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
Items 201–300 of 328
Evolving Training Sets for Improved Transfer Learning in Brain Computer Interfaces
Adair, J., Brownlee, A. E. I., Daolio, F., & Ochoa, G. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-72926-8_16 · Cited by 12
Motor Imagery Classification Based on Subject to Subject Transfer in Riemannian Manifold
Singh, A. S. G., Lal, S. P., & Guesgen, H. W. (2019) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/iww-bci.2019.8737256 · Cited by 7
“Second, through different signal processing techniques discriminative features from the high-dimensional EEG trials are fed into machine learning algorithms for MI classification [3].”
MethodKim, K., Kim, K., & Lee, S.-B. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127805 · Cited by 5
Multi-Scale Adaptive Graph Learning Based on Multi-Wave EEG Data for Dementia Diagnosis
Wei, J., Jiao, B., Lin, H., Tian, X., Shen, L., & Liu, J. (2025) · Big Data Mining and Analytics · doi:10.26599/bdma.2025.9020015 · Cited by 8
Hu, H., Zhou, Z., Zhang, Z., & Yuan, W. (2025) · Electronics · doi:10.3390/electronics14142853 · Cited by 5
Abdulwahab, S., Khleaf, H. K., & Jasim, M. H. (2021) · Engineering and Technology Journal · doi:10.30684/etj.v39i7.1854 · Cited by 6
“Even with well pre-possessed EEG data, the BCI has limitations when the brain is used by itself to control the robot [5], [6].”
MethodEEG Data Augmentation Method Based on the Gaussian Mixture Model
Liao, C., Zhao, S., Wang, X., Zhang, J., Liao, Y., & Wu, X. (2025) · Mathematics · doi:10.3390/math13050729 · Cited by 10
Mifnet: a MamBa-based interactive frequency convolutional neural network for motor imagery decoding
Yang, L., & Zhu, W. (2025) · Cognitive Neurodynamics · doi:10.1007/s11571-025-10287-1 · Cited by 6
“Inspired by (Lotte et al. 2015), we apply time-domain segmentation and reconstruction within the same iteration batch on the training data to generate new data, thereby increasing the sample size.”
Mobile BCI Technology: NeuroIS Goes Out of the Lab, into the Field
Wriessnegger, S. C., Krumpl, G., Pinegger, A., & Mueller-Putz, G. R. (2016) · Lecture notes in information systems and organisation · doi:10.1007/978-3-319-41402-7_8 · Cited by 5
Singh, A. K., & Tao, X. (2020) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci47803.2020.9308292 · Cited by 5
“In addition, it is also possible that the pre-processed data does not contain all the information and potentially could be excluded the relevant EEG features depend on the choice of pre-processing such as different filtering [13], channel referencing [14], etc.”
BackgroundGupta, E., & Sivakumar, R. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892115 · Cited by 6
“Traditionally, BCI signal detection has been done using statistical [28] and spatial filtering techniques [29], however more recently, deep learning methods are used as well.”
MethodAutomatic control of reactive brain computer interfaces
Tufvesson, P., & Heskebeck, F. (2024) · IFAC Journal of Systems and Control · doi:10.1016/j.ifacsc.2024.100251 · Cited by 6
Decoding imagined speech for EEG-based BCI
Reyes-Garcia, C. A., Torres-García, A. A., Hernández-Del-Toro, T., García‐Salinas, J. S., & Villaseñor-Pineda, L. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-95439-6.00004-1 · Cited by 7
Transfer Learning for Brain-Computer Interfaces: A Complete PipelinePreprint
Wu, D., Peng, R., Huang, J., & Zeng, Z. (2020) · arXiv (Cornell University) · Cited by 6
FA-STTM: A hybrid Transformer-Mamba network for motor imagery EEG classification
Gao, M., Gao, C., Yao, Z., & Zhu, W. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132481 · Cited by 6
Zhao, J., & Liu, M. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.107163 · Cited by 7
Bai, G., Jin, J., Xu, R., Wang, X., & Cichocki, A. S. (2024) · Cognitive Neurodynamics · doi:10.1007/s11571-023-10053-1 · Cited by 4
“EEG-based BCI includes steady-state visual evoked potential (SSVEP) (Lotte 2015), Event-related Potential (ERP) (Jin et al. 2020), and Motor Imagery (MI) (Liang et al. 2022).”
Self-paced training on motor imagery-based BCI for minimal calibration time
Kim, S., Lee, M.-H., & Lee, S. (2017) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2017.8122963 · Cited by 4
“Alternatively, generating artificial data with a small amount of EEG data was proposed in [4].”
BackgroundMethodZollanvari, A., Abdirash, M., Dadlani, A., & Abibullaev, B. (2019) · IEEE Signal Processing Letters · doi:10.1109/lsp.2019.2918485 · Cited by 4
“Fisher [1] and then formalized by Wald [2] and Anderson [3] in the context of decision theory, has found many applications in its long history in pattern recognition [4]–[7].”
Signal processing algorithms for motor imagery brain-computer interface: State of the art
Hong, J., Qin, X., Li, J., Niu, J., & Wang, W. (2018) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-181309 · Cited by 4
“In recent years, reduction and suppression of calibration time is emphasized [96].”
Carlson, D. E., Chavarriaga, R., Liu, Y.-L., Lotte, F., & Lu, B.-L. (2025) · Journal of Neural Engineering · doi:10.1088/1741-2552/adbfbd · Cited by 9
Self-citationEFRM: A Multimodal EEG–fNIRS Representation-learning Model for few-shot brain-signal classification
Jung, E., & An, J. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.111292 · Cited by 5
sEMG-based gesture recognition using multi-domain feature fusion with a lightweight Vanilla network
Li, Y., Li, K., Wang, X., & Sheng, Y. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.109430 · Cited by 3
Ren, Z., Du, X., Lin, Y., Tian, D., Ma, Y., & Wu, X. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109696 · Cited by 4
Yuan, J., Zhang, R., Zhao, Y., Zhou, W., Tian, L., & Liu, G. L. (2026) · Biomimetics · doi:10.3390/biomimetics11060377 · Cited by 3
“To mitigate overfitting under limited training data, a segmentation-and-reconstruction (S&R) augmentation strategy was applied to the training session only [51].”
Xiang, B., & Abdelmonsef, A. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17615-9_44 · Cited by 5
Deep Pinsker and James-Stein Neural Networks for Decoding Motor Intentions From Limited Data
Angjelichinoski, M., Soltani, M., Choi, J. S., Pesaran, B., & Tarokh, V. (2021) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2021.3083755 · Cited by 4
“It is well-known that neuronal activity is non-stationary across time, space as well as subjects; this occurs as a result of the natural variability of the recording conditions as the experiment proceeds [22], [29], [30].”
BackgroundPiozin, C., Altamira, G. H., Simon, C., Lavrard, B., Audran, J.-Y., Waszak, F., & Eskiizmirliler, S. (2022) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/bci53720.2022.9734823 · Cited by 6
Analyzing Data Augmentation Methods for Convolutional Neural Network-based Brain-Computer Interfaces
Faria, G. O. M., de Souza, G. H., Bernardino, H. S., Motta, L. P., & Vieira, A. B. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9891891 · Cited by 3
“We adopt the same setup used in [10].”
BackgroundMethodInfluentialPMSA-Net: A parallel multi-scale attention network for MI-BCI classification
Cui, M., Chen, T., Jiao, Y., Zheng, Q., Pan, Y. F., & Xie, L. (2024) · ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) · doi:10.1145/3698587.3701382 · Cited by 3
“According to [31], we employed the time-domain segmentation and reconstruction technique to generate new data.”
OFFLINE LINEAR DISCRIMINANT ANALYSIS CLASSFICATION OF TWO CLASS EEG SIGNALS
Abdulkareem, H. A., & Al-Faiz, M. Z. (2019) · Iraqi Journal of Information & Communications Technology · doi:10.31987/ijict.2.3.71 · Cited by 6
“The LDA hyperplane, used to classify EEG features is formulated as [10]: a = V · μT (13)”
MethodTogha, M. M., Salehi, M. R., & Abiri, E. (2020) · Biomedical Physics & Engineering Express · doi:10.1088/2057-1976/ab70e7 · Cited by 3
A Many Objective Optimization Approach for Transfer Learning in EEG ClassificationPreprint
Pal, M., Bandyopadhyay, S., & Bhattacharyya, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.04156 · Cited by 5
“Similarly, the works in [26, 27, 28, 35, 43] uses Linear Discriminant Analysis (LDA) as a base classifier and modifies the covariance matrix or uses covariate shift adaption to make the framework suitable for transfer learning.”
BackgroundMethodInfluentialEnK: Encoding time-information in convolutionPreprint
Singh, A. K., & Lin, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.04198 · Cited by 3
“Other than that, also vary by choice of filtering [21], channel referencing [14], and artifact removal [34] methods.”
BackgroundCen, H., Gu, T., & Zhao, Q. (2024) · International Conference on Data-driven Optimization of Complex Systems (DOCS) · doi:10.1109/docs63458.2024.10704248 · Cited by 2
“Yet, although prior deep learning methods have achieved impressive levels of accuracy, researchers discovered that the performance of models could be significantly influenced when the training and evaluating data are from different individuals due to the inter-subject variability of EEG [7].”
BackgroundA Multi-Scale Attention-Based Reconstruction Fusion Network for Motor Imagery Classification
Qiu, L., Hu, Y. Z., Wu, M., Long, B., Chen, T. L., & Pan, J. (2026) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2026.3668760 · Cited by 2
“To alleviate overfitting caused by limited training samples, we employ the segmentation-and-reconstruction (S&R) strategy [37] for data augmentation.”
Devi, S., Singh, K. J., Singha, N., & Singh, M. K. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05232-6 · Cited by 2
Papon, J. P., Ahmad, M., Mondal, M., & Rahman, M. A. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104683 · Cited by 2
Supervised and Semisupervised Manifold Embedded Knowledge Transfer in Motor Imagery-Based BCI
Xu, Y., Yin, H., Yi, W., Huang, X., Jian, W., Wang, C., & Hu, R. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/1603104 · Cited by 4
“+e artificial data generation method can generate numerous artificial labelled data by recombining the few original labelled data in the time and frequency domains [29].”
MethodA Multitask Bayesian Framework for the analysis of Motor Imagery EEG Data
Oikonomou, V. P., Nikolopoulos, S., & Kompatsiaris, I. Y. (2022) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco55093.2022.9909921 · Cited by 5
Structure invariance-driven collaborative contrastive network for EEG decoding
Liang, S., Li, Z., Hang, W., Zhang, Y., Lei, B., Qin, J., Zhang, Y., & Choi, K. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105214 · Cited by 2
Saito, Y., Kamagata, K., Akashi, T., Wada, A., Shimoji, K., Hori, M., Kuwabara, M., Ryota Kanai, C., & Aoki, S. (2023) · Juntendō Igaku/Juntendo igaku · doi:10.14789/jmj.jmj23-0011-r · Cited by 2
“To overcome this problem, artificial EEG signal generation methods based on time-frequency representation ( TFR ) and analogy methods were proposed 24 ) .”
MethodMI-EEG Recognition Based on Euclidean Alignment and Style Transfer Mapping
Niu, X., Zhang, X., & Yang, L. (2022) · International Conference on Computational Modeling, Simulation and Data Analysis (CMSDA) · doi:10.1109/cmsda58069.2022.00039 · Cited by 2
Working memory load recognition with deep learning time series classification
Pang, R.-D., Sang, H., Yi, L., Gao, C., Xu, H., Wei, Y., Zhang, L., & Sun, J. (2024) · Biomedical Optics Express · doi:10.1364/boe.516063 · Cited by 4
“The feature extraction raised a 72×352 data set for every subject, then the LASSO regression was conducted to retract some redundant features to improve the recognition accuracy.”
MethodSun, Q., Wang, L., Zhang, L., Gong, P., Zhou, Y., & Zhang, D. (2024) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi56570.2024.10635172 · Cited by 2
“In order to fully utilize EEG data, we employ the segmentation and reconstruction (S&R) method [10] to augment EEG data.”
MethodHuang, J., Li, M., & Chen, W. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103298 · Cited by 8
Towards subject-centered co-adaptive brain–computer interfaces based on backward optimal transport
Peterson, V., Spagnolo, V., Galván, C. M., Nieto, N., Spies, R. D., & Milone, D. H. (2025) · Journal of Neural Engineering · doi:10.1088/1741-2552/addb7a · Cited by 2
“The common spatial pattern (CSP) in conjunction with the linear discriminant analysis (LDA) are used to build the decoding algorithm [21].”
InfluentialHigashi, H., Rutkowski, T. M., Tanaka, T., & Tanaka, Y. (2015) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2015.7415409 · Cited by 3
“As the subspaces {Sn}n=1 for SC-DGTDA, we propose the subspace design method using datasets from other participants [22], [25].”
MethodCalibration Time Reduction for Motor Imagery-Based BCI Using Batch Mode Active Learning
Hossain, I., & Hettiarachchi, I. T. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489547 · Cited by 2
“Therefore, attempt to reduce the training data to attain robust performance has an utmost significance in BCI system development process [8].”
Weighted Subject-Semi-Independent ERP-based Brain-Computer Interface
An, X., Zhou, X., Zhong, W., Liu, S., Li, X., & Ming, D. (2020) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc44109.2020.9176683 · Cited by 2
“[9] introduced a method using modified EEG data.”
MethodSubject-Independent Motor Imagery EEG Classification Based on Graph Convolutional Network
Lee, J., Choi, J. W., & Jo, S. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-02444-3_20 · Cited by 3
“In general, human EEG signals change according to the difference in each individual’s mental state, resulting in large variability on inter-subject relations [19, 20].”
BackgroundPorssut, T., Gouret, A., Bryzgalov, D., Lafont, A., Rouzé, S., & Bars, S. L. (2023) · IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE) · doi:10.1109/metroxraine58569.2023.10405804 · Cited by 2
“CCA is often used when studying VEP-based BCI [21] to classify VEP automatically.”
MethodAn Optimized Self-adjusting Model for EEG Data Analysis in Online Education Processes
Zhang, H., Lee, S., & He, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59277-6_31 · Cited by 2
A few filters are enough: Convolutional Neural Network for P300 DetectionPreprint
Alvarado-Gonzalez, A. M., Fuentes-Pineda, G., & Cervantes‐Ojeda, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.06970 · Cited by 2
“These characteristics may be a disadvantage for P300 detection, mostly due to the limited training data available [16, 4].”
BackgroundVisual Motion Imagery Classification with Deep Neural Network based on Functional ConnectivityPreprint
Kwon, B.-H., Jeong, J.-H., & Lee, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.02851 · Cited by 3
Fraser, A. (2021) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2021-14400 · Cited by 2
Khalili, M. D., Abootalebi, V., & Saeedi‐Sourck, H. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.08.28.555094 · Cited by 2
“In ERP-based BCI [61] and oscillatory activity BCI [62], the resulting SLDA classifier has demonstrated superiority over the conventional LDA classifier.”
MethodCross-Dataset Montage Alignment via Electroencephalogram Source Imaging for Enhanced Motor Decoding
Xiang, T., Wang, W.-K., Zhou, X.-H., Yang, H., Gui, M.-J., Xie, X., Liu, S.-Q., Wang, J., Liu, J., & Hou, Z. (2025) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2025.3624805 · Cited by 2
“It encourages models to learn invariant features by applying transformations to the original EEG signals in the spatial [25], [26], [38], temporal [27], [39], [40], and frequency domains [27], [41], or by employing comprehensive dataset-level transformation [28], [29], [42].”
Duan, S., Li, P., Ding, Y., Wang, K., Yu, D., & Cheng, L. (2025) · Biomedical Engineering Letters · doi:10.1007/s13534-025-00542-z · Cited by 1
Qi, W., Wang, X., Yang, W., & Wang, W. (2026) · Biomedical Physics & Engineering Express · doi:10.1088/2057-1976/ae33c7 · Cited by 1
FSTAM-net: A dual attention network for motor imagery decoding and visualization analysis
Fu, S., Shi, B., Wei, Y., Wu, D., Yin, S., Liu, G., Zhang, J., Zhu, A., Wang, J., & Zhou, G. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109916 · Cited by 1
Khan, S. A., Salem, A., & Jiang, J. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134459 · Cited by 1
Kao, C. (2017) · International Journal of Computers and Applications · doi:10.1080/1206212x.2017.1313490 · Cited by 1
“A Brain–Computer Interface (BCI) is a communication system that enables a subject to send commands to an electronic device by brain activity [1,2].”
BackgroundMotor imagery classification method based on long and short windows interception
Liu, X., Yan, P., Zhang, S., & Zheng, D. (2022) · Measurement Science and Technology · doi:10.1088/1361-6501/ac6cc8 · Cited by 1
ML vs DL: Accuracy and Testing Runtime Trade-offs in BCI
Tuvshinjargal, A., & Kim, E. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17618-0_35 · Cited by 1
Convolutional Neural Networks Approach Comparison in EEG-Based BCIs
Marques, D. C., Cagy, M., & de Sá, A. M. F. L. M. (2024) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-031-49407-9_15 · Cited by 1
Zhan, H., Li, X., Song, X., Lv, Z., & Li, P. (2025) · Bioengineering · doi:10.3390/bioengineering12070775 · Cited by 1
“To solve this problem, MCTGNet adopts a class-consistent data augmentation strategy [48] based on time-series slicing and recombination (S&R).”
Asynchronous Brain Computer Interfaces Using Echo State Networks
Zakkay, E., Abu-Rmileh, A., Geva, A. B., & Shriki, O. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207481 · Cited by 2
“While CSP methods (which are also usually followed by an LDA classifier [19]) might result in more informative features, they usually require recording from a large number of electrodes to be efficient [20], [21].”
MethodAnálisis de las interfaces cerebro-máquina basadas en imaginación motora de la marcha
Ferrero, L., Quiles, V., Ortiz, M., Iáñez, E., Flores, J. A., & Azorín, J. M. (2021) · Servizo de Publicacións da UDC eBooks · doi:10.17979/spudc.9788497498043.133 · Cited by 1
“Por otro lado, si se diseñasen BMI más generalizadas, se podrían utilizar los datos de sesiones previas para el bucle-cerrado o incluso de otros usuarios [22].”
BackgroundEffect of Hand Dominance When Decoding Motor Imagery Grasping Tasks
Nergård, K. L., Endestad, T., & Tørresen, J. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-08443-0_15 · Cited by 1
ERP-XTTN: interpretable prototype-guided cross-attention for cross-subject ERP classification
Genevier Wyman, C., & Hirshfield, L. (2026) · Journal of Neural Engineering · doi:10.1088/1741-2552/ae9f95
“Classification must generalize across subjects, since per-subject calibration delays setup and limits scalability [4], and standard calibration pipelines fail to produce a functional classifier for a non-negligible portion of users [5].”
An Approach to Minimize Calibration Time for Brain Computer Interface Based on Motion Imagery
Zou, Y., Zhao, X., Xu, W., & Jianda, H. (2017) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber.2017.8446610
“Lotte’s method get a much better result than the semi-supervised study, but this result is for the two types classification problem too.”
MethodInfluentialHossain, I., Khosravi, A., Hettiarachchi, I. T., & Nahavandi, S. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489209
“Therefore, reduction of training sample or zero training BCI is one of the most cited problems for BCI [4].”
BackgroundBrain-computer interface for mental attention
Fahimi, F. (2019) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/137001
Anindya, S. F., & Darmakusuma, R. (2020) · doi:10.1109/ibiomed50285.2020.9487602
Optimal Calibration Time for Lower-Limb Brain–Machine Interfaces
Ferrero, L., Quiles, V., Ortíz, M., Iáñez, E., Contreras-Vidal, J. L., & Azorín, J. M. (2021) · Biosystems & biorobotics · doi:10.1007/978-3-030-70316-5_10
Statistical learning and inference in neural signal processing: applications to brain interfaces
Özdenizci, O. (2020) · Digital Repository Service (Northeastern University) · doi:10.17760/d20382835
Clerc, M., Bougrain, L., & Lotte, F. (2016) · doi:10.1002/9781119144977.fmatter
Self-citationOptimizing ML Algorithms Under CSP and Riemannian Covariance in MI-BCIs
Windhorse, Y., & Almadbooh, N. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17618-0_38 · Cited by 1
A Decoding Model of Upper Limb Movement Intention Based on Data Augmentation
Ke, X., Bi, L., Fei, W., & Feleke, A. G. (2022) · China Automation Congress (CAC) · doi:10.1109/cac57257.2022.10055468
“in [6] also pointed out that after the split reorganization in the time-domain, an artificial signal in the higher frequency band may be generated at the junction, thereby introducing impurity signals.”
BackgroundSeizure Prediction Based on Multidimensional EEG Spatial Matrix and Residual Network Structure
Zhang, J., Meng, Q., & Wang, Z. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-4749-2_24 · Cited by 1
EEG Data Enhancement and Emotion Recognition Based on Generative Adversarial Networks
Wang, T., Sun, J., Li, Z., & Zhang, Z. (2023) · IEEE International Conference on Electronic Information and Communication Technology (ICEICT) · doi:10.1109/iceict57916.2023.10245428
Park, S., Jeong, B., & Kim, H. (2024) · Journal of the Korea Institute of Military Science and Technology · doi:10.9766/kimst.2023.26.5.422
Construction of the Indonesian Presidents’ Speeches at the UN: Historical Discourse Analysis
Risaldi, A., & Santoso, A. (2024) · KEMBARA Journal of Scientific Language Literature and Teaching · doi:10.22219/kembara.v10i1.27085
Goswami, S., Phelan, J., Anderson, S., & Arvaneh, M. (2024) · IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE) · doi:10.1109/metroxraine62247.2024.10795940
“We investigate straightforward augmentation techniques, such as segmentation and recombination in the time-frequency domain using the short-time Fourier transform (TFSR) [19].”
InfluentialAn improved multi-scale convolution and transformer network for EEG-based motor imagery decoding
Zhu, L., Wang, Y., Huang, A., Tan, X., & Zhang, J. (2025) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-025-02556-6 · Cited by 4
“Following the approach described in [45], we divide training samples of the same category into n segments on average and randomly recombine them while maintaining the original temporal order.”
Li, L., Jiang, Y., Zan, P., Yue, J., & Li, C. (2025) · Review of Scientific Instruments · doi:10.1063/5.0240003
Analysis of Window-Delay Score for Data Augmentation Methods in Brain-Computer Interfaces
Maurício, J. S. S., Amorim, M. M., Vieira, A. B., Bernardino, H. S., & de Souza, G. H. (2024) · doi:10.5753/eniac.2024.245225 · Cited by 1
Leveraging Exoskeleton-Induced Finger Proprioception from EEG for Enhanced Motor Intention DecodingPreprint
Sun, Q., Merino, E. C., & Hulle, M. M. V. (2025) · doi:10.36227/techrxiv.174702151.11095405/v1
Yin, F., Si, F., Jiang, W., Huo, S., Wang, B., Yang, N., & Cao, J. (2025) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2025.1564049
Using Riemannian Processing to Represent Manifolds in EEG
Yamauti, S. Y., Soares, A. K. A., Filho, G. O. S., Costa, A. B., de Albuquerque, T. S., & Vasiljevic, G. A. M. (2025) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-031-93646-3_96
From signals to decisions in noninvasive neural technologies
Cabestaing, F., & Chevallier, S. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-24824-5.00020-x · Cited by 1
Tian, Z. (2025) · Science and Technology of Engineering Chemistry and Environmental Protection · doi:10.61173/zkk51s84
del Valle, D. C. V., Forero, A. Q., FARABELLO, J. S., Arlettaz, M. E., Schiaffino, L., Carrere, L. C., Tabernig, C. B., & Acevedo, R. (2025) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-032-06401-1_87
FSTAM-net: A Dual Attention Network for Motor Imagery Decoding and Visualization AnalysisPreprint
Fu, S., Shi, B., Wu, D., Yin, S., Liu, G., Zhang, J., Zhu, A., Zhou, G., & Wang, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5615153
Brain-Computer Interface of Motor Imagery EEG Signal Using Hybrid GNN-Mamba Networks
Jamil, B. I., & Djamal, E. C. (2025) · International Conference on Informatics and Computing (ICIC) · doi:10.1109/icic68054.2025.11309504
“To expand the dataset and improve generalization, we applied a Segmentation and Reconstruction (S&R) method [15], [13], in which each trial was divided into four segments and randomly recombined within the same class to generate ~100 additional trials per class per subject.”
Xie, T., Zhao, W., Liu, Y., Chen, L., Bao, Z., Zhang, B., & Qiu, Y. (2025) · International Symposium on Artificial Intelligence for Medicine Sciences (ISAIMS) · doi:10.1145/3777577.3777695
“Following the segmentation–recombination (S&R) scheme [ 15 ] , each training trial was partitioned into non-overlapping segments, and synthetic trials were created by stitching together segments drawn from different trials of the same class while maintaining the temporal order.”
Fu, J. Z. X., Yang, L., Sun, Y., Du, J., & Wang, Q. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11357111
“Despite this, the cross-subject task faces significant challenges: high variability and non-stationarity of EEG across individuals cause severe performance degradation on new users [3].”
Khalili, M. D., Abootalebi, V., & Saeedi‐Sourck, H. (2026) · Journal of Medical Signals & Sensors · doi:10.4103/jmss.jmss_88_24 · Cited by 2
“In ERP‑based BCI [53] and oscillatory activity BCI, [54] the resulting SLDA classifier has demonstrated superiority over the conventional LDA classifier.”
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.