Comparing user-dependent and user-independent training of CNN for SSVEP BCI
Open accessThe DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index.
Abstract
OBJECTIVE: We presented a comparative study on the training methodologies of a convolutional neural network (CNN) for the detection of steady-state visually evoked potentials (SSVEP). Two training scenarios were also compared: user-independent (UI) training and user-dependent (UD) training. APPROACH: The CNN was trained in both UD and UI scenarios on two types of features for SSVEP classification: magnitude spectrum features (M-CNN) and complex spectrum features (C-CNN). The canonical correlation analysis (CCA), widely used in SSVEP processing, was used as the baseline. Additional comparisons were performed with task-related components analysis (TRCA) and filter-bank canonical correlation analysis (FBCCA). The performance of the proposed CNN pipelines, CCA, FBCCA and TRCA were evaluated with two datasets: a seven-class SSVEP dataset collected on 21 healthy participants and a twelve-class publicly available SSVEP dataset collected on ten healthy participants. MAIN RESULTS: The UD based training methods consistently outperformed the UI methods when all other conditions were the same, as one would expect. However, the proposed UI-C-CNN approach performed similarly to the UD-M-CNN across all cases investigated on both datasets. On Dataset 1, the average accuracies of the different methods for 1 s window length were: CCA: 69.1% ± 10.8%, TRCA: 13.4% ± 1.5%, FBCCA: 64.8% ± 15.6%, UI-M-CNN: 73.5% ± 16.1%, UI-C-CNN: 81.6% ± 12.3%, UD-M-CNN: 87.8% ± 7.6% and UD-C-CNN: 92.5% ± 5%. On Dataset 2, the average accuracies of the different methods for data length of 1 s were: UD-C-CNN: 92.33% ± 11.1%, UD-M-CNN: 82.77% ± 16.7%, UI-C-CNN: 81.6% ± 18%, UI-M-CNN: 70.5% ± 22%, FBCCA: 67.1% ± 21%, CCA: 62.7% ± 21.5%, TRCA: 40.4% ± 14%. Using t-SNE, visualizing the features extracted by the CNN pipelines further revealed that the C-CNN method likely learned both the amplitude and phase related information from the SSVEP data for classification, resulting in superior performance than the M-CNN methods. The results suggested that UI-C-CNN method proposed in this study offers a good balance between performance and cost of training data. SIGNIFICANCE: The proposed C-CNN based method is a suitable candidate for SSVEP-based BCIs and provides an improved performance in both UD and UI training scenarios.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures







Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
(2008) · Journal of Machine Learning Research · Cited by 33,051
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
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 4×
“%) achieves the highest performance compared to CCA (62.7% ± 21.5%), UI-M-CNN (70.5% ± 22%), FBCCA (67.1% ± 21%), Compact-CNN (79% ± 15”
MethodInfluentialEEGNet: 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 · cited 4×
“%) achieves the highest performance compared to CCA (62.7% ± 21.5%), UI-M-CNN (70.5% ± 22%), FBCCA (67.1% ± 21%), Compact-CNN (79% ± 15”
MethodInfluentialA review of classification algorithms for EEG-based brain–computer interfaces: A 10 year update
Lotte, F., Bougrain, L., Cichocki, A., Clerc, M., Congedo, M., Rakotomamonjy, A., & Yger, F. (2018) · Journal of Neural Engineering · doi:10.1088/1741-2552/aab2f2 · Cited by 2,239 · cited 1×
“In a recent study, it was reported that a vast majority of published studies based on deep learning for EEG based BCIs did not compare the proposed techniques to state-of-the-art methods or they performed biased comparisons [40].”
BackgroundDeep learning for electroencephalogram (EEG) classification tasks: a review
Craik, A., He, Y., & Contreras-Vidal, J. L. (2019) · Journal of Neural Engineering · doi:10.1088/1741-2552/ab0ab5 · Cited by 1,758
Deep learning-based electroencephalography analysis: a systematic review
Roy, Y., Banville, H., Albuquerque, I., Gramfort, A., Falk, T. H., & Faubert, J. (2019) · Journal of Neural Engineering · doi:10.1088/1741-2552/ab260c · Cited by 1,532 · cited 1×
“One of the key challenges highlighted in deep learning based methods for BCIs is the reproducibility of results [18], where the authors provided guidelines such as: providing a clear description of the architecture, clearly describing the data used, use of existing datasets and evaluating the performance with baseline.”
BackgroundDeep learning for healthcare applications based on physiological signals: A review
Faust, O., Hagiwara, Y., Hong, T. J., Lih, O. S., & Acharya, U. R. (2018) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2018.04.005 · Cited by 1,026
High-speed spelling with a noninvasive brain–computer interface
Chen, X., Wang, Y., Nakanishi, M., Gao, X., Jung, T.-P., & Gao, S. (2015) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1508080112 · Cited by 969
A comprehensive review of EEG-based brain–computer interface paradigms
Abiri, R., Borhani, S., Sellers, E. W., Jiang, Y., & Zhao, X. (2019) · Journal of Neural Engineering · doi:10.1088/1741-2552/aaf12e · Cited by 946 · cited 1×
“BCIs can be classified into two broad categories: endogenous BCIs and exogenous BCIs [5].”
BackgroundFrequency recognition based on canonical correlation analysis for SSVEP-based BCIs
Lin, Z., Zhang, C., Wu, W., & Gao, X. (2007) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2006.889197 · Cited by 867
Renard, Y., Lotte, F., Gibert, G., Congedo, M., Maby, E., Delannoy, V., Bertrand, O., & Lécuyer, A. (2010) · Presence: Teleoperators and Virtual Environments · doi:10.1162/pres.19.1.35 · Cited by 830 · cited 1×
“The experimental protocol and stimulus were designed using OpenViBE software [36].”
Enhancing Detection of SSVEPs for a High-Speed Brain Speller Using Task-Related Component Analysis
Nakanishi, M., Wang, Y., Chen, X., Wang, Y.-T., Gao, X., & Jung, T.-P. (2018) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2017.2694818 · Cited by 813 · cited 2×
“TRCA is a UD training method used to obtain spatial filters that extract task related source activities from multi-channel EEG data [14].”
MethodChen, X., Wang, Y., Gao, S., Jung, T.-P., & Gao, X. (2015) · Journal of Neural Engineering · doi:10.1088/1741-2560/12/4/046008 · Cited by 805 · cited 2×
“Most widely used UD methods include: Combination method-CCA [12], Individual Template CCA (IT-CCA) [13] and more recently proposed Task Related Components Analysis (TRCA) [14]; UI methods include: Filter-Bank CCA (FBCCA) [15], Combined-tCCA and Adaptive Combined CCA (A3C) [16].”
MethodToward Brain-Computer Interfacing
(2007) · The MIT Press eBooks · doi:10.7551/mitpress/7493.001.0001 · Cited by 785
Bin, G., Gao, X., Yan, Z., Hong, B., & Gao, S. (2009) · Journal of Neural Engineering · doi:10.1088/1741-2560/6/4/046002 · Cited by 773 · cited 2×
“The most widely used training-free method for SSVEP classification is the canonical correlation analysis (CCA) [7, 8].”
BackgroundMethodA practical VEP-based brain-computer interface
Wang, Y., Wang, R., Gao, X., Hong, B., & Gao, S. (2006) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2006.875576 · Cited by 617 · cited 1×
“Each stimulus was white in colour and circular in shape as they were shown to elicit the better SSVEP responses than other shapes and colors [34, 35].”
BackgroundNakanishi, M., Wang, Y., Wang, Y.-T., & Jung, T.-P. (2015) · PLoS ONE · doi:10.1371/journal.pone.0140703 · Cited by 376 · cited 10×
“The proposed methods and other previously published methods were evaluated and compared on two datasets; a dataset acquired in our lab — Dataset 1 [33] and a public dataset — Dataset 2 [12].”
MethodInfluentialTowards an independent brain–computer interface using steady state visual evoked potentials
Allison, B. Z., McFarland, D. J., Schalk, G., Zheng, S. D., Jackson, M. M., & Wolpaw, J. R. (2008) · Clinical Neurophysiology · doi:10.1016/j.clinph.2007.09.121 · Cited by 327
Kwak, N.-S., Müller, K.-R., & Lee, S.-W. (2017) · PLOS ONE · doi:10.1371/journal.pone.0172578 · Cited by 272 · cited 5×
“Among these studies [21, 23, 24], have transformed the SSVEP trials into the frequency domain before providing it as an input to the CNN for classification.”
MethodInfluentialWaytowich, N., Lawhern, V. J., Garcia, J. O., Cummings, J., Faller, J., Sajda, P., & Vettel, J. M. (2018) · Journal of Neural Engineering · doi:10.1088/1741-2552/aae5d8 · Cited by 262
A Self-Paced and Calibration-Less SSVEP-Based Brain–Computer Interface Speller
Cecotti, H. (2010) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2009.2039594 · Cited by 253
BCI Demographics II: How Many (and What Kinds of) People Can Use a High-Frequency SSVEP BCI?
Volosyak, I., Valbuena, D., Luth, T., Malechka, T., & Graser, A. (2011) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2011.2121919 · Cited by 175 · cited 1×
“This method is particularly suited for SSVEP BCIs as these responses are more consistent across most humans, compared with other signal modalities of BCI such as sensory-motor rhythm [11].”
MethodTo train or not to train? A survey on training of feature extraction methods for SSVEP-based BCIs
Zerafa, R., Camilleri, T., Falzon, O., & Camilleri, K. P. (2018) · Journal of Neural Engineering · doi:10.1088/1741-2552/aaca6e · Cited by 160
Pan, J., Gao, X., Duan, F., Yan, Z., & Gao, S. (2011) · Journal of Neural Engineering · doi:10.1088/1741-2560/8/3/036027 · Cited by 139 · cited 1×
“Many studies have used a frequency-phase coding approach in the stimulus design [12, 27] and use the phase information as part of the classifier to detect the SSVEP targets [28, 29].”
MethodNguyen, H. V., To, D. D., & Lee, D. (2018) · IEEE Access · doi:10.1109/access.2018.2876645 · Cited by 128
An independent SSVEP-based brain–computer interface in locked-in syndrome
Lesenfants, D., Habbal, D., Lugo, Z., Lebeau, M., Horki, P., Amico, E., Pokorny, C., Gómez, F., Soddu, A., Müller-Putz, G., et al. (2014) · Journal of Neural Engineering · doi:10.1088/1741-2560/11/3/035002 · Cited by 127
On the Classification of SSVEP-Based Dry-EEG Signals via Convolutional Neural Networks
Aznan, N. K. N., Bonner, S., Connolly, J., Moubayed, N. A., & Breckon, T. P. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00631 · Cited by 105
Duszyk-Bogorodzka, A., Bierzyńska, M., Radzikowska, Z., Milanowski, P., Kuś, R., Suffczyński, P., Michalska, M., Łabęcki, M., Zwoliński, P., & Durka, P. J. (2014) · PLoS ONE · doi:10.1371/journal.pone.0112099 · Cited by 102 · cited 1×
“Each stimulus was white in colour and circular in shape as they were shown to elicit the better SSVEP responses than other shapes and colors [34, 35].”
BackgroundLASSO based stimulus frequency recognition model for SSVEP BCIs
Zhang, Y., Jin, J., Qing, X., Wang, B., & Wang, X. (2011) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2011.02.002 · Cited by 101 · cited 1×
“In [23], the authors showed that the CNN classification was better than LASSO [26] in decoding the SSVEP targets.”
MethodA Single-Channel SSVEP-Based BCI Speller Using Deep Learning
Nguyen, T.-H., & Chung, W.-Y. (2018) · IEEE Access · doi:10.1109/access.2018.2886759 · Cited by 99 · cited 5×
“In [23], the authors showed that the CNN classification was better than LASSO [26] in decoding the SSVEP targets.”
MethodInfluentialEnhancing detection of steady-state visual evoked potentials using individual training data
Wang, Y., Nakanishi, M., Wang, Y.-T., & Jung, T. (2014) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2014.6944263 · Cited by 96
Cecotti, H. (2011) · Pattern Recognition Letters · doi:10.1016/j.patrec.2011.02.022 · Cited by 80
Zhang, X., Xu, G., Mou, X., Ravi, A., Li, M., Wang, Y., & Jiang, N. (2019) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2019.2914904 · Cited by 67 · cited 4×
“In [24], an asynchronous SSMVEP BCI was developed in which EEG was converted to the frequency domain using a fast Fourier transform (FFT) and then applied as input to the CNN to distinguish between an intentional control (IC) and a no control (NC) state.”
BackgroundMethodInfluentialSelf-citationDoi, T., Yamamoto, S., Morinaga, T., Sada, K., Kurita, N., & Ônishi, Y. (2015) · PLoS ONE · doi:10.1371/journal.pone.0129180 · Cited by 63
Kluge, T., & Hartmann, M. (2007) · 2007 3rd International IEEE/EMBS Conference on Neural Engineering · doi:10.1109/cne.2007.369700 · Cited by 50 · cited 1×
“Many studies have used a frequency-phase coding approach in the stimulus design [12, 27] and use the phase information as part of the classifier to detect the SSVEP targets [28, 29].”
MethodWaytowich, N. R., Faller, J., Garcia, J. O., Vettel, J. M., & Sajda, P. (2016) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2016.7844880 · Cited by 46 · cited 6×
“In addition, two datasets were used in this study for the comparison: (1) a seven class SSVEP dataset with 21 participants recorded in our lab and; (2) a publicly available 12 class SSVEP dataset with ten participants, which has been used in many earlier studies [12, 13, 16, 22].”
MethodResultInfluentialAn EEG-driven Lower Limb Rehabilitation Training System for Active and Passive Co-stimulation
Zhang, X., Xu, G., Xie, J., Li, M., Wei, P., & Zhang, J. (2015) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2015.7319414 · Cited by 39
Reducing Delay and Maximizing Lifetime for Wireless Sensor Networks With Dynamic Traffic Patterns
Wang, Q., Liu, W., Wang, T., Zhao, M., Li, X., Xie, M., Ma, M., Zhang, G., & Liu, A. (2019) · IEEE Access · doi:10.1109/access.2019.2918928 · Cited by 28
Deep neural networks and transfer learning applied to multimedia web mining
López-Sánchez, D., Arrieta, A. G., & Corchado, J. M. (2017) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-62410-5_15 · Cited by 24 · cited 1×
“This method is a widely used feature visualization technique which enables us to visualize high-dimensional feature spaces in 2 or 3 dimensions [16, 22, 39].”
MethodUser-Independent SSVEP BCI Using Complex FFT Features and CNN Classification
Ravi, A., Beni, N. H., & Jiang, N. (2019) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2019.8914258 · Cited by 22
Self-citationKim, K. I., Suh, H. S., Kwak, A., Kim, S., Han, N., Lee, E., & Oh, J. M. (2017) · PLoS ONE · doi:10.1371/journal.pone.0174004 · Cited by 17
Ravi, A., Pearce, S., Zhang, X., & Jiang, N. (2019) · International IEEE/EMBS Conference on Neural Engineering · doi:10.1109/ner.2019.8716912 · Cited by 15 · cited 2×
“The experimental protocol was similar to the one used in our previous study [33].”
BackgroundResultSelf-citationRavi, A., Manuel, J., Beni, N. H., & Jiang, N. (2019) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2019.8857822 · Cited by 14 · cited 3×
“The CNN architecture used in this study was the one proposed in our previous study [32] and was inspired by the one proposed in [21].”
MethodSelf-citationMethods to Assess the Impact of Mass Oral Cholera Vaccination Campaigns under Real Field Conditions
Deen, J. L., Ali, M., & Sack, D. A. (2014) · PLoS ONE · doi:10.1371/journal.pone.0088139 · Cited by 12
Cecotti, H., & Coyle, D. (2014) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2014.6889802 · Cited by 7 · cited 1×
“Training-free algorithms do not require any training data and the user of the BCI can immediately start using the system [7 – 10].”
Method
Cited by
Summary of over Fifty Years with Brain-Computer Interfaces—A Review
Kawala-Sterniuk, A., Browarska, N., Al-Bakri, A., Pelc, M., Zygarlicki, J., Sidikova, M., Martinek, R., & Gorzelanczyk, E. J. (2021) · Brain Sciences · doi:10.3390/brainsci11010043 · Cited by 292
“The SSVEP-BCIs also require little or not training, what makes it a great candidate for real-life applications [113,118].”
BackgroundA transformer-based deep neural network model for SSVEP classification
Chen, J., Zhang, Y., Pan, Y., Xu, P., & Guan, C. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.04.045 · Cited by 170
A Deep Neural Network for SSVEP-Based Brain-Computer Interfaces
Güney, O. B., Oblokulov, M., & Özkan, H. (2021) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2021.3110440 · Cited by 153
“Indeed, subject specific adaptation has been observed in [39] to largely improve the identification performance.”
BackgroundKohli, V., Tripathi, U., Chamola, V., Rout, B. K., & Kanhere, S. S. (2021) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2021.104392 · Cited by 151
Review of brain encoding and decoding mechanisms for EEG-based brain–computer interface
Xu, L., Xu, M., Jung, T., & Ming, D. (2021) · Cognitive Neurodynamics · doi:10.1007/s11571-021-09676-z · Cited by 112
Metadata
- Authors
- Ravi, A., Beni, N. H., Manuel, J., & Jiang, N.
- Affiliations
- University of Waterloo (CA)
- Corresponding author
- Jiang, Ning
- Venue
- Journal of Neural Engineering
- Publisher
- IOP Publishing
- Published
- 2020-04-01
- Volume
- 17
- Issue
- 2
- Pages
- 026028
- ISSN
- 1741-2552 (ISSN-L)
- 1741-2560
- OpenAlex
- W3000563309
- Cited by
- 165
- References
- 46
- Citations by year
- 2026: 14 · 2025: 43 · 2024: 40 · 2023: 22 · 2022: 24 · 2021: 17 · 2020: 5
- FWCI
- 9.15
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/3.0/ (vor, 7 d)
- iopscience.iop.org/info/page/text-and-data-mining (tdm, 7 d)
- Locations
- Journal of Neural Engineering (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- Natural Sciences and Engineering Research Council of Canada (401261605)
- NSERC – CREATE, Training in Global Biomedical Technology Research and Innovation at the University of Waterloo. (401207296)
- 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
- steady-state visual evoked potentials, SSVEP-based brain-computer interface, convolutional neural networks, canonical correlation analysis, filter bank canonical correlation analysis, SSVEP classification, EEG feature extraction
- MeSH terms
- Algorithms, Electroencephalography, Evoked Potentials, Evoked Potentials, Visual, Humans, Photic Stimulation, Neural Networks, Computer, Brain-Computer Interfaces
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.