Signal Processing Approaches to Minimize or Suppress Calibration Time in Oscillatory Activity-Based Brain–Computer Interfaces
Open accessThe DOI matches its Crossref record; 86 of the 88 references it cites were found in a registry or an index.
Abstract
One of the major limitations of brain-computer interfaces (BCI) is their long calibration time, which limits their use in practice, both by patients and healthy users alike. Such long calibration times are due to the large between-user variability and thus to the need to collect numerous training electroencephalography (EEG) trials for the machine learning algorithms used in BCI design. In this paper, we first survey existing approaches to reduce or suppress calibration time, these approaches being notably based on regularization, user-to-user transfer, semi-supervised learning and a priori physiological information. We then propose new tools to reduce BCI calibration time. In particular, we propose to generate artificial EEG trials from the few EEG trials initially available, in order to augment the training set size. These artificial EEG trials are obtained by relevant combinations and distortions of the original trials available. We propose three different methods to do so. We also propose a new, fast and simple approach to perform user-to-user transfer for BCI. Finally, we study and compare offline different approaches, both old and new ones, on the data of 50 users from three different BCI data sets. This enables us to identify guidelines about how to reduce or suppress calibration time for BCI.
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
“In addition, the BCI system requires a long calibration phase before each time it is used because, to achieve a good performance, every subject’s BCI system needs to be trained by their own EEG signals and cannot use other’s EEG signals [11].”
From Transfer Learning Algorithm of P300-EEG Signal Based on XDAWN Spatial Filter and Riemannian Geometry Classifier (2020) · cites this paper as [11]
In the citing paper
“In addition, the BCI system requires a long calibration phase before each time it is used because, to achieve a good performance, every subject’s BCI system needs to be trained by their own EEG signals and cannot use other’s EEG signals [11].”
From Transfer Learning Algorithm of P300-EEG Signal Based on XDAWN Spatial Filter and Riemannian Geometry Classifier (2020) · cites this paper as [11]
In the citing paper
“Classification must generalize across subjects, since per-subject calibration delays setup and limits scalability [4]”
From ERP-XTTN: interpretable prototype-guided cross-attention for cross-subject ERP classification (2026) · cites this paper as [4]
Citations
Cites
Caruana, R. (1997) · Machine Learning · doi:10.1023/a:1007379606734 · Cited by 6,636 · cited 1×
“…guide the optimization algorithms towards good solutions, similar to that of the other users, thus enabling a better learning from little data. b) Multi-task learning: Multi-task learning consists of learning simultaneously multiple tasks that share some constraints or prior information [37].”
BackgroundSemi-Supervised Learning Literature Survey
Zhu, X. (2005) · Minds at UW (University of Wisconsin) · Cited by 4,505
A well-conditioned estimator for large-dimensional covariance matrices
Ledoit, O., & Wolf, M. (2004) · Journal of Multivariate Analysis · doi:10.1016/s0047-259x(03)00096-4 · Cited by 3,046 · cited 3×
“More precisely, it is known that when covariance matrices are estimated from too little training data, their largest and smallest eigen values will be, respectively, over and under estimated [32].”
BackgroundMethodInfluentialA review of classification algorithms for EEG-based brain–computer interfaces
Lotte, F., Congedo, M., Lécuyer, A., Lamarche, F., & Arnaldi, B. (2007) · Journal of Neural Engineering · doi:10.1088/1741-2560/4/2/r01 · Cited by 2,665 · cited 2×
“The LDA classifier uses a linear hyperplane to separate feature vectors from two classes [10].”
MethodSelf-citationOptimizing Spatial filters for Robust EEG Single-Trial Analysis
Blankertz, B., Tomioka, R., Lemm, S., Kawanabe, M., & Muller, K.-R. (2008) · IEEE Signal Processing Magazine · doi:10.1109/msp.2008.4408441 · Cited by 2,080 · cited 3×
“Since the variance of a band-pass filtered signal corresponds to the band-power of the signal in that band, CSP optimizes spatial filters that lead to optimally discriminant band-power features [29].”
BackgroundMethodInfluentialMotor imagery and direct brain-computer communication
Pfurtscheller, G., & Neuper, C. (2001) · Proceedings of the IEEE · doi:10.1109/5.939829 · Cited by 1,990 · cited 1×
“As an example, during left hand motor imagery (i.e., the imagination of a left hand movement), the EEG band power in the (cid:2) (8–12 Hz) and (16–24 Hz) frequency bands will decrease in the right sensorimotor cortex [30].”
BackgroundA tutorial on Principal Components Analysis
Smith, L. I. (2002) · Otago University Research Archive (University of Otago) · Cited by 1,636
Filter 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×
“…and classifier optimization from limited training data), several algorithms being available to optimize such bands with CSP and LDA; see, e.g., [75]–[81]; 2) outlier/ artifact removal in small sample size settings, as when little data is available, a single outlier (artefacts being…”
MethodSingle-trial analysis and classification of ERP components — A tutorial
Blankertz, B., Lemm, S., Treder, M., Haufe, S., & Müller, K.-R. (2011) · NeuroImage · doi:10.1016/j.neuroimage.2010.06.048 · Cited by 1,138 · cited 1×
“Since this is a simple, computationally efficient and parameter free method, we advocate that it should become a standard tool for BCI design, including for oscillatory activity-based BCI (it is already becoming a rather standard tool for ERP classification [74]).”
MethodAn EEG-based brain-computer interface for cursor control
Wolpaw, J. R., McFarland, D. J., Neat, G. W., & Forneris, C. A. (1991) · Electroencephalography and Clinical Neurophysiology · doi:10.1016/0013-4694(91)90040-b · Cited by 1,114 · cited 2×
“, [2] and [3].”
Research works printed but not linked: 3
- tu, 0, Dynamical ensemble learning with model-friendly classifiers for domain adaptation, Proc IEEE ICPR, 1181
- lu, 0, Boosting-based subject-independent brain computer interface, Proc ICPR
- meng, 2014, Improved semi-supervised adaptation for small training data set in brain-computer interface, IEEE J Biomed Health Inform, 18
Cited by
EEGNet: 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
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
A 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
“robustness of the LDA to mislabelling [137].”
BackgroundSelf-citationEEG Conformer: Convolutional Transformer for EEG Decoding and Visualization
Song, Y., Zheng, Q., Liu, B., & Gao, X. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3230250 · Cited by 1,095
“Follow [37], the training samples of the same category are equally divided into N s segments, then randomly concatenated while maintaining the original time order.”
BackgroundA 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
Riemannian Approaches in Brain-Computer Interfaces: A Review
Yger, F., Berar, M., & Lotte, F. (2017) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2016.2627016 · Cited by 420
“so, such as subject-to-subject transfer, semi-supervised learning, or artificial data generation [13].”
MethodInfluentialSelf-citationSubject-Independent Brain–Computer Interfaces Based on Deep Convolutional Neural Networks
Kwon, O.-Y., Lee, M.-H., Guan, C., & Lee, S.-W. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2946869 · Cited by 347
“Over the course of numerous BCI studies [16]–[21], growing attention has been dedicated to the analysis of electroencephalography (EEG) signals, especially by movement imagination, called motor imagery (MI) [1], [2], [8], [12], [14], [16], [22].”
BackgroundMethodInfluentialHS-CNN: a CNN with hybrid convolution scale for EEG motor imagery classification
Dai, G., Zhou, J., Huang, J., & Wang, N. (2020) · Journal of Neural Engineering · doi:10.1088/1741-2552/ab405f · Cited by 336
Intra- and Inter-subject Variability in EEG-Based Sensorimotor Brain Computer Interface: A Review
Saha, S., & Baumert, M. (2020) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2019.00087 · Cited by 325
“…Intra-and Inter-subject BCI Performance Predictors concept of transfer learning (Kang et al., 2009; Li et al., 2010; Lu et al., 2010; Niazi et al., 2013; Kang and Choi, 2014; Fazli et al., 2015; Lotte, 2015; Jayaram et al., 2016; Saha et al., 2017a,b, 2019; Fahimi et al., 2018; He and Wu, 2019).”
BackgroundEpilepsy Seizure Prediction on EEG Using Common Spatial Pattern and Convolutional Neural Network
Zhang, Y., Guo, Y., Yang, P., Chen, W., & Lo, B. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2933046 · Cited by 319
“ting and splicing [30] and the second one is to generate EEG data by generative adversarial networks (GAN) [31].”
BackgroundGenerative Adversarial Networks-Based Data Augmentation for Brain–Computer Interface
Fahimi, F., Dosen, S., Ang, K. K., Mrachacz-Kersting, N., & Guan, C. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3016666 · Cited by 228
“2) Segmentation and Recombination (S&R): We also implemented EEG generation using S&R methods presented in [7] to minimize the calibration time.”
MethodResultInfluentialEEG Data Augmentation for Emotion Recognition Using a Conditional Wasserstein GAN
Luo, Y., & Lu, B.-L. (2018) · 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2018.8512865 · Cited by 214
“In [7], artificial EEG trials were generated by the relevant combinations and distortions of the original trials.”
BackgroundJeunet, C., Jahanpour, E., & Lotte, F. (2016) · Journal of Neural Engineering · doi:10.1088/1741-2560/13/3/036024 · Cited by 192
“While 20 trials per class is not much, it has been shown to be sufficient to set up a motor imagery classifier [7, 29].”
BackgroundSelf-citationRoy, A. M. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.103496 · Cited by 187
CTNet: a convolutional transformer network for EEG-based motor imagery classification
Zhao, W., Jiang, X., Zhang, B., Xiao, S., & Weng, S. (2024) · Scientific Reports · doi:10.1038/s41598-024-71118-7 · Cited by 182
Sparse Group Representation Model for Motor Imagery EEG Classification
Jiao, Y., Zhang, Y., Chen, X., Yin, E., Jin, J., Wang, X., & Cichocki, A. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2018.2832538 · Cited by 189
“vestigated using signal segmentation and recombination in time or time-frequency domain, or based on analogy [44].”
Dehais, F., Duprès, A., Blum, S., Drougard, N., Scannella, S., Roy, R. N., & Lotte, F. (2019) · Sensors · doi:10.3390/s19061324 · Cited by 180
“Here, a regularized CSP with automatic covariance matrix shrinkage was used, as recommended in [49].”
MethodSelf-citationWeighted Transfer Learning for Improving Motor Imagery-Based Brain–Computer Interface
Azab, A. M., Mihaylova, L., Ang, K. K., & Arvaneh, M. (2019) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2019.2923315 · Cited by 176
“Thus, developing reliable methods and approaches that reduce calibration time while keeping accuracy in an acceptable range is highly desirable in MI-based BCI research [7], [9], [10].”
MethodData augmentation for enhancing EEG-based emotion recognition with deep generative models.
Luo, Y., Zhu, L.-Z., Wan, Z.-Y., & Lu, B.-L. (2020) · Journal of Neural Engineering · doi:10.1088/1741-2552/abb580 · Cited by 162
GANSER: A Self-Supervised Data Augmentation Framework for EEG-Based Emotion Recognition
Zhang, Z., Liu, Y., & Zhong, S.-H. (2022) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2022.3170369 · Cited by 178
“Relying on relevant combinations and distortions of original trials, Lotte proposed three methods to obtain artificial EEG trials [23].”
MethodBorra, D., Fantozzi, S., & Magosso, E. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.05.032 · Cited by 145
Learning across multi-stimulus enhances target recognition methods in SSVEP-based BCIs
Wong, C. M., Wan, F., Wang, B., Wang, Z., Nan, W., Lao, K. F., Mak, P. U., Vai, M. I., & Rosa, A. C. (2019) · Journal of Neural Engineering · doi:10.1088/1741-2552/ab2373 · Cited by 148
Transfer learning for motor imagery based brain–computer interfaces: A tutorial
Wu, D., Jiang, X., & Peng, R. (2022) · Neural Networks · doi:10.1016/j.neunet.2022.06.008 · Cited by 182
“Signal processing [22].”
Wu, D., Lawhern, V. J., Gordon, S., Lance, B. J., & Lin, C.-T. (2017) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2016.2633379 · Cited by 130
Time-Series Data Augmentation based on Interpolation
Oh, C., Han, S., & Jeong, J. (2020) · Procedia Computer Science · doi:10.1016/j.procs.2020.07.012 · Cited by 149
Wei, C.-S., Lin, Y.-P., Wang, Y.-T., Lin, C.-T., & Jung, T.-P. (2018) · NeuroImage · doi:10.1016/j.neuroimage.2018.03.032 · Cited by 115
“…using only a few trials from each class in the BCI task (Devlaminck et al., 2011; Kang and Choi, 2014; Dalhoumi et al., 2014; Arvaneh et al., 2014; Lotte, 2015), or by using only a subset of classes with a regularized feature-extraction method that improves the robustness of the covariance matrix…”
InfluentialOnline and Offline Domain Adaptation for Reducing BCI Calibration Effort
Wu, D. (2017) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2016.2608931 · Cited by 114
Multi-Scale Neural Network for EEG Representation Learning in BCI
Ko, W., Jeon, E., Jeong, S., & Suk, H. (2021) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2021.3061875 · Cited by 117
Electroencephalography (EEG)‐Based Brain–Computer Interfaces
Lotte, F., Bougrain, L., & Clerc, M. (2015) · Wiley Encyclopedia of Electrical and Electronics Engineering · doi:10.1002/047134608x.w8278 · Cited by 98
“EEG-based BCI also generally require relatively long calibration time [24] and may also require long to very long human training time [22, 33].”
BackgroundSelf-citationHeading for new shores! Overcoming pitfalls in BCI design
Chavarriaga, R., Fried-Oken, M., Kleih, S., Lotte, F., & Scherer, R. (2017) · Brain-Computer Interfaces · doi:10.1080/2326263x.2016.1263916 · Cited by 97
Self-citationPei, Y., Luo, Z., Yan, Y., Yan, H., Jiang, J., Li, W., Xie, L., & Yin, E. (2021) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2021.645952 · Cited by 101
“In another work, artificial EEG trials were generated by segmentation and recombination in time and frequency domains (Lotte, 2015), and the results were more convincing.”
ResultA Temporal Dependency Learning CNN With Attention Mechanism for MI-EEG Decoding
Ma, X., Chen, W., Pei, Z., Liu, J., Huang, B., & Chen, J. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3299355 · Cited by 103
“Compared with the previous study (time window [0s, 4s]), we used a time window [0.5, 2.5] seconds post cue onset (the same window which was used in [20] and [42]) to extract EEG signals for decoding.”
MethodInfluentialTransfer learning in imagined speech EEG-based BCIs
García‐Salinas, J. S., Villaseñor-Pineda, L., Reyes-Garcia, C. A., & Torres-García, A. A. (2019) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2019.01.006 · Cited by 100
Passive Brain-Computer Interfaces for Enhanced Human-Robot Interaction
Alimardani, M., & Hiraki, K. (2020) · Frontiers in Robotics and AI · doi:10.3389/frobt.2020.00125 · Cited by 111
“Also, there have been attempts in reducing calibration time by means of machine learning techniques and adaptive classifiers that extract common features among all users (Lotte, 2015), known as inter-subject associativity (Saha and Baumert, 2019).”
BackgroundEmbodied VR environment facilitates motor imagery brain–computer interface training
Škola, F., & Liarokapis, F. (2018) · Computers & Graphics · doi:10.1016/j.cag.2018.05.024 · Cited by 97
“This technique, together with the outlier removal, was adapted from the suggestions in work of Lotte [62] on MI-BCI set-up time reduction.”
MethodMSVTNet: Multi-Scale Vision Transformer Neural Network for EEG-Based Motor Imagery Decoding
Liu, K., Yang, T., Yu, Z., Yi, W., Yu, H. Z., Wang, G., & Wu, W. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3450753 · Cited by 105
Waytowich, N. R., Lawhern, V. J., Bohannon, A. W., Ball, K. R., & Lance, B. J. (2016) · Frontiers in Neuroscience · doi:10.3389/fnins.2016.00430 · Cited by 79
“The use of advanced signal processing and machine learning techniques to minimize or eliminate this need for calibration data is an area of on-going interest for the development of practical BCI systems (Lotte, 2015).”
BackgroundMethodInfluentialNafea, M. S., & Ismail, Z. H. (2022) · Bioengineering · doi:10.3390/bioengineering9120781 · Cited by 105
Double ErrP Detection for Automatic Error Correction in an ERP-Based BCI Speller
Cruz, A., Pires, G., & Nunes, U. (2017) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2017.2755018 · Cited by 87
“Performing a calibration for each session is something to avoid, since it limits the usability of the BCI system [38], [39].”
BackgroundDual-Encoder VAE-GAN With Spatiotemporal Features for Emotional EEG Data Augmentation
Tian, C., Ma, Y., Cammon, J., Fang, F. Z., Zhang, Y., & Meng, M. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3266810 · Cited by 88
“Lotte [31] generated EEG data by combining and distorting the original experimental data.”
MethodMa, X., Chen, W., Pei, Z., Zhang, Y., & Chen, J. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108504 · Cited by 86
MsCNN: A Deep Learning Framework for P300-Based Brain–Computer Interface Speller
Kundu, S., & Ari, S. (2020) · IEEE Transactions on Medical Robotics and Bionics · doi:10.1109/tmrb.2019.2959559 · Cited by 70
“In addition, requirement of long calibration time for the network due to the large variability of EEG signals restricts the use of BCI in real time application for both patients and healthy subjects [27], [28].”
BackgroundCustom Domain Adaptation: A New Method for Cross-Subject, EEG-Based Cognitive Load Recognition
Jiménez-Guarneros, M., & Gómez‐Gil, P. (2020) · IEEE Signal Processing Letters · doi:10.1109/lsp.2020.2989663 · Cited by 75
“Several works have been proposed to solve cross-subject classification using both generic and unsupervised domain adaptation (UDA) methods [13].”
BackgroundSelf-supervised Learning with Attention Mechanism for EEG-based seizure detection
Xiao, T., Wang, Z., Zhang, Y., Lv, H., Wang, S., Feng, H., & Zhao, Y. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105464 · Cited by 75
Bird, J. J., Pritchard, M., Fratini, A., Ekárt, A., & Faria, D. R. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3056355 · Cited by 68
“1Equations for Lotte’s EEG generation technique can be found in [6].”
BackgroundMethodEEG data augmentation: towards class imbalance problem in sleep staging tasks
Fan, J., Sun, C., Chen, C., Jiang, X., Liu, X., Zhao, X. F., Meng, L., Dai, C., & Chen, W. (2020) · Journal of Neural Engineering · doi:10.1088/1741-2552/abb5be · Cited by 82
Jiménez-Guarneros, M., & Fuentes-Pineda, G. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105138 · Cited by 78
EEG-Based User Reaction Time Estimation Using Riemannian Geometry Features
Wu, D., Lance, B. J., Lawhern, V. J., Gordon, S., Jung, T.-P., & Lin, C.-T. (2017) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2017.2699784 · Cited by 64
Li, F., Xia, Y., Wang, F., Zhang, D., Li, X., & He, F. (2020) · Applied Sciences · doi:10.3390/app10051804 · Cited by 64
“Some other transfer learning methods are semi-supervised learning [17] and using uniform local binary patterns [18] or artificial data generation [11].”
BackgroundMethodMulti-scale convolutional transformer network for motor imagery brain-computer interface
Zhao, W., Zhang, B., Zhou, H., Wei, D., Huang, C., & Lan, Q. (2025) · Scientific Reports · doi:10.1038/s41598-025-96611-5 · Cited by 90
“We employ the segmentation and reconstruction (S&R) method 44 in the time domain to augment training data, which involves a systematic approach to artificially increasing the amount and variability of EEG training datasets.”
Tactile Stimulation Improves Sensorimotor Rhythm-Based BCI Performance in Stroke Patients
Shu, X., Chen, S., Meng, J., Yao, L., Sheng, X., Jia, J., Farina, D., & Zhu, X. (2018) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2018.2882075 · Cited by 60
“the existed methods for reducing or suppressing calibration time [36]–[39], the proposed approach in this study achieved similar improvements without increasing additional source information”
MethodZhang, Q., & Liu, Y. (2018) · arXiv · doi:10.48550/arxiv.1806.07108 · Cited by 57
“Although many achievements have been obtained in this field and many algorithms can get state of the art performance with high classification accuracy in standard dataset or self-recorded dataset, most of the algorithms are only evaluated offline and lack of robustness and reliability [4].”
BackgroundMethodPeterson, V., Wyser, D., Lambercy, O., Spies, R. D., & Gassert, R. (2019) · Journal of Neural Engineering · doi:10.1088/1741-2552/aaf046 · Cited by 62
Singh, A. S. G., Lal, S. P., & Guesgen, H. W. (2019) · Sensors · doi:10.3390/s19020379 · Cited by 56
“During training and calibration phase, new subjects learn to voluntarily regulate oscillatory EEG pattern and training trials are collected to obtain discriminative features that are fed into machine learning algorithms for MI classification [8].”
MethodA systematic deep learning model selection for p300-based brain-computer interfaces
Abibullaev, B., & Zollanvari, A. (2022) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2021.3051136 · Cited by 53
“Furthermore, using the specific structure of P3Net prevents the time-consuming model selection process, which, in turn, leads to a reduction in the required calibration time of the BCI [22].”
BackgroundMethodMotor imagery EEG decoding using manifold embedded transfer learning
Cai, Y., She, Q., Ji, J., Ma, Y., Zhang, J., & Zhang, Y. (2022) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2022.109489 · Cited by 53
Towards Adaptive Classification using Riemannian Geometry approaches in Brain-Computer Interfaces
Kumar, S., Yger, F., & Lotte, F. (2019) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/iww-bci.2019.8737349 · Cited by 65
“matrix for motor imagery trials is then estimated using shrinkage based covariance estimator [19] to avoid any numerical problems and provide better estimates, and thus possibly better BCI performances [20].”
MethodSelf-citationOnline Adaptation Boosts SSVEP-Based BCI Performance
Wong, C. M., Wang, Z., Nakanishi, M., Wang, B., Rosa, A., Chen, C. L. P., Jung, T., & Wan, F. (2021) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2021.3133594 · Cited by 55
Wearable Robotics for Upper-Limb Rehabilitation and Assistance
Varghese, R. J., Freer, D., Deligianni, F., Liu, J., & Yang, G. (2018) · Elsevier eBooks · doi:10.1016/b978-0-12-811810-8.00003-8 · Cited by 61
A novel hybrid CNN-Transformer model for EEG Motor Imagery classification
Ma, Y., Song, Y., & Gao, F. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892821 · Cited by 61
“Here we use a 4-40Hz band pass filter as most paper did, to retain a specific frequency range of interest, and remove the effect of eye movement artifact [27], [28].”
MethodJiménez-Guarneros, M., & Fuentes-Pineda, G. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3302938 · Cited by 52
“problem of existing classification systems to new users [13].”
BackgroundCalibration free meta learning based approach for subject independent EEG emotion recognition
Bhosale, S., Chakraborty, R., & Kopparapu, S. K. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103289 · Cited by 55
Small Sample Motor Imagery Classification Using Regularized Riemannian Features
Singh, A. S. G., Lal, S. P., & Guesgen, H. W. (2019) · IEEE Access · doi:10.1109/access.2019.2909058 · Cited by 50
“criminative features from high-dimensional EEG trials are obtained that are fed into machine learning algorithms for MI classification [5].”
MethodUsing EEG to Distinguish Between Writing and Typing for the Same Cognitive Task
Qu, X., Mei, Q., Liu, P., & Hickey, T. J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60735-7_7 · Cited by 54
“[3, 4, 12].”
User’s Self-Prediction of Performance in Motor Imagery Brain–Computer Interface
Ahn, M., Cho, H., Ahn, S., & Jun, S. C. (2018) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2018.00059 · Cited by 50
“But considering the existing literature (Samek et al., 2012; Lotte, 2015; Alimardani et al., 2017), the order of performance across subjects is hardly changed.”
Jiménez-Guarneros, M., & Gómez‐Gil, P. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.11.013 · Cited by 49
FMLAN: A novel framework for cross-subject and cross-session EEG emotion recognition
Yu, P., He, X., Li, H., Dou, H., Tan, Y., Wu, H., & Chen, B. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106912 · Cited by 58
Brain–Computer Interface Contributions to Neuroergonomics
Lotte, F., & Roy, R. N. (2018) · Elsevier eBooks · doi:10.1016/b978-0-12-811926-6.00007-5 · Cited by 53
“Some extensions of such algorithms were also proposed so as to be more robust to noise or limited training data (Samek et al., 2014; Lotte, 2015).”
MethodSelf-citationKang, J.-S., Kavuri, S., & Lee, M. (2019) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2019.2942587 · Cited by 47
Huang, X., Xu, Y., Hua, J., Yi, W., Yin, H., Hu, R., & Wang, S. (2021) · Frontiers in Neuroscience · doi:10.3389/fnins.2021.733546 · Cited by 56
“Lotte (2015) generated numerous artificial labeled samples from the few original labeled samples available for EEG-based BCI by means of segmentation and recombination in the time domain or time-frequency domain.”
BackgroundInfluentialEffect of power feature covariance shift on BCI spatial-filtering techniques: A comparative study
Miladinović, A., Ajčević, M., Jarmolowska, J., Marušič, U., Colussi, M., Silveri, G., Battaglini, P. P., & Accardo, A. (2020) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2020.105808 · Cited by 46
A novel semi-supervised meta learning method for subject-transfer brain–computer interface
Li, J., Wang, F., Huang, H., Qi, F., & Pan, J. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.03.039 · Cited by 50
Navarro-Sune, X., Hudson, A. L., Fallani, F. D. V., Martinerie, J., Witon, A., Pouget, P., Raux, M., Similowski, T., & Chavez, M. (2017) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2016.2592820 · Cited by 41
“The use of regularization or adaptive learning approaches (see [45] and references”
MethodNagasawa, T., Sato, T., Nambu, I., & Wada, Y. (2020) · Journal of Neural Engineering · doi:10.1088/1741-2552/ab6cb9 · Cited by 46
“In EEG analysis, similar simple data augmentation [13], concatenation of the segments from different trials [11, 12], and empirical mode decomposition [14, 15] has showed improvements of BCI accuracies.”
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
“first employed in situations with limited training data, but it has recently been used to suppress the need for BCI calibration data for motor-imagery and P300 based BCIs [15], [16], [17], [18].”
MethodHossain, I., Khosravi, A., Hettiarachchi, I. T., & Nahavandi, S. (2018) · Computational Intelligence and Neuroscience · doi:10.1155/2018/6323414 · Cited by 42
“Calibration time reduction approaches reported in literatures also reflect the scenario well [17–22].”
BackgroundMIEEG-GAN: Generating Artificial Motor Imagery Electroencephalography Signals
Roy, S., Dora, S., McCreadie, K. A., & Prasad, G. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9206942 · Cited by 40
“[3] recently proposed several methods for the artificial generation of EEG trials through the combination and distortion of the real samples, whilst Dinares-Ferran et al.”
MethodGrand Challenges in Neurotechnology and System Neuroergonomics
Fairclough, S. H., & Lotte, F. (2020) · Frontiers in Neuroergonomics · doi:10.3389/fnrgo.2020.602504 · Cited by 54
“A classification algorithm that could be efficiently trained (i.e., from little data) would also reduce the calibration times of current neurotechnologies ( Lotte, 2015).”
MethodSelf-citationEpileptic Seizure Prediction Using Attention Augmented Convolutional Network
Liu, D., Dong, X., Bian, D., & Zhou, W. (2023) · International Journal of Neural Systems · doi:10.1142/s0129065723500545 · Cited by 37
A GAN-Based Data Augmentation Method for Multimodal Emotion Recognition
Luo, Y., Zhu, L., & Lu, B. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-22796-8_16 · Cited by 48
A few filters are enough: Convolutional neural network for P300 detection
Alvarado-González, M., Fuentes-Pineda, G., & Cervantes‐Ojeda, J. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.10.104 · Cited by 46
EEG Signal Processing in MI-BCI Applications With Improved Covariance Matrix Estimators
Olias, J., Martín-Clemente, R., Sarmiento-Vega, M. A., & Cruces, S. (2019) · IEEE transactions on neural systems and rehabilitation engineering · doi:10.1109/tnsre.2019.2905894 · Cited by 34
“This is the case of sLDA [7] a shrinkage variant of LDA and also of the classifiers that exploit the Riemmanian geometry of the manifold of symmetric and positive definite (SPD) matrices.”
BackgroundMethodTransfer Learning Based on Optimal Transport for Motor Imagery Brain-Computer Interfaces
Peterson, V., Nieto, N., Wyser, D., Lambercy, O., Gassert, R., Milone, D. H., & Spies, R. D. (2021) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2021.3105912 · Cited by 43
Preparing Laboratory and Real-World EEG Data for Large-Scale Analysis: A Containerized Approach
Bigdely-Shamlo, N., Makeig, S., & Robbins, K. A. (2016) · Frontiers in Neuroinformatics · doi:10.3389/fninf.2016.00007 · Cited by 35
“Improved BCI classification accuracy and reduced calibration data requirements have already been demonstrated using such approaches (Lotte, 2015).”
BackgroundRimbert, S., Riff, P., Gayraud, N., Schmartz, D., & Bougrain, L. (2019) · Frontiers in Neuroscience · doi:10.3389/fnins.2019.00622 · Cited by 40
“Indeed, transfer learning has proven to be very effective in designing BCIs with little or no calibration for a new user (Lotte, 2015).”
Multi-class Time Continuity Voting for EEG Classification
Qu, X., Liu, P., Li, Z., & Hickey, T. J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60735-7_3 · Cited by 41
“[3, 15].”
Generative AI Enables EEG Data Augmentation for Alzheimer’s Disease Detection Via Diffusion Model
Zhou, T., Chen, X., Shen, Y., Nieuwoudt, M., Pun, C., & Wang, S. (2023) · IEEE International Symposium on Product Compliance Engineering - Asia (ISPCE-ASIA) · doi:10.1109/ispce-asia60405.2023.10365931 · Cited by 50
Qi, H., Xue, Y., Xu, L., Cao, Y., & Jiao, X. (2018) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2018.2801887 · Cited by 33
“[13] incorporated transfer learning and adaptive strategy, and Lotte [15] combined spatial filters and transfer learning.”
BackgroundTCANet: a temporal convolutional attention network for motor imagery EEG decoding
Zhao, W., Lu, H., Zhang, B., Zheng, X., Wang, W., & Zhou, H. (2025) · Cognitive Neurodynamics · doi:10.1007/s11571-025-10275-5 · Cited by 36
“Additionally, a time-domain segmentation and reconstruction (S&R) method (Lotte 2015) is employed to enrich training data while preserving temporal structure.”
Hübner, D., Verhoeven, T., Müller, K., Kindermans, P.-J., & Tangermann, M. (2018) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2018.2807039 · Cited by 41
“For an analysis of transfer learning and unsupervised adaptation in the oscillatory domain, which is not in the scope of this review, we refer to the work by Lotte and colleagues [53].”
MethodHossain, I., Khosravi, A., & Nahavandhi, S. (2016) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2016.7727726 · Cited by 35
A Multi-Source Transfer Joint Matching Method for Inter-Subject Motor Imagery Decoding
Wei, F., Xu, X., Jia, T., Zhang, D., & Wu, X. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3243257 · Cited by 35
“Besides that, a series of MI decoding algorithms have been proposed, such as selecting the optimal frequency band or channels [31], [32], and adding physiological information [15].”
BackgroundMethodAdvantages of EEG phase patterns for the detection of gait intention in healthy and stroke subjects
Sburlea, A. I., Montesano, L., & Mínguez, J. (2017) · Journal of Neural Engineering · doi:10.1088/1741-2552/aa5f2f · Cited by 32
Temporal convolutional transformer for EEG based motor imagery decoding
Altaheri, H., Karray, F., & Karimi, A.-H. (2025) · Scientific Reports · doi:10.1038/s41598-025-16219-7 · Cited by 55
“To mitigate overfitting that arises from the limited amount of labelled EEG available for training, we enlarge the training set using the segmentation and reconstruction (S&R) strategy as introduced by Lotte et al. 57 .”
Dehghani, M., Mobaien, A., & Boostani, R. (2021) · Brain-Computer Interfaces · doi:10.1080/2326263x.2021.1943955 · Cited by 33
Three-Branch Temporal-Spatial Convolutional Transformer for Motor Imagery EEG Classification
Chen, W., Luo, Y., & Wang, J. (2024) · IEEE Access · doi:10.1109/access.2024.3405652 · Cited by 35
Universal EEG Encoder for Learning Diverse Intelligent Tasks
Jolly, B. L. K., Aggrawal, P., Nath, S. S., Gupta, V., Grover, M. S., & Shah, R. R. (2019) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm.2019.00-23 · Cited by 33
“Oscillatory BCI tasks are a limitation for the GRU-based architecture, which should be dealt with.”
MethodInfluentialImproving Generalization of CNN-Based Motor-Imagery EEG Decoders via Dynamic Convolutions
Barmpas, K., Panagakis, Y., Bakas, S., Adamos, D. A., Laskaris, N., & Zafeiriou, S. P. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3265304 · Cited by 33
“One of the renowned challenges in motor-imagery classification problem - as in any medical-related machine learning problem - is the scarcity of labelled data due to the lengthy acquisition process (e.g. [44], [45], [46]).”
BackgroundGao, W., Huang, W., Li, M., Gu, Z., Pan, J., Yu, T., Yu, Z. L., & Li, Y. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3259991 · Cited by 32
“These models are usually obtained using two approaches, i.e., the pooled approach and the ensemble approach [2].”
MethodXu, Y., Wei, Q., Zhang, H., Hu, R., Liu, J., Hua, J., & Guo, F. (2018) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126619501238 · Cited by 27
Metadata
- Authors
- Lotte, F.
- Affiliations
- Centre Inria de l'université de Bordeaux (FR)
- Corresponding author
- Lotte, Fabien
- ORCID
- Lotte, Fabien
- Venue
- Proceedings of the IEEE
- Published
- 2015-06
- Volume
- 103
- Issue
- 6
- Pages
- 871-890
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W1610928686
- Cited by
- 327
- References
- 88
- Citations by year
- 2026: 29 · 2025: 45 · 2024: 36 · 2023: 28 · 2022: 38 · 2021: 30 · 2020: 36 · 2019: 29 · 2018: 25 · 2017: 12 · 2016: 16 · 2015: 3
- FWCI
- 11.10
- Type
- journal article
- Language
- en
- Open access
- green
- inria.hal.science
- Locations
- Proceedings of the IEEE (publishedVersion)
- HAL (submittedVersion, other-oa)
- 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
- brain-computer interface, calibration time reduction, EEG, neural oscillations, semi-supervised learning, regularization, data augmentation, training data size
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.