An improved EEGNet for single-trial EEG classification in rapid serial visual presentation task
Open accessThe DOI matches its Crossref record; 31 of the 32 references it cites were found in a registry or an index.
Abstract
As a new type of brain–computer interface (BCI), the rapid serial visual presentation (RSVP) paradigm has attracted significant attention. The mechanism of RSVP is detecting the P300 component corresponding to the target image to realize fast and correct recognition. This paper proposed an improved EEGNet model to achieve good performance in offline and online data. Specifically, the data were filtered by xDAWN to enhance the signal-to-noise ratio of the electroencephalogram (EEG) signals. The focal loss function was used instead of the cross-entropy loss function to solve the classification problems of unbalanced samples. Additionally, the subject-specific data were fed to the improved EEGNet model to obtain a subject-specific model. We applied the proposed model at the BCI Controlled Robot Contest in World Robot Contest 2021 and won the second place. The average recall rate of the four participants reached 51.56% in triple classification. In the offline data benchmark dataset (64 subjects-RSVP tasks), the average recall rates of groups A and B reached 76.07% and 78.11%, respectively. We provided an alternative method to identify targets based on the RSVP paradigm.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Research has extensively explored the combination of xDAWN with classification algorithms, yielding promising results.”
From A Cascade xDAWN EEGNet Structure for Unified Visual-Evoked Related Potential Detection (2024) · cites this paper as [34]
In the citing paper
“Building upon our previous study [34], which utilized the combination of xDAWN with EEGNet and achieved the second place in the RSVP competition at the BCI Controlled Robot Contest during the 2021 World Robot Contest, we have further extended our previous work [34].”
From A Cascade xDAWN EEGNet Structure for Unified Visual-Evoked Related Potential Detection (2024) · cites this paper as [34]
Citations
Cites
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581 · cited 1×
“In this study, we used the focal loss [32] as the loss function.”
MethodXception: Deep Learning with Depthwise Separable Convolutions
Chollet, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.195 · Cited by 20,380 · cited 1×
“It includes the depthwise convolution and pointwise convolution layers [29] with parameter F2.”
BackgroundBrain–computer interfaces for communication and control
Wolpaw, J. R., Birbaumer, N., McFarland, D. J., Pfurtscheller, G., & Vaughan, T. M. (2002) · Clinical Neurophysiology · doi:10.1016/s1388-2457(02)00057-3 · Cited by 7,927
EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces
Lawhern, V. J., Solon, A. J., Waytowich, N. R., Gordon, S. M., Hung, C. P., & Lance, B. J. (2018) · Journal of Neural Engineering · doi:10.1088/1741-2552/aace8c · Cited by 5,115 · cited 2×
“EEGNet is a compact CNN architecture that can be applied to motor imagery classification tasks and ERP, feedback error-related negativity, and steady-state visual evoked potential (SSVEP), as demonstrated by Vernon Lawhern et al. [19].”
BackgroundEEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces
Lawhern, V. J., Solon, A. J., Waytowich, N. R., Gordon, S. M., Hung, C. P., & Lance, B. J. (2016) · arXiv · doi:10.48550/arxiv.1611.08024 · Cited by 5,105
Deep learning with convolutional neural networks for EEG decoding and visualization
Schirrmeister, R. T., Springenberg, J. T., Fiederer, L. D. J., Glasstetter, M., Eggensperger, K., Tangermann, M., Hutter, F., Burgard, W., & Ball, T. (2017) · Human Brain Mapping · doi:10.1002/hbm.23730 · Cited by 3,751
Striving for Simplicity: The All Convolutional Net
Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2014) · arXiv · doi:10.48550/arxiv.1412.6806 · Cited by 3,447
Cognitive and biological determinants of P300: an integrative review
Polich, J., & Kok, A. (1995) · Biological Psychology · doi:10.1016/0301-0511(95)05130-9 · Cited by 1,613 · cited 9×
“EEGNet is a compact CNN architecture that can be applied to motor imagery classification tasks and ERP, feedback error-related negativity, and steady-state visual evoked potential (SSVEP), as demonstrated by Vernon Lawhern et al. [19].”
BackgroundInfluentialA two-stage model for multiple target detection in rapid serial visual presentation.
Chun, M. M., & Potter, M. C. (1995) · Journal of Experimental Psychology: Human Perception and Performance · doi:10.1037//0096-1523.21.1.109 · Cited by 1,430 · cited 1×
“The rapid serial visual presentation (RSVP) paradigm [7] can induce endogenous ERP [8] in the brain according to the visual stimulation of the target image.”
BackgroundFilter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2b
Ang, K. K., Chin, Z. Y., Wang, C., Guan, C., & Zhang, H. (2012) · Frontiers in Neuroscience · doi:10.3389/fnins.2012.00039 · Cited by 1,264 · cited 1×
“The main idea of a two-step convolution sequence comes from the filter-bank common spatial pattern [27].”
BackgroundSelf-citationThe P300: Where in the Brain Is It Produced and What Does It Tell Us?
Linden, D. E. J. (2005) · The Neuroscientist · doi:10.1177/1073858405280524 · Cited by 833
Convolutional Neural Networks for P300 Detection with Application to Brain-Computer Interfaces
Cecotti, H., & Graser, A. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.125 · Cited by 778 · cited 16×
“EEGNet is a compact CNN architecture that can be applied to motor imagery classification tasks and ERP, feedback error-related negativity, and steady-state visual evoked potential (SSVEP), as demonstrated by Vernon Lawhern et al. [19].”
MethodInfluentialSpatio-spectral filters for improving the classification of single trial EEG
Lemm, S., Blankertz, B., Curio, G., & Muller, K.-R. (2005) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2005.851521 · Cited by 643 · cited 1×
“Existing methods include the common spatial patterns algorithm and its derived common spatio-spectral pattern algorithm [9], common sparse spectral spatial pattern algorithm [10], common spatio-temporal pattern algorithm [11],”
MethodxDAWN Algorithm to Enhance Evoked Potentials: Application to Brain–Computer Interface
Rivet, B., Souloumiac, A., Attina, V., & Gibert, G. (2009) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2009.2012869 · Cited by 537 · cited 1×
“Therefore, not only is the SNR very low, but it is not easy to complete the classification task [25].”
BackgroundA Brain Controlled Wheelchair to Navigate in Familiar Environments
Rebsamen, B., Guan, C., Zhang, H., Wang, C., Teo, C., Ang, M. H., & Burdet, E. (2010) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2010.2049862 · Cited by 405
Self-citationCombined Optimization of Spatial and Temporal Filters for Improving Brain-Computer Interfacing
Dornhege, G., Blankertz, B., Krauledat, M., Losch, F., Curio, G., & Muller, K.-R. (2006) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2006.883649 · Cited by 394 · cited 1×
“Existing methods include the common spatial patterns algorithm and its derived common spatio-spectral pattern algorithm [9], common sparse spectral spatial pattern algorithm [10], common spatio-temporal pattern algorithm [11],”
Method(2012) · IEEE Pulse · doi:10.1109/mpul.2012.2203714 · Cited by 231
Deep learning based on Batch Normalization for P300 signal detection
Liu, M., Wu, W., Gu, Z., Yu, Z., Qi, F., & Li, Y. (2018) · Neurocomputing · doi:10.1016/j.neucom.2017.08.039 · Cited by 230 · cited 1×
“Since then, EEGNet [19], BN3 [20], MACRO [21], and other network models have been derived.”
BackgroundDESIGN OF ASSISTIVE WHEELCHAIR SYSTEM DIRECTLY STEERED BY HUMAN THOUGHTS
LI, J., LIANG, J., ZHAO, Q., LI, J., HONG, K., & ZHANG, L. (2013) · International Journal of Neural Systems · doi:10.1142/s0129065713500135 · Cited by 114 · cited 1×
“For people with disabilities, BCI has designed a braindriven wheelchair that can help and facilitate their movement [3, 4].”
BackgroundDiscriminative Canonical Pattern Matching for Single-Trial Classification of ERP Components
Xiao, X., Xu, M., Jin, J., Wang, Y., Jung, T.-P., & Ming, D. (2020) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2019.2958641 · Cited by 113 · cited 1×
“[16] proposed a feature classification method to discriminate”
MethodEEG-Based Seizure detection using linear graph convolution network with focal loss
Zhao, Y., Dong, C., Zhang, G., Wang, Y., Chen, X., Jia, W., Yuan, Q., Xu, F., & Zheng, Y. (2021) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2021.106277 · Cited by 105 · cited 1×
“For the problem of unbalanced samples, the focal loss function can reduce the weight of non-target samples to make the model focus more on the classification of target samples during training [33].”
BackgroundSliding HDCA: Single-Trial EEG Classification to Overcome and Quantify Temporal Variability
Marathe, A. R., Ries, A. J., & McDowell, K. (2014) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2014.2304884 · Cited by 72
Parameter Estimation in Softmax Decision-Making Models With Linear Objective Functions
Reverdy, P., & Leonard, N. E. (2016) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2015.2499244 · Cited by 69 · cited 1×
“In the softmax classification block, softmax with N units classifies the transmitted features, where N is the number of classes in the data [31].”
BackgroundControl or non-control state: that is the question! An asynchronous visual P300-based BCI approach
Pinegger, A., Faller, J., Halder, S., Wriessnegger, S. C., & Müller-Putz, G. R. (2015) · Journal of Neural Engineering · doi:10.1088/1741-2560/12/1/014001 · Cited by 55 · cited 1×
“Event-related potential (ERP)-based non-invasive BCI has been widely used in different EEG signals [5].”
BackgroundSajda, P., Gerson, A., & Parra, L. (2003) · First International IEEE EMBS Conference on Neural Engineering, 2003. Conference Proceedings. · doi:10.1109/cne.2003.1196297 · Cited by 54 · cited 1×
“[13] applied hierarchical discriminant component analysis”
A Benchmark Dataset for RSVP-Based Brain–Computer Interfaces
Zhang, S., Wang, Y., Zhang, L., & Gao, X. (2020) · Frontiers in Neuroscience · doi:10.3389/fnins.2020.568000 · Cited by 49 · cited 2×
“Additionally, we also used Tsinghua University’s A benchmark dataset for RSVP-based on BCI [24] as an offline dataset to compare the performance of these models.”
MethodCapsule Network for ERP Detection in Brain-Computer Interface
Ma, R., Yu, T., Zhong, X., Yu, Z. L., Li, Y., & Gu, Z. (2021) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2021.3070327 · Cited by 47 · cited 1×
“[22] proposed a model based on a capsule”
MethodBilinear common spatial pattern for single-trial ERP-based rapid serial visual presentation triage
Yu, K., Shen, K., Shao, S., Ng, W. C., & Li, X. (2012) · Journal of Neural Engineering · doi:10.1088/1741-2560/9/4/046013 · Cited by 35
Yu, K., Shen, K., Shao, S., Ng, W. C., Kwok, K., & Li, X. (2011) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2011.2158542 · Cited by 33 · cited 1×
“Existing methods include the common spatial patterns algorithm and its derived common spatio-spectral pattern algorithm [9], common sparse spectral spatial pattern algorithm [10], common spatio-temporal pattern algorithm [11],”
MethodMACRO: Multi-Attention Convolutional Recurrent Model for Subject-Independent ERP Detection
Lan, Z., Yan, C., Li, Z., Tang, D., & Xiang, X. (2021) · IEEE Signal Processing Letters · doi:10.1109/lsp.2021.3095761 · Cited by 27 · cited 1×
“Since then, EEGNet [19], BN3 [20], MACRO [21], and other network models have been derived.”
BackgroundIntelligent Human Computer Interaction
(2018) · Lecture notes in computer science · doi:10.1007/978-3-030-04021-5 · Cited by 3
Research works printed but not linked: 3
- Mathan S, 2005, Proceedings of the 11th International Conference on Human-Computer Interaction, 110
- Rivet B, 2011, 19th European Signal Processing Conference, 1382
- Dyrholm M, 2007, J Mach Learn Res, 8, 1097
Cited by
Wang, Z., Chen, C., Li, J., Wan, F., Sun, Y., & Wang, H. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3237319 · Cited by 75
“Zhang et al. proposed an improved EEGNet [19] that combined xDAWN saptial filtering with EEGNet [20] for the individually-calibrated rapid serial visual presentation (RSVP) task and won second place in the BCI Controlled Robot Contest at 2022 World Robot Con-test [21].”
MethodSelf-citationA Cascade xDAWN EEGNet Structure for Unified Visual-Evoked Related Potential Detection
Wang, H., Wang, Z., Sun, Y., Yuan, Z., Xu, T., & Li, J. (2024) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2024.3415474 · Cited by 20
“Building upon our previous study [34], which utilized the combination of xDAWN with EEGNet and achieved the second place in the RSVP competition at the BCI Controlled Robot Contest during the 2021 World Robot Contest, we have further extended our previous work [34].”
BackgroundMethodResultInfluentialSelf-citationLuo, J., Cui, W., Xu, S., Wang, L., Chen, H., & Li, Y. (2024) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2024.3359191 · Cited by 22
“Many researchers have proposed various temporal feature extraction methods to improve EEG classification performance in the RSVP task [8], [9].”
InfluentialSingle-trial P300 classification algorithm based on centralized multi-person data fusion CNN
Du, P., Li, P., Cheng, L., Li, X., & Su, J. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2023.1132290 · Cited by 17
“The P300 usually exhibits a low signal-to-noise ratio (SNR) (Zhang et al., 2022).”
BackgroundModel-agnostic meta-learning for EEG-based inter-subject emotion recognition
Chen, C., Fang, H., Yang, Y., & Zhou, Y. (2024) · Journal of Neural Engineering · doi:10.1088/1741-2552/ad9956 · Cited by 26
“We use four popular machine learning architectures in our experiments, including SVM [38], LeNet-5 [39], EEGNet [40, 41] and ResNet-18 [42, 43], which are further described below.”
Self-citation
Metadata
- Authors
- Zhang, H., Wang, Z., Yu, Y., Yin, H., Chen, C., & Wang, H.
- Affiliations
- Wuyi University (CN)
- Corresponding author
- Wang, Hongtao
- Venue
- Brain Science Advances
- Publisher
- Tsinghua University Press
- Published
- 2022-06
- Volume
- 8
- Issue
- 2
- Pages
- 111-126
- ISSN
- 2096-5958 (ISSN-L)
- OpenAlex
- W4283732837
- Cited by
- 30
- References
- 32
- Citations by year
- 2026: 3 · 2025: 7 · 2024: 16 · 2023: 4
- FWCI
- 3.48
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- Locations
- Brain Science Advances (publishedVersion, cc-by-nc)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Physical Sciences › Computer Science › Human-Computer Interaction › Gaze Tracking and Assistive Technology
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Keywords
- EEGNet, rapid serial visual presentation, P300, single-trial EEG classification, brain-computer interface, focal loss, class imbalance, subject-specific modeling, online BCI
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.