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
Cited by
Items 101–170 of 170
EvoMoE: Evolutionary Mixture-of-Experts for SSVEP-EEG Classification With User-Independent Training
Yang, X., Li, Y., Zhang, J., Tian, H., Li, S., & Pan, G. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3565882 · Cited by 4
“It is worth noting that the overall accuracy in our study was lower than in [16] due to differences in dataset complexity: our dataset included 40 categories (chance level = 2.5% ), whereas [16] used a dataset with only 12 categories (chance level = 8.33% ).”
InfluentialDual-Branch Attention-Based Frequency Domain Network for Cross-Subject SSVEP-BCIs
Yang, Y., Wang, Z., Jia, Z., Wang, B., Zhang, S., Wong, C. M., Gao, X., Jung, T., & Wan, F. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3630249 · Cited by 2
“…that complex spectrum features not only can represent phase and amplitude-related features but also include more discriminative information, leading to higher classification accuracy [32], [33], [34], [35] Then, we evaluate the effectiveness of each component in the proposed DB-AFDNet method.”
InfluentialCross-domain correlation analysis to improve SSVEP signals recognition in brain-computer interfaces
Hu, K., Wang, Y., Tu, K., Guo, H., & Yan, J. (2025) · Biomedical Physics & Engineering Express · doi:10.1088/2057-1976/ae2772 · Cited by 2
SUMamba: A Mamba-based deep learning model with multi-scale feature fusion for SSVEP classification
Dong, L., Xu, C., Wang, X., Xie, R., Lei, G., Li, Y., & Yang, W. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108376 · Cited by 2
Ravi, A., Tung, J. Y., & Jiang, N. (2023) · International IEEE/EMBS Conference on Neural Engineering · doi:10.1109/ner52421.2023.10123867 · Cited by 2
Self-citationPMF-CNN: parallel multi-band fusion convolutional neural network for SSVEP-EEG decoding
Yang, J., Zhao, S., Fu, Z., & Liu, X. (2024) · Biomedical Physics & Engineering Express · doi:10.1088/2057-1976/ad2e36 · Cited by 2
Enhancing SSEVP Classification via Hybrid Convolutional-Transformer Networks
Mao, S., & Gao, S. (2024) · IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS) · doi:10.1109/icpics62053.2024.10796567 · Cited by 2
A Multibranch CNN Framework Based on Time–Frequency Feature Fusion for SSVEP Detection
Shao, Y., Zheng, H., & Chen, X. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3605622 · Cited by 2
“These approaches typically employ either spectral magnitude features exclusively [18], [19] or a combination of magnitude and phase information as network inputs [20], [21].”
Shen, J., & Jiang, L. (2022) · Frontiers in Psychology · doi:10.3389/fpsyg.2022.906952 · Cited by 2
“Ravi et al. (2020) put forward an interactive attention mechanism for capturing network faults in text classification key characteristics, focusing on the extraction and classification of key characteristics using the BiLSTM and the CNN, as well as the formation of global and local features: the use…”
MethodPersonalized Classifier Selection for EEG-Based BCIs
Anaraki, J. R., Kolokolova, A., & Chau, T. T. (2024) · Computers · doi:10.3390/computers13070158 · Cited by 3
“User-dependent classifiers generally tend to outperform user-independent classifiers [21], necessitating a personalized classifier selection.”
BackgroundA Novel End-to-End Neural Network for SSVEP-Based Brain-Computer Interfaces
Niu, S., Lin, J., Zhai, D., & Xia, Y. (2024) · Chinese Control Conference (CCC) · doi:10.23919/ccc63176.2024.10661458 · Cited by 1
“Ravi et al.[18] processed and spliced the spectral information obtained by fast Fourier transform (FFT) of SSVEP signals and used the obtained frequency domain features as inputs to the neural network.”
MethodApplying SSVEP BCI on Dynamic Background
Li, J., Fu, B., Li, F., Gu, W., Ji, Y., Li, Y., Liu, T., & Shi, G. (2025) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2025.3576984 · Cited by 1
“Ravi et al. proposed the complex convolutional neural network (CCNN), which uses the complex spectrum of SSVEP signals as input data to CNN, and demonstrate that it is feasible to use complex spectral features for SSVEP classification tasks [31].”
EEG-TFNet: Spatiotemporal and Spectral Feature Integration for EEG-Based AD Detection
Zeng, A., Guo, Z. Z., Pan, D., Zhang, Y., Liu, J., & Hong, H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-0698-9_16 · Cited by 1
Dong, L., Xu, C., Xie, R., Wang, X., Yang, W., & Li, Y. (2025) · Biomimetics · doi:10.3390/biomimetics10080554 · Cited by 1
“The CCNN [21] proves the effectiveness of the combination of complex spectral features and convolutional neural networks.”
InfluentialOn the application of neural networks for structured domains to fMRI data
Donghi, G., Pasa, L., Grazia, M. D. F. D., Testolin, A., Zorzi, M., Sperduti, A., & Navarin, N. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.108029 · Cited by 2
Efficient artificial intelligence algorithms for on-site discrimination of Angelica sinensis
Yue, J., Feng, T., Zhong, L., Du, R., Gao, X., Nie, L., & Zang, H. (2025) · Spectrochimica Acta Part A Molecular and Biomolecular Spectroscopy · doi:10.1016/j.saa.2025.126934 · Cited by 1
A Transfer Generalization Framework for Improved SSVEP-Based BCI Pattern Recognition
Prof. Hanumanthappa, H., Biradar, V. G., & Arakeri, M. P. (2025) · SN Computer Science · doi:10.1007/s42979-025-04368-5 · Cited by 1
“At the maximum sig - nal strength of 1, TRANSGEN MODEL achieves 98.8% accuracy, with Existing at 96.3%, highlighting TRANSGEN MODEL’s consistent advantage across all signal strengths [38–41].”
InfluentialTest-Time Training for Inter-Subject Generalization in SSVEP-Based BCI
Duan, S.-B., Xiang, T., Zhou, X.-H., Gui, M.-J., Xie, X., Liu, S.-Q., Lai, Z., Hao, J., & Hou, Z. (2025) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icia64617.2025.11277456 · Cited by 2
“For CNN [17] and FBCNN [18], in the CNN experiment, only the BatchNorm in the last layer is updated, whereas in the FBCNN experiment, only the BatchNorm1, BatchNorm2, and BatchNorm3 layers are updated; the pre-training stage is conducted for 50 epochs (learning rate 3 × 10 − 4 ), fine-tuning for 40…”
Xiong, B., Wan, B., Huang, J., & Yang, P. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3587765 · Cited by 1
“Furthermore, considering the architecture of convolutional neural networks (CNNs) to capture nonlinear and non-stationary features from SSVEP signals [34].”
BrainWaveDecoder: From raw EEG to SSVEP-BCI target selection via end-to-end deep learning
Pashapouryeganeh, M., Zafarghandi, M. S., & Setayeshi, S. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108792 · Cited by 1
Data Augmentation for Subject-Independent SSVEP-BCIs via Simultaneous Spatial-Energy Representation
Ding, W., Liu, A., Wu, L., Cui, H., Fang, B., & Chen, X. (2026) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2026.3659606 · Cited by 1
“Therefore, models trained on source subjects can classify EEG signals from new subjects without prior exposure [19], [21], [22].”
InfluentialNavigation paradigms for non-invasive BCI-controlled wheelchairs: a systematic review
Ukaegbu, U. F., Houshmand, S., Hammond, L., Adams, K. D., Andersen, J. C., & Noamani, A. (2026) · Progress in Biomedical Engineering · doi:10.1088/2516-1091/ae5563 · Cited by 1
“Nevertheless, two of the included studies [60, 66] employed a 1 s window length for segmenting the EEG signals shown by Ravi et al [98] to yield the optimized values for classification accuracy and ITR.”
Duan, S.-B., & Hao, J. (2026) · Applied Sciences · doi:10.3390/app16083799 · Cited by 1
Seraphim, M., Laville, M., Quintyn, J. C., & Thariat, J. (2026) · Frontiers in Neuroscience · doi:10.3389/fnins.2026.1811969 · Cited by 1
Karimi, R., Mohammadi, A., Rosero, L., & Asif, A. A. (2020) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco47968.2020.9287784 · Cited by 1
“To implement flexible target frequencies, we need to have designs with variable number of frames per cycle; as such, we used the technique in Reference [34] and verified in [35] to implement our designs.”
MethodInfluentialFeature Extraction for a Genetic Programming-Based Brain-Computer Interface
de Souza, G. H., Faria, G. O. M., Motta, L. P., Bernardino, H. S., & Vieira, A. B. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-21686-2_10 · Cited by 2
Atchuthan, N. A., Clark, H. F., Danyar, M. B., Andersen, A. K., Andreis, F. R., & Meijs, S. (2023) · International IEEE/EMBS Conference on Neural Engineering · doi:10.1109/ner52421.2023.10123776 · Cited by 1
Forty-Class SSVEP-Based Brain-Computer Interface to Inter-subject Using Complex Spectrum Features
Flores, C., Attux, R., & Carvalho, S. N. (2024) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-031-49404-8_5 · Cited by 1
Shishavan, H. H., Roy, R., Golzari, K., Singla, A., Zalozhin, D., Lohan, D. J., Farooq, M., Dede, E. M., & Kim, I.-S. (2024) · PLoS ONE · doi:10.1371/journal.pone.0308506 · Cited by 2
“Therefore, advancements in classification methods and the selection of optimal SPs, incorporating machine learning techniques outlined in previous studies [52,53], could result in increased accuracies and significant improvement of BMI system performance through faster detection of SSVEPs.”
MethodChinese Spelling and Voice Interaction System based on Brain-Computer Interface
Yuna, Y., Zhidong, G., Hui, Z., & Gao, N. (2020) · IEEE International Conference on Signal and Image Processing (ICSIP) · doi:10.1109/icsip49896.2020.9339394
Zhang, Z., Guan, K. Y., Qian, Z., Shen, F., Liu, T., & Niu, H. (2021) · International IEEE/EMBS Conference on Neural Engineering · doi:10.1109/ner49283.2021.9441431
Luo, T.-J., & Zhou, C. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-11971-8
“In addition, deep neural networks have been used on the EEG signals classification, such as P300, SSVEP, and ERD suppressions of motor imagery [44, 60, 72].”
MethodAn Asynchronous BCI-VR Hybrid Interactive System Based on a Mixed Template CCA MethodPreprint
Niu, L., Bin, J., zhao, Y., Deng, T., & Huo, Z. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4635887
A new approach to neural networks using pseudo-differential operators
Du, H., Molahajloo, S., & Wang, X. (2024) · Journal of Pseudo-Differential Operators and Applications · doi:10.1007/s11868-023-00580-0
First Uruguayan Robotic Vehicle Hackathon Controlled by Brain Computer Interfaces
Baldezzari, L. (2024) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-031-51723-5_61
Self-supervised deep learning and EEG categorization
Svantesson, M. (2024) · Linköping University medical dissertations · doi:10.3384/9789180755429
Li, Q., Han, C., Liu, Y., & Liu, J. (2024) · IEEE China Conference on System Simulation Technology and its Applications (CCSSTA) · doi:10.1109/ccssta62096.2024.10691737
“Brain-computer interfaces (BCIs) technology is a technology that translates brain activity into commands to control external devices[1].”
BackgroundComplex Spectrum Correlation Analysis Network based on Attention Convolution for SSVEP-BCI
Chen, C., Zheng, H., Lü, L. T., & Wu, D. (2024) · IEEE China Conference on System Simulation Technology and its Applications (CCSSTA) · doi:10.1109/ccssta62096.2024.10691862
“Ravi et al [17] aimed to enable neural models to learn amplitude and phase-related stimulus information for classification, introducing the C-CCN (Complex Convolution of Spectrum Features) model.”
Zhang, J., & Zhong, X. (2024) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126625501075
A Novel SSVEP Modulation and Decoding Method in Dynamic Display Interactive Scene
Gu, W., Li, F., Fu, B., Li, J., Ji, Y., & Chen, Y. (2024) · IEEE International Conference on Unmanned Systems (ICUS) · doi:10.1109/icus61736.2024.10839612
Multi modal fusion human-machine interactive nursing bed system
Wang, P., Zhang, L., & Ji, X. (2024) · IEEE International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA) · doi:10.1109/iciba62489.2024.10867891
Zhang, C. Z., Su, P., & Wu, X. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8173-0_28
Bekhelifi, O., Berrached, N.-E., Brezini, S. E., & Mebtouche, N. E.-D. (2025) · International Conference on Pattern Analysis and Intelligent Systems (PAIS) · doi:10.1109/pais66004.2025.11126056
“In [15] the authors proposed the concatenation of the real and imaginary information into a single matrix that will be the input to a two blocks CNN.”
Enhancing performance of SSVEP-based visual acuity via exploiting subject-specific information
Zheng, X., Wen, B., Yan, X., Xu, G., & Zhang, R. (2025) · Cognitive Neurodynamics · doi:10.1007/s11571-025-10331-0
“Moreover, some deep learning methods, e.g., a convolutional neural network (CNN) (Ravi et al. 2020 ) and trans-former (Chen et al. 2023 ), may also be utilized to improve the performance of SSVEP-based visual acuity in future research.”
TRCA with sparrow-optimized adaptive filter banks for SSVEP recognition
Nan, J., Zhang, S., Xu, P., Zhang, K., Li, D., Zhu, F., Li, Y., Xia, Y., & Meng, Y. (2025) · Cluster Computing · doi:10.1007/s10586-025-05795-y
“Later, Ravi et al. [21] utilized fast Fourier transform to convert time-domain SSVEP data into frequency-domain data and developed a complex frequency-domain convolutional neural network (CNN), achieving around 81.6% accuracy on the same dataset.”
InfluentialWavNet: Learning Time-Frequency Representations for Robust SSVEP-Based BCIs
Xu, L., Jiang, X., Wang, R., & Ge, S. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-3739-6_22
Adaptive Multi-Domain Joint Decoding Algorithm for SSVEP Signal Classification
Jia, S., & Cao, R. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227745
“Building upon this foundation, the team later developed a more intricate model known as the complex spectral convolutional neural network (C-CNN) [14].”
Template Comparison Network for Enhancing Classification Performance of High-Frequency SSVEPs
Yu, D., Wang, C., Zhang, L., Li, P., & Lv, Z. (2025) · Journal of Physics Conference Series · doi:10.1088/1742-6596/3147/1/012015
MCRBM–CNN: A Hybrid Deep Learning Framework for Robust SSVEP Classification
Gao, D., Zhao, Y., Zhou, J., Zhang, H., & Li, H. (2025) · Sensors · doi:10.3390/s25247456
Dual-channel TRCA-net based on cross-subject positive transfer for SSVEP-BCI
Xiong, H., Chang, S., & Liu, J. (2025) · Biomedical Physics & Engineering Express · doi:10.1088/2057-1976/ae291c
Ingel, A. (2023) · DSpace repository (University of Tartu)
Dual-templates transferred canonical correlation analysis for cross-subject SSVEP-based BCIs
Luo, T.-J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130611
Fine-Tuning FB-MultiCNN for Enhanced SSVEP Detection in Brain-Computer Interfaces
Shao, Y., Zheng, H., & Chen, X. (2025) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2025.12.526
Pang, R., Xu, H., Li, B., Ou, B., & tang, S. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6045168
Ding, W., Liu, A., & Chen, X. (2026) · Journal of Neural Engineering · doi:10.1088/1741-2552/ae36f6
“To further examine the generalizability of JFPTS, it is applied to five additional models, including EEGNet [18], tCNN [20], CNN-Former [25], C-CNN [19], and SSVEPformer [24].”
InfluentialDing, W., Liu, A., Cui, H., Shan, J., & Chen, X. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109600
Research on Frequency Recognition Algorithm Based on Convolution-Long Short-Term Memory Network
Li, F., Tian, Y.-J., Su, Y., Shi, Z.-X., Zhang, M., & Yang, H.-S. (2025) · Proceedings of the 2025 International Conference on Artificial Intelligence and Foundation Model · doi:10.1145/3786709.3786717
Abdallah, A., Benayed, W., Trigui, O., Bouabid, A., & Ghorbel, M. (2025) · International Conference on Sciences and Techniques of Automatic Control and Computer Engineering · doi:10.1109/sta66620.2025.11364809
LARSNet: A Lightweight Asymmetric Residual Siamese Network for SSVEP-Based Brain–Computer Interfaces
Gu, Y., Luo, P., Su, R., & Li, X. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3660428
“6) C-CNN [32]: A complex-spectrum CNN that uses fast Fourier transform-transformed EEG as input to preserve both amplitude and phase information.”
Asynchronous SSVEP-BCI recognition via Multi-Start-Point Slice Ensembles and Hard Voting
Wu, H., Tu, Y.-T., & Wu, D. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461264
Zhou, Z., Chen, D., & Lai, S. (2025) · International Conference on Industrial Automation, Robotics and Control Engineering (IARCE) · doi:10.1109/iarce68366.2025.11485755
“Aravind Ravi et al. proposed using complex spectral features (containing both amplitude and phase information) as CNN inputs and compared user-dependent and user-independent training strategies for SSVEP classification[11].”
Xu, L., Jiang, X., Wang, R., Leng, Y., Iramina, K., Yang, Y., & Ge, S. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111115
Research on SSVEP Signal Classification Based on CNN-Mamba
Xie, R., Xu, C., Dong, L., & Wang, X. (2026) · International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE) · doi:10.1109/icbase70763.2026.11619472
“We compare the Acc and ITR metrics with traditional baseline models such as Transformer and deep learning models including EEGNet [8] , CCNN [9] and PLFA [10] .”
Zhao, J., Li, S., Qin, Y., Zhang, W., Wang, L., Wang, Q., Sataer, Y., & Tao, X. (2026) · International Symposium on Communications and Information Technologies · doi:10.1109/iscit70453.2026.11695329
“…SCCNet [28] 70.93 ShallowCNN [9] 61.84 TCNet-F [14] 45.00 ShallowCNN [9] 71.86 DeepCNN [9] 62.15 FBCNet [26] 53.09 SPDNet [15] 72.05 GDLNet [18] 62.15 CCNN [29] 52.96 SPDNetBN [15] 72.34 LST-BEEGSE [30] 64.58 EEGNet [27] 53.72 EEGNet [27] 74.28 B-FNN [24] 68.59 – – U-FNN [24] 74.25 SNR-PRD [11] 69”
InfluentialWu, X., Allison, B. Z., Chen, W., He, X., Wang, C., Wang, X., CICHOCKI, A., Lu, Y., & Jin, J. (2026) · Cognitive Neurodynamics · doi:10.1007/s11571-026-10565-6
“The real and imaginary components of 𝐙𝐙 are then concatenated along the feature dimension to construct the complex-spectrum representation: (2) Earlier studies have shown the crucial role of phase in accurate SSVEP classification (Ravi et al. 2020, Falzon et al. 2012, Pan et al. 2023).”
Technology acceptance of passive brain-computer interfaces in vehicles for adaptive automation
Wehrle, T., Krahnen, L. S., Bauernfeind, G., Haar, A., & Meyer, B. (2026) · Transportation Research Part F Traffic Psychology and Behaviour · doi:10.1016/j.trf.2026.103828
Zhang, Z., Yang, Y., Wang, Y., Jiang, C., You, M., Wang, L., Chen, J., Huang, S., Tan, Z., & Liu, J. (2026) · International Conference on Advanced Algorithms and Neural Networks (AANN) · doi:10.1109/aann71145.2026.11709375
“50% chance level, consistent with prior FBCCA [10], CNN-based [11], and few-channel evaluations [2].”
DenoFlow: Flow matching for SSVEP denoising under recorded physiological artifacts
He, Z., Wang, Z., & Wu, D. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.117288
Hu, K., Zhao, L., Wu, F., Liu, Y., Zhang, Z., & Song, Z. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728657
“(2) Deep models learn nonlinear representations to boost short-window decoding, ranging from compact CNN back-bones [22], [24], [26] and CNN-RNN variants [25] to Trans-former designs [27], [28].”
Frequency-Aware Class-Incremental Learning for SSVEP-Based Brain–Computer Interfaces
An, J., Wu, H., & Wu, D. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729978
“Convolutional neural network (CNN) architectures, such as EEGNet [21] and compact CNN variants [12], [22], automatically learn spatial–temporal features directly from raw EEG signals.”
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.