Skip to main content

Advertisement

Springer Nature Link
Log in

Classification of EEG event-related potentials based on channel attention mechanism

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

A Correction to this article was published on 20 January 2025

This article has been updated

Abstract

Event-related potentials (ERPs) represent the electroencephalographic responses to specific stimuli and are crucial for analyzing and understanding the processing of conscious activities within the human brain. Their classification is of significant importance in psychology and cognitive science. To address the multichannel and high signal-to-noise ratio characteristics of EEG signals, we introduce a single-subject short-distance ERP superposition averaging method for preprocessing raw data and propose an ERP-Xception model that integrates an ECA module with depth-separable convolutions. The ECA module was modified to reduce potential information loss through hierarchical dimensionality reduction, effectively extracting channel weight information. The Xception architecture was optimized to minimize model parameters and inference time. Additionally, a feature panning module was incorporated in parallel, allowing for minor channel displacements to enhance model generalizability and robustness. Our model achieved the highest F1-scores of 74.7%, 84.5%, 81.2%, 50.6%, 93.5%, and 88.5% across six ERP datasets, including ERN, LRP, N2PC, N170, N400, and P3, thereby validating its effectiveness and transferability.

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
Algorithm 1
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Data availability

The data used in this study came from ERP-CORE, an open event-related potential dataset. Specific information about the dataset can be found in article [32]. This study proposed the model code and the corresponding data preprocessing method can be downloaded on making: https://github.com/YiouTang/ERP_Xception.

Change history

  • 19 January 2025

    The original online version of this article was revised: Affiliation 1’s address has been revised and a name has been updated in the Author Contributions.

  • 20 January 2025

    A Correction to this paper has been published: https://doi.org/10.1007/s11227-024-06830-2

References

  1. Altaheri H, Muhammad G, Alsulaiman M et al (2023) Deep learning techniques for classification of electroencephalogram (EEG) motor imagery (MI) signals: a review. Neural Comput Appl 35(20):14681–14722

    Article  MATH  Google Scholar 

  2. Turakhonova GB (2022) Theoretical fundamentals of the concept in cognitive linguistics. Curr Res J Philol Sci 3(01):36–39

    MATH  Google Scholar 

  3. Antonicelli G, Rastelli S (2023) Event-related potentials in the study of l2 sentence processing: a scoping review of the decade 2010–2020. Lang Acquis 30(2):163–200

    Article  MATH  Google Scholar 

  4. Hossain KM, Islam MA, Hossain S et al (2023) Status of deep learning for EEG-based brain-computer interface applications. Front Comput Neurosci 16:1006763

    Article  MATH  Google Scholar 

  5. Sha’Abani MNAH, Fuad N, Jamal N, Ismail MF (2020). kNN and SVM classification for EEG: a review. In: InECCE2019: Proceedings of the 5th International Conference on Electrical, Control & Computer Engineering, pp. 555–565. Springer Singapore, Kuantan, Pahang, Malaysia

  6. Antoniou E, Bozios P, Christou V, Tzimourta KD, Kalafatakis K, Tsipouras G et al (2021) EEG-based eye movement recognition using brain-computer interface and random forests. Sensors 21(7):2339

    Article  Google Scholar 

  7. Mao WL, Fathurrahman HIK, Lee Y, Chang TW (2020) EEG dataset classification using CNN method. J Phys: Conf Ser 1456(1):012017

    Google Scholar 

  8. Supakar R, Satvaya P, Chakrabarti P (2022) A deep learning based model using RNN-LSTM for the detection of schizophrenia from EEG data. Comput Biol Med 151:106225

    Article  Google Scholar 

  9. Tian C, Ma Y, Cammon J, Fang F, Zhang Y, Meng M (2023) Dual-encoder VAE-GAN with spatiotemporal features for emotional EEG data augmentation. IEEE Trans Neural Syst Rehabil Eng 31:2018–2027

    Article  MATH  Google Scholar 

  10. Zhang R, Liu Q (2023) Learning with few samples in deep learning for image classification, a mini-review. Front Comput Neurosci 16:1075294

    Article  Google Scholar 

  11. Altaheri H, Muhammad G, Alsulaiman M, Amin SU, Altuwaijri GA, Abdul W et al (2023) Deep learning techniques for classification of electroencephalogram (EEG) motor imagery (MI) signals: a review. Neural Comput Appl 35(20):14681–14722

    Article  MATH  Google Scholar 

  12. Singh AK, Krishnan S (2023) Trends in EEG signal feature extraction applications. Front Artif Intell 5:1072801

    Article  Google Scholar 

  13. Cohen MX (2014) Analyzing Neural Time Series Data: Theory and Practice. MIT press, Cambridge

    Book  MATH  Google Scholar 

  14. Roach BJ, Mathalon DH (2008) Event-related EEG time-frequency analysis: an overview of measures and an analysis of early gamma band phase locking in schizophrenia. Schizophr Bull 34(5):907–926

    Article  MATH  Google Scholar 

  15. Molina M, Tardón LJ, Barbancho AM, De-Torres I, Barbancho I (2024) Enhanced average for event-related potential analysis using dynamic time warping. Biomed Signal Process Control 87:105531

    Article  MATH  Google Scholar 

  16. Marco-Pallares J, Cucurell D, Münte TF et al (2011) On the number of trials needed for a stable feedback-related negativity. Psychophysiology 48(6):852–860

    Article  Google Scholar 

  17. Petitjean F, Ketterlin A, Gançarski P (2011) A global averaging method for dynamic time warping, with applications to clustering. Pattern Recogn 44(3):678–693

    Article  MATH  Google Scholar 

  18. Cuturi M, Blondel M (2017) Soft-DTW: a differentiable loss function for time-series, pp 894–903

  19. Ma Y, Tang Y, Zeng Y et al (2023) An n400 identification method based on the combination of soft-dtw and transformer. Front Comput Neurosci 17:1120566

    Article  Google Scholar 

  20. Simbolon AI, Turnip A, Hutahaean J et al (2015) An experiment of lie detection based EEG-p300 classified by svm algorithm. In: 2015 International Conference on Automation, Cognitive Science, Optics, Micro Electro-Mechanical System, and Information Technology (ICACOMIT)

  21. Abou-Abbas L, Noordt S, Elsabbagh M (2021) Event related potential analysis using machine learning to predict diagnostic outcome of autism spectrum disorder. In: International Conference on Bioengineering and Biomedical Signal and Image Processing, pp 71–79

  22. Ma M, Feng S (2021) Classification and recognition of p300 event related potential based on convolutional neural network. J Phys: Conf Ser 1952(3):032007

    MATH  Google Scholar 

  23. Abibullaev B, Kunanbayev K, Zollanvari A (2022) Subject-independent classification of p300 event-related potentials using a small number of training subjects. IEEE Trans Human-Mach Syst 52(5):843–854

    Article  Google Scholar 

  24. Dubreuil-Vall L, Ruffini G, Camprodon JA (2020) Deep learning convolutional neural networks discriminate adult ADHD from healthy individuals on the basis of event-related spectral EEG. Front Neurosci 14:251

    Article  Google Scholar 

  25. Atchuthan NA, Clark H, Danyar MB et al (2023) Classification of noxious and non-noxious event-related potentials from s1 in pigs using a convolutional neural network. In: 2023 11th International IEEE/EMBS Conference on Neural Engineering (NER), pp 1–4

  26. Cecotti H, Jha G (2019). 3D convolutional neural networks for event-related potential detection. In: 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp 4160–4163

  27. Chou YT, Qiu TS, Zhong MJ (2018) Convolutional neural network based classification and recognition of p300 event-related potential. Chin J Biomed Eng 37(6):657–664

    MATH  Google Scholar 

  28. Yu HW, Xie J, He LS et al (2021) Convolutional neural network and support vector machine based event-related potential identification method. J Xi’an Jiaotong Univ

  29. Maddula R, Stivers J, Mousavi M et al (2017) Deep recurrent convolutional neural networks for classifying P300 BCI signals. In: GBCIC, pp 18–22

  30. Wang XL, Kan X, Fan YX (2022) Research on p300 event-related potential recognition classification based on LSTM-attention. Electron Sci Technol. https://doi.org/10.16180/j.cnki.issn1007-7820.2022.12.002

    Article  MATH  Google Scholar 

  31. Duru DG, Duru AD (2018) Classification of event Related potential patterns using deep learning. In: 2018 Medical Technologies National Congress (TIPTEKNO), pp 1–4

  32. Kappenman ES, Farrens JL, Zhang W et al (2021) ERP CORE: an open resource for human event-Related potential research. Neuroimage 225:117465

    Article  MATH  Google Scholar 

  33. Hinojosa JA, Mercado F, Carretié L (2015) N170 sensitivity to facial expression: a meta-analysis. Neurosci Biobehav Rev 55:498–509

    Article  Google Scholar 

  34. Qi K (2023) Investigating the relationship between N2pc and rapid saccadic eye movements

  35. Lepock JR, Sanches M, Ahmed S et al (2023) N400 event-related brain potential index of semantic processing and two-year clinical outcomes in persons at high risk for psychosis: a longitudinal study. Euro J Neurosci 59(8):1877–1888

    Article  MATH  Google Scholar 

  36. Paz V, Nicolaisen-Sobesky E, FernÃndez-Theoduloz G et al (2023) Event-related potentials of social comparisons in depression and social anxiety

  37. Ody E, Kircher T, Straube B et al (2023) Pre-movement event-related potentials and multivariate pattern of EEG encode action outcome prediction

  38. Antoniou K (2023) The ups and downs of bilingualism: a review of the literature on executive control using event-related potentials. Psychon Bulletin Rev 30(4):1187–1226

    Article  MATH  Google Scholar 

  39. Cuturi M, Vert JP, Birkenes O et al (2007) A kernel for time series based on global alignments. In: 2007 IEEE International Conference on Acoustics, Speech and Signal Processing-ICASSP’07 2, pp 413–416

  40. Kee CY, Ponnambalam SG, Loo CK (2015) Multi-objective genetic algorithm as channel selection method for P300 and motor imagery data set. Neurocomputing 161:120–131

    Article  Google Scholar 

  41. Wang HT, Huang H, He YB et al (2019) Analysis method of event-related potential EEG signal based on denoising autoencoder neural network. Control Theory Appl 36(4)

  42. Ahn D, Kim HJ, Kim S et al (2022) Shift-ViT: siamese vision transformer using shifted branches. In: 2022 37th International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC), pp 259–261

  43. Lotey T, Keserwani P, Wasnik G et al (2022) Cross-session motor imagery EEG classification using self-supervised contrastive learning. In: 2022 26th International Conference on Pattern Recognition (ICPR), pp 975–981

Download references

Funding

This research was funded by: 2024 Key Project of Humanities and Social Sciences Research of Chongqing Education Commission,“Research on Rural Teachers’ Digital Competence and Improvement Path under the Digital Transformation of Education” (Project No.: 24SKGH056); 2024 Chongqing Graduate Education Reform Research Project “Logical Model and Evaluation System of ’Artificial Intelligence +’ Subject Group: A Case Study of Wisdom Education Subject Group” (Project No.: yjg242021); Chongqing Education Science “14th Five-Year Plan” 2024 Teaching reform research project “AI Enabling Teaching Paradigm Innovation and Practice Exploration” (Project number: K24ZG2050087).

Author information

Authors and Affiliations

  1. School of Computer Science and Engineering, Guangzhou Institute of Science and Technology, Baiyun District Taihe Xingtai Three road, Guangzhou, 510540, China

    Yiou Tang

  2. College of Computer and Information Science, Chongqing Normal University, University Town Central Road, Chongqing, 401331, China

    Yan Ma, Chunling Xiao, Min Wu & Guoyuan Zeng

  3. Wisdom Education Research Institute, Chongqing Normal University, University Town Central Road, Chongqing, 401331, China

    Yan Ma

Authors
  1. Yiou Tang
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Yan Ma
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Chunling Xiao
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Min Wu
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Guoyuan Zeng
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

Yiou Tang was responsible for designing and implementing the experiments and the overall writing of the manuscript. Yan Ma was responsible for the review and revision of the manuscript. Guoyuan Zeng, Chunling Xiao, and Min Wu were responsible for some of the programming and data visualization. All authors contributed to the article and approved the submitted version.

Corresponding author

Correspondence to Yan Ma.

Ethics declarations

Conflict of interest

The authors declare that there is no conflict of interest, financial or otherwise, that could have influenced the research process, analysis, and interpretation of the findings presented in this paper.

Ethical approval

This study does not involve the direct participation of human subjects or animals, thereby obviating the need for ethical approval. The utilization of data in this research is derived from the publicly accessible ERP-CORE dataset, which serves as an open and extensively employed resource for scholarly investigations.

Additional information

Publisher's Note

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

The original online version of this article was revised: Affiliation 1’s address has been revised and a name has been updated in the Author Contributions.

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

Tang, Y., Ma, Y., Xiao, C. et al. Classification of EEG event-related potentials based on channel attention mechanism. J Supercomput 81, 126 (2025). https://doi.org/10.1007/s11227-024-06627-3

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11227-024-06627-3

Keywords