi.org/10.1109/THMS.2023.3332209

    Article  Google Scholar 

  23. Ye Z, Jing Y, Wang Q, Li P, Liu Z, Yan M, Zhang Y, Dongrui G (2023) Emotion recognition based on convolutional gated recurrent units with attention. Connect Sci. https://doi.org/10.1080/09540091.2023.2289833

    Article  MATH  Google Scholar 

  24. Krishna R, Das K, Meena HK, Pachori RB (2023) Spectral graph wavelet transform-based feature representation for automated classification of emotions from EEG signal. IEEE Sens J 23(24):31229–31236. https://doi.org/10.1109/JSEN.2023.3330090

    Article  Google Scholar 

  25. Fabbiano L, Vacca G, Morello R, De Capua C (2013) An innovative strategy for correctly interpreting simultaneous acquisition of EEG signals and FMRI images. IEEE Sens J 13(9):3175–3181. https://doi.org/10.1109/JSEN.2013.2261294

    Article  Google Scholar 

  26. Li W, Fang C, Zhu Z, Chen C, Song A (2024) Fractal spiking neural network scheme for EEG-based emotion recognition. IEEE J Trans Eng Health Med 12:106–118. https://doi.org/10.1109/JTEHM.2023.3320132

    Article  MATH  Google Scholar 

  27. Hassan MM, Alam MGR, Uddin MZ, Huda S, Almogren A, Fortino G (2019) Human emotion recognition using deep belief network architecture. Inf Fus 51:10–18. https://doi.org/10.1016/j.inffus.2018.10.009

    Article  Google Scholar 

  28. Wang Z, Wang Y, Hu C, Yin Z, Song Y (2022) Transformers for EEG-based emotion recognition: a hierarchical spatial information learning model. IEEE Sens J 22(5):4359–4368. https://doi.org/10.1109/JSEN.2022.3144317

    Article  MATH  Google Scholar 

  29. Gagliardi G, Alfeo AL, Catrambone V, Candia-Rivera D, Cimino MGCA, Valenza G (2023) Improving emotion recognition systems by exploiting the spatial information of EEG sensors. IEEE Access 11:39544–39554. https://doi.org/10.1109/ACCESS.2023.3268233

    Article  Google Scholar 

  30. Sampathila N, Tanmay T, GS SK (2022) Wavelet based machine learning models for classification of human emotions using EEG signal. Meas Sens 24:100554. https://doi.org/10.1016/j.measen.2022.100554

    Article  Google Scholar 

  31. Zhang X, Cheng X (2024) A transformer convolutional network with the method of image segmentation for EEG-based emotion recognition. IEEE Signal Process Lett 31:401–405. https://doi.org/10.1109/LSP.2024.3353679

    Article  MATH  Google Scholar 

  32. Liu S, Wang X, Zhao L, Li B, Hu W, Yu J, Zhang Y-D (2022) 3dcann: A spatio-temporal convolution attention neural network for EEG emotion recognition. IEEE J Biomed Health Inf 26(11):5321–5331. https://doi.org/10.1109/JBHI.2021.3083525

    Article  MATH  Google Scholar 

  33. Gilakjani SS, Osman HA (2024) A graph neural network for EEG-based emotion recognition with contrastive learning and generative adversarial neural network data augmentation. IEEE Access 12:113–130. https://doi.org/10.1109/ACCESS.2023.3344476

    Article  MATH  Google Scholar 

  34. Song T, Zheng W, Song P, Cui Z (2020) EEG emotion recognition using dynamical graph convolutional neural networks. IEEE Trans Affect Comput 11(3):532–541. https://doi.org/10.1109/TAFFC.2018.2817622

    Article  MATH  Google Scholar 

  35. Kong W, Qiu M, Li M, Jin X, Zhu L (2023) Causal graph convolutional neural network for emotion recognition. IEEE Trans Cognitive Dev Syst 15(4):1686–1693. https://doi.org/10.1109/TCDS.2022.3175538

    Article  MATH  Google Scholar 

  36. Pan J, Liang R, He Z, Li J, Liang Y, Zhou X, He Y, Li Y (2024) St-scgnn: A spatio-temporal self-constructing graph neural network for cross-subject EEG-based emotion recognition and consciousness detection. IEEE J Biomed Health Inf 28(2):777–788. https://doi.org/10.1109/JBHI.2023.3335854

    Article  MATH  Google Scholar 

  37. Zhang T, Zheng W, Cui Z, Zong Y, Li Y (2019) Spatial temporal recurrent neural network for emotion recognition. IEEE Trans Cybern 49(3):839–847. https://doi.org/10.1109/TCYB.2017.2788081

    Article  MATH  Google Scholar 

  38. Liu S, Zhao Y, An Y, Zhao J, Wang S-H, Yan J (2023) Glfanet: A global to local feature aggregation network for EEG emotion recognition. Biomed Signal Process Control 85:104799. https://doi.org/10.1016/j.bspc.2023.104799

    Article  MATH  Google Scholar 

  39. Liu Y-T, Lin Y-Y, Wu S-L, Chuang C-H, Lin C-T (2016) Brain dynamics in predicting driving fatigue using a recurrent self-evolving fuzzy neural network. IEEE Trans Neural Netw Learn Syst 27(2):347–360. https://doi.org/10.1109/TNNLS.2015.2496330

    Article  MATH  Google Scholar 

  40. Zhang P, Wang X, Zhang W, Chen J (2019) Learning spatial spectral temporal features with recurrent 3d convolutional neural networks for cross-task mental workload assessment. IEEE Trans Neural Syst Rehabil Eng 27(1):31–42. https://doi.org/10.1109/TNSRE.2018.2884641

    Article  MATH  Google Scholar 

  41. Huang W, Xue Y, Hu L, Liuli H (2020) S-EEGENT: Electroencephalogram signal classification based on a separable convolution neural network with bilinear interpolation. IEEE Access 8:131636–131646. https://doi.org/10.1109/ACCESS.2020.3009665

    Article  Google Scholar 

  42. Khare SK, Bajaj V (2021) Time–frequency representation and convolutional neural network-based emotion recognition. IEEE Trans Neural Netw Learn Syst 32(7):2901–2909. https://doi.org/10.1109/TNNLS.2020.3008938

    Article  MATH  Google Scholar 

  43. Çelebi M, Öztürk S, Kaplan K (2024) An emotion recognition method based on EWT-3d-CNN-BiLSTM-GRU-at model. Comput Biol Med 169:107954. https://doi.org/10.1016/j.compbiomed.2024.107954

    Article  Google Scholar 

  44. Chu W, Fu B, Xia Y, Liu Y (2023) EEG-based emotion recognition using spatial-temporal connectivity. IEEE Access 11:92496–92504. https://doi.org/10.1109/ACCESS.2023.3308811

    Article  Google Scholar 

  45. Wang Y, Zhou Y, Lu W, Wu Q, Li Q, Zhang R (2024) Ac-cfc: An attention-based convolutional closed-form continuous-time neural network for raw multi-channel EEG-based emotion recognition. Biomed Signal Process Control 94:106249. https://doi.org/10.1016/j.bspc.2024.106249

    Article  Google Scholar 

  46. Li R, Ren C, Li C, Zhao N, Lu D, Zhang X (2023) SSTD: A novel spatio-temporal demographic network for EEG-based emotion recognition. IEEE Trans Computat Social Syst 10(1):376–387. https://doi.org/10.1109/TCSS.2022.3188891

    Article  MATH  Google Scholar 

  47. Miao M, Zheng L, Xu B, Yang Z, Hu W (2023) A multiple frequency bands parallel spatial temporal 3d deep residual learning framework for EEG-based emotion recognition. Biomed Signal Process Control 79:104141. https://doi.org/10.1016/j.bspc.2022.104141

    Article  MATH  Google Scholar 

  48. Koelstra S, Muhl C, Soleymani M, Lee J-S, Yazdani A, Ebrahimi T, Pun T, Nijholt A, Patras I (2012) Deap: A database for emotion analysis; using physiological signals. IEEE Trans Affect Comput 3(1):18–31. https://doi.org/10.1109/T-AFFC.2011.15

    Article  Google Scholar 

  49. Garg D, Verma GK, Singh AK (2024) EEG-based emotion recognition using mobilenet recurrent neural network with time-frequency features. Appl Soft Comput 154:111338. https://doi.org/10.1016/j.asoc.2024.111338

    Article  MATH  Google Scholar 

  50. Sarma P, Barma S (2021) Emotion recognition by distinguishing appropriate EEG segments based on random matrix theory. Biomed Signal Process Control 70:102991. https://doi.org/10.1016/j.bspc.2021.102991

    Article  MATH  Google Scholar 

  51. Cimtay Y, Ekmekcioglu E, Caglar-Ozhan S (2020) Cross-subject multimodal emotion recognition based on hybrid fusion. IEEE Access 8:168865–168878. https://doi.org/10.1109/ACCESS.2020.3023871

    Article  Google Scholar 

  52. Liu Z-T, Hu S-J, She J, Yang Z, Xu X (2023) Electroencephalogram emotion recognition using combined features in variational mode decomposition domain. IEEE Trans Cognitive Dev Syst 15(3):1595–1604. https://doi.org/10.1109/TCDS.2022.3233858

    Article  Google Scholar 

  53. Kumari E, Shukla MK, Pandey OJ, Yadav S (2023) Neuroaid: Emotion-based EEG analysis for Parkinson’s disease identification. IEEE Sens Lett 7(12):1–4. https://doi.org/10.1109/LSENS.2023.3335226

    Article  MATH  Google Scholar 

Download references

Funding

No funding.

Author information

Authors and Affiliations

  1. School of Computer Science and Engineering, VIT University, Bhopal, Madhya Pradesh, 466114, India

    Shrishtika Raikwar & A. V. R. Mayuri

Authors
  1. Shrishtika Raikwar
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. A. V. R. Mayuri
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

All authors contributed to the framework and design. Shrishtika Raikwar performed material preparation, data collection, analysis, writing—original draft preparation, and editing, whereas A.V.R. Mayuri reviewed and supervised the research in the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Shrishtika Raikwar.

Ethics declarations

Conflict of interest

The authors have no conflict of interest to declare that are relevant to the content of this article.

Ethics approval and consent to participate

Not applicable

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Raikwar, S., Mayuri, A.V.R. Self-attention-based 1DCNN model for multiclass EEG emotion classification. J Supercomput 81, 520 (2025). https://doi.org/10.1007/s11227-025-07015-1

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11227-025-07015-1

Keywords