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].”
Caruana, R. (1998) · Cited by 1,110
Brain–Computer InterfacesPrinciples and Practice
Wolpaw, J., & Wolpaw, E. W. (2012) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780195388855.001.0001 · Cited by 1,104
Regularizing Common Spatial Patterns to Improve BCI Designs: Unified Theory and New Algorithms
Lotte, F., & Guan, C. (2011) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2010.2082539 · Cited by 1,045 · cited 1×
“Similarly, one can use as prior information which channels are the most likely to be useful and use that as a regularizer to optimize spatial filters [55].”
Self-citationBrain–machine interface in chronic stroke rehabilitation: A controlled study
Ramos‐Murguialday, A., Broetz, D., Rea, M., Läer, L., Yilmaz, Ö., Brasil, F. L., Liberati, G., Curado, M. R., Garcia‐Cossio, E., Vyziotis, A., et al. (2013) · Annals of Neurology · doi:10.1002/ana.23879 · Cited by 994 · cited 1×
“…for a number of applications for which ERP-based BCI cannot be used, including (but not limited to) self-paced BCI control [23], [24], stroke rehabilitation [25], [26] or passive BCI that monitor and adapt an application based on users’ mental states such as attention or workload [7], [27], [28].”
MethodBlankertz, B., Dornhege, G., Krauledat, M., Müller, K.-R., & Curio, G. (2007) · NeuroImage · doi:10.1016/j.neuroimage.2007.01.051 · Cited by 946 · cited 1×
“For instance, a typical online BCI based on motor imagery (i.e., imagination of movements) requires a calibration time of about 20 min [11], which is still far too long.”
BackgroundZander, T. O., & Kothe, C. (2011) · Journal of Neural Engineering · doi:10.1088/1741-2560/8/2/025005 · Cited by 887 · cited 2×
“Moreover, oscillatory activity-based BCI can be useful for a number of applications for which ERP-based BCI cannot be used, including (but not limited to) self-paced BCI control [23][24], stroke rehabilitation [25][26] or passive BCI that monitor and adapt an application based on users’ mental states such as attention…”
BackgroundMethodMulticlass Brain–Computer Interface Classification by Riemannian Geometry
Barachant, A., Bonnet, S., Congedo, M., & Jutten, C. (2012) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2011.2172210 · Cited by 878
EMG and EOG artifacts in brain computer interface systems: A survey
Fatourechi, M., Bashashati, A., Ward, R. K., & Birch, G. E. (2007) · Clinical Neurophysiology · doi:10.1016/j.clinph.2006.10.019 · Cited by 638 · cited 1×
“…in small sample size settings, as when little data is available, a single outlier (artefacts being un-fortunately rather common in EEG measurements [82]) can have dramatic negative effects on the quality of the optimized BCI; 3) combining user-independent BCI de-sign followed by online adaptation…”
MethodTowards adaptive classification for BCI
Shenoy, P., Krauledat, M., Blankertz, B., Rao, R. P. N., & Müller, K.-R. (2006) · Journal of Neural Engineering · doi:10.1088/1741-2560/3/1/r02 · Cited by 438 · cited 1×
“…data is available to calibrate the BCI for a given user, another approach that can be used to still reach reasonable classification performance is to use an adaptive approach [46], [47], i.e., to refine the calibration of the BCI during use, as new EEG data (labeled or not) become available.”
MethodBrain-Computer Interfaces, Virtual Reality, and Videogames
Lecuyer, A., Lotte, F., Reilly, R. B., Leeb, R., Hirose, M., & Slater, M. (2008) · Computer · doi:10.1109/mc.2008.410 · Cited by 402 · cited 2×
“, to provide some communication abilities to severely disabled users [4], as a new control device for gaming for healthy users [5], [6] or to design adaptive human–computer interfaces that can react to the user’s mental state [7], among many other promising applications [1], [8].”
BackgroundSelf-citationCombined Optimization of Spatial and Temporal Filters for Improving Brain-Computer Interfacing
Dornhege, G., Blankertz, B., Krauledat, M., Losch, F., Curio, G., & Muller, K.-R. (2006) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2006.883649 · Cited by 394 · cited 1×
“, [75], [76], [77], [78], [79], [80], [81], 2) outlier/artifact removal in small sample size settings, as when few data are available, a single outlier (artefacts being unfortunately rather common in EEG measurements [82]) can have dramatic negative effects on the quality of the optimized BCI, 3) combining user-indepe…”
BackgroundBrain-Computer Interfaces: Beyond Medical Applications
van Erp, J., Lotte, F., & Tangermann, M. (2012) · Computer · doi:10.1109/mc.2012.107 · Cited by 362
Self-citationP300 brain computer interface: current challenges and emerging trends
Fazel-Rezai, R., Allison, B. Z., Guger, C., Sellers, E. W., Kleih, S. C., & Kübler, A. (2012) · Frontiers in Neuroengineering · doi:10.3389/fneng.2012.00014 · Cited by 359 · cited 1×
“Indeed, ERP are usually more stable across users than EEG oscillations [13], [14], and the specific structures of ERP spellers can be exploited in a smart way to reduce or suppress the need for calibration [15], [16].”
BackgroundThe Berlin Brain–Computer Interface: Non-Medical Uses of BCI Technology
Blankertz, B., Tangermann, M., Vidaurre, C., Fazli, S., Sannelli, C., Haufe, S., Maeder, C., Ramsey, L., Sturm, I., Curio, G., et al. (2010) · Frontiers in Neuroscience · doi:10.3389/fnins.2010.00198 · Cited by 357 · cited 1×
“Among the different reasons currently preventing BCI from being widely used outside laboratories for practical applications, one can cite their lack of robustness and reliability, their cum-bersome setup and their long calibration time [1], [8], [9].”
BackgroundThe Berlin brain-computer Interface: accurate performance from first-session in BCI-naive subjects
Blankertz, B., Losch, F., Krauledat, M., Dornhege, G., Curio, G., & Muller, K.-R. (2008) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2008.923152 · Cited by 338 · cited 2×
“[31] B.”
BackgroundA New Discriminative Common Spatial Pattern Method for Motor Imagery Brain–Computer Interfaces
Thomas, K. P., Guan, C., Lau, C. T., Vinod, A. P., & Ang, K. K. (2009) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2009.2026181 · Cited by 321
Regularized Common Spatial Pattern With Aggregation for EEG Classification in Small-Sample Setting
Lu, H., Eng, H.-L., Guan, C., Plataniotis, K. N., & Venetsanopoulos, A. N. (2010) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2010.2082540 · Cited by 309 · cited 4×
“…estimate used in CSP and/ or LDA for each class can be regularized to reassemble the covariance matrices of other users as follows: where P can be the average covariance matrix of the other users [35], a weighted average of them [36], or an average of the covariance matrices of selected users [33].”
BackgroundMethodInfluentialLotte, F., Larrue, F., & Mühl, C. (2013) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2013.00568 · Cited by 307 · cited 1×
“Indeed, on the one hand, calibration reduction enables us to provide BCI users with feedback as early as possible, such feedback being necessary for efficient training [84].”
MethodSelf-citationToward Unsupervised Adaptation of LDA for Brain–Computer Interfaces
Vidaurre, C., Kawanabe, M., von Bünau, P., Blankertz, B., & Müller, K. R. (2011) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2010.2093133 · Cited by 296 · cited 1×
“…data is available to calibrate the BCI for a given user, another approach that can be used to still reach reasonable classification performance is to use an adaptive approach [46], [47], i.e., to refine the calibration of the BCI during use, as new EEG data (labeled or not) become available.”
MethodSeperability of four-class motor imagery data using independent components analysis
Naeem, M., Brunner, C., Leeb, R., Graimann, B., & Pfurtscheller, G. (2006) · Journal of Neural Engineering · doi:10.1088/1741-2560/3/3/003 · Cited by 295 · cited 1×
“The first data set used is data set 2a from BCI competition IV, provided by the Graz group [70].”
MethodConversion of EEG activity into cursor movement by a brain-computer interface (BCI)
Fabiani, G. E., McFarland, D. J., Wolpaw, J. R., & Pfurtscheller, G. (2004) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2004.834627 · Cited by 292 · cited 2×
“, [2] and [3].”
Composite Common Spatial Pattern for Subject-to-Subject Transfer
Kang, H., Nam, Y., & Choi, S. (2009) · IEEE Signal Processing Letters · doi:10.1109/lsp.2009.2022557 · Cited by 265
Subject-independent mental state classification in single trials
Fazli, S., Popescu, F., Danóczy, M., Blankertz, B., Müller, K.-R., & Grozea, C. (2009) · Neural Networks · doi:10.1016/j.neunet.2009.06.003 · Cited by 252
Towards Zero Training for Brain-Computer Interfacing
Krauledat, M., Tangermann, M., Blankertz, B., & Müller, K.-R. (2008) · PLoS ONE · doi:10.1371/journal.pone.0002967 · Cited by 249 · cited 1×
“In [59], a clustering approach was used to suppress recalibration for a user for which data from previous days was available.”
MethodA Novel Bayesian Framework for Discriminative Feature Extraction in Brain-Computer Interfaces
Suk, H.-I., & Lee, S.-W. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.69 · Cited by 241 · cited 1×
“, [75], [76], [77], [78], [79], [80], [81], 2) outlier/artifact removal in small sample size settings, as when few data are available, a single outlier (artefacts being unfortunately rather common in EEG measurements [82]) can have dramatic negative effects on the quality of the optimized BCI, 3) combining user-indepe…”
BackgroundLi, Y., Guan, C., Li, H., & Chin, Z. (2008) · Pattern Recognition Letters · doi:10.1016/j.patrec.2008.01.030 · Cited by 228
Turning Shortcomings into Challenges: Brain-Computer Interfaces for Games
Nijholt, A., Reuderink, B., & Oude Bos, D. (2009) · Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-642-02315-6_15 · Cited by 223 · cited 1×
“…technology, e.g., to provide some communication abilities to severely disabled users [4], as a new control device for gaming for healthy users [5], [6] or to design adaptive human–computer interfaces that can react to the user’s mental state [7], among many other promising applications [1], [8].”
BackgroundRehabilitation with Brain-Computer Interface Systems
Pfurtscheller, G., Muller-Putz, G. R., Scherer, R., & Neuper, C. (2008) · Computer · doi:10.1109/mc.2008.432 · Cited by 222 · cited 1×
“, to provide some communication abilities to severely disabled users [4], as a new control device for gaming for healthy users [5], [6] or to design adaptive human–computer interfaces that can react to the user’s mental state [7], among many other promising applications [1], [8].”
BackgroundTurning shortcomings into challenges: Brain–computer interfaces for games
Nijholt, A., Bos, D. P.-O., & Reuderink, B. (2009) · Entertainment Computing · doi:10.1016/j.entcom.2009.09.007 · Cited by 217
Brain-Computer Interface in Stroke Rehabilitation
Ang, K. K., & Guan, C. (2013) · Journal of Computing Science and Engineering · doi:10.5626/jcse.2013.7.2.139 · Cited by 212 · cited 1×
“…for a number of applications for which ERP-based BCI cannot be used, including (but not limited to) self-paced BCI control [23], [24], stroke rehabilitation [25], [26] or passive BCI that monitor and adapt an application based on users’ mental states such as attention or workload [7], [27], [28].”
MethodMachine-learning-based coadaptive calibration for brain-computer interfaces
Vidaurre, C., Sannelli, C., Müller, K.-R., & Blankertz, B. (2011) · Neural Computation · doi:10.1162/neco_a_00089 · Cited by 207 · cited 1×
“…un-fortunately rather common in EEG measurements [82]) can have dramatic negative effects on the quality of the optimized BCI; 3) combining user-independent BCI de-sign followed by online adaptation to completely remove calibration and quickly reach high performances, as suggested in [69], [83].”
MethodBeamforming in Noninvasive Brain–Computer Interfaces
Grosse-Wentrup, M., Liefhold, C., Gramann, K., & Buss, M. (2009) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2008.2009768 · Cited by 182
Wu, W., Gao, X., Hong, B., & Gao, S. (2008) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2008.919125 · Cited by 179 · cited 1×
“, [75], [76], [77], [78], [79], [80], [81], 2) outlier/artifact removal in small sample size settings, as when few data are available, a single outlier (artefacts being unfortunately rather common in EEG measurements [82]) can have dramatic negative effects on the quality of the optimized BCI, 3) combining user-indepe…”
BackgroundSpüler, M., Rosenstiel, W., & Bogdan, M. (2012) · PLoS ONE · doi:10.1371/journal.pone.0051077 · Cited by 177 · cited 2×
“[22] M.”
Divergence-Based Framework for Common Spatial Patterns Algorithms
Samek, W., Kawanabe, M., & Muller, K.-R. (2014) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2013.2290621 · Cited by 174 · cited 2×
“Multi-task learning [38], [39], [40], [41]”
MethodSpelling with non-invasive Brain–Computer Interfaces – Current and future trends
Cecotti, H. (2011) · Journal of Physiology-Paris · doi:10.1016/j.jphysparis.2011.08.003 · Cited by 172 · cited 1×
“ERP have been extensively used to design BCI-based spellers exploiting the user’s brain responses to attended visual stimulus, including the P300 and the N200 [12]; 2) Oscillatory activity-based BCI which exploit changes in the amplitudes of EEG oscillations due to spontaneously performed mental tasks (e.”
MethodEEG-based workload estimation across affective contexts
Mühl, C., Jeunet, C., & Lotte, F. (2014) · Frontiers in Neuroscience · doi:10.3389/fnins.2014.00114 · Cited by 163 · cited 5×
“[27] C.”
MethodInfluentialSelf-citationLearning from other subjects helps reducing Brain-Computer Interface calibration time
Lotte, F., & Guan, C. (2010) · 2010 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2010.5495183 · Cited by 144
Self-citationUnsupervised Brain Computer Interface Based on Intersubject Information and Online Adaptation
Lu, S., Guan, C., & Zhang, H. (2009) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2009.2015197 · Cited by 122
A subject transfer framework for EEG classification
Tu, W., & Sun, S. (2011) · Neurocomputing · doi:10.1016/j.neucom.2011.10.024 · Cited by 118 · cited 1×
“In [42], spatial filters were optimized separately on the data of each other user available, and then the spatial filters that work well across users and for the target user were identified.”
MethodSubject and class specific frequency bands selection for multiclass motor imagery classification
Suk, H., & Lee, S. (2011) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.20283 · Cited by 115 · cited 1×
“, [75], [76], [77], [78], [79], [80], [81], 2) outlier/artifact removal in small sample size settings, as when few data are available, a single outlier (artefacts being unfortunately rather common in EEG measurements [82]) can have dramatic negative effects on the quality of the optimized BCI, 3) combining user-indepe…”
BackgroundThe Self-Paced Graz Brain-Computer Interface: Methods and Applications
Scherer, R., Schloegl, A., Lee, F., Bischof, H., Janša, J., & Pfurtscheller, G. (2007) · Computational Intelligence and Neuroscience · doi:10.1155/2007/79826 · Cited by 113 · cited 1×
“…BCI can be useful for a number of applications for which ERP-based BCI cannot be used, including (but not limited to) self-paced BCI control [23], [24], stroke rehabilitation [25], [26] or passive BCI that monitor and adapt an application based on users’ mental states such as attention or…”
MethodMultitask Learning for Brain-Computer Interfaces
Alamgir, M., Grosse‐Wentrup, M., & Altün, Y. (2010) · Max Planck Institute for Plasma Physics · Cited by 108
Multisubject Learning for Common Spatial Patterns in Motor-Imagery BCI
Devlaminck, D., Wyns, B., Grosse-Wentrup, M., Otte, G., & Santens, P. (2011) · Computational Intelligence and Neuroscience · doi:10.1155/2011/217987 · Cited by 107
Review of the Use of Electroencephalography as an Evaluation Method for Human-Computer Interaction
Frey, J., Mühl, C., Lotte, F., & Hachet, M. (2014) · International Conference on Physiological Computing Systems (PhyCS) · doi:10.5220/0004708102140223 · Cited by 103 · cited 1×
“…for a number of applications for which ERP-based BCI cannot be used, including (but not limited to) self-paced BCI control [23], [24], stroke rehabilitation [25], [26] or passive BCI that monitor and adapt an application based on users’ mental states such as attention or workload [7], [27], [28].”
MethodSelf-citationBayesian common spatial patterns for multi-subject EEG classification
Kang, H., & Choi, S. (2014) · Neural Networks · doi:10.1016/j.neunet.2014.05.012 · Cited by 103 · cited 2×
“Multi-task learning [38], [39], [40], [41]”
MethodKindermans, P.-J., Tangermann, M., Müller, K.-R., & Schrauwen, B. (2014) · Journal of Neural Engineering · doi:10.1088/1741-2560/11/3/035005 · Cited by 98 · cited 2×
“[16] P.”
BackgroundFriedrich, E. V. C., Neuper, C., & Scherer, R. (2013) · PLoS ONE · doi:10.1371/journal.pone.0076214 · Cited by 89 · cited 2×
“EEG signals were band-pass filtered in the 8–30-Hz frequency band, as in [73].”
MethodKindermans, P.-J., Verstraeten, D., & Schrauwen, B. (2012) · PLoS ONE · doi:10.1371/journal.pone.0033758 · Cited by 81 · cited 2×
“Indeed, ERP are usually more stable across users than EEG oscillations [13], [14], and the specific structures of ERP spellers can be exploited in a smart way to reduce or suppress the need for calibration [15], [16].”
BackgroundOptimum Spatio-Spectral Filtering Network for Brain–Computer Interface
Zhang, H., Chin, Z. Y., Ang, K. K., Guan, C., & Wang, C. (2010) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2010.2084099 · Cited by 75 · cited 1×
“, [75], [76], [77], [78], [79], [80], [81], 2) outlier/artifact removal in small sample size settings, as when few data are available, a single outlier (artefacts being unfortunately rather common in EEG measurements [82]) can have dramatic negative effects on the quality of the optimized BCI, 3) combining user-indepe…”
BackgroundComparison of designs towards a subject-independent brain-computer interface based on motor imagery
Lotte, F., Guan, C., & Ang, K. K. (2009) · 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/iembs.2009.5334126 · Cited by 74 · cited 3×
“1) A pooled user-independent design , studied in [56], which simply consists of pooling together the EEG data of all available users, and then training CSP filters and a LDA classifier on them.”
BackgroundMethodInfluentialSelf-citationLi, Y., & Guan, C. (2007) · Machine Learning · doi:10.1007/s10994-007-5039-1 · Cited by 70 · cited 2×
“For BCI, this approach has been used with CSP features and an LDA or support vector machine (SVM) classifier [49]– [51].”
MethodA New Generation of Brain-Computer Interface Based on Riemannian Geometry
Congedo, M., Barachant, A., & Andreev, A. (2013) · arXiv · doi:10.48550/arxiv.1310.8115 · Cited by 69 · cited 2×
“…un-fortunately rather common in EEG measurements [82]) can have dramatic negative effects on the quality of the optimized BCI; 3) combining user-independent BCI de-sign followed by online adaptation to completely remove calibration and quickly reach high performances, as suggested in [69], [83].”
Methodℓ1-penalized linear mixed-effects models for high dimensional data with application to BCI
Fazli, S., Danóczy, M., Schelldorfer, J., & Müller, K. (2011) · NeuroImage · doi:10.1016/j.neuroimage.2011.03.061 · Cited by 57 · cited 2×
“More recently, the same group explored l1-penalized linear mixed-effect models to identify and separate within-user variability from between-user variability, hence extracting a more efficient user-independent model [61].”
BackgroundA subject-independent brain-computer interface based on smoothed, second-order baselining
Reuderink, B., Farquhar, J., Poel, M., & Nijholt, A. (2011) · 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/iembs.2011.6091139 · Cited by 54 · cited 1×
“To address the between-user variability, a spatial normalization scheme, based on unlabeled data, can be used to make the data of different users spatially similar, and thus improve the performance of a user-independent BCI system optimized on data from multiple users [58].”
MethodGenerating Artificial EEG Signals To Reduce BCI Calibration Time
Lotte, F. (2011) · HAL · Cited by 48
Self-citationCSP patches: an ensemble of optimized spatial filters. An evaluation study
Sannelli, C., Vidaurre, C., Müller, K., & Blankertz, B. (2011) · Journal of Neural Engineering · doi:10.1088/1741-2560/8/2/025012 · Cited by 47
Cantillo-Negrete, J., Gutiérrez-Martínez, J., Carino-Escobar, R. I., Carrillo‐Mora, P., & Elías-Viñas, D. (2014) · BioMedical Engineering OnLine · doi:10.1186/1475-925x-13-158 · Cited by 38 · cited 1×
“, a BCI calibrated on EEG signals from female users only for a target female user) may improve performances [57].”
An Efficient P300-based Brain-Computer Interface with Minimal Calibration Time
Lotte, F., & Guan, C. (2009) · HAL · Cited by 31
Self-citationAdaptive Common Spatial Pattern for single-trial EEG classification in multisubject BCI
Song, X., Yoon, S.-C., & Perera, V. (2013) · International IEEE/EMBS Conference on Neural Engineering · doi:10.1109/ner.2013.6695959 · Cited by 28 · cited 1×
“Along the same line of ideas, [52] also adapted the CSP spatial filters in an unsupervised way.”
MethodSemi-supervised feature extraction for EEG classification
Tu, W., & Sun, S. (2012) · Pattern Analysis and Applications · doi:10.1007/s10044-012-0298-2 · Cited by 28 · cited 2×
“For BCI, this approach has been used with CSP features and an LDA or SVM (support vector machine) classifier [49][50][51].”
MethodImproved Semisupervised Adaptation for a Small Training Dataset in the Brain–Computer Interface
Meng, J., Sheng, X., Zhang, D., & Zhu, X. (2013) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2013.2285232 · Cited by 27
Arvaneh, M., Robertson, I. H., & Ward, T. E. (2014) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2014.6945117 · Cited by 26 · cited 1×
“In [43] and [44], data features optimized for the other users were transformed in order to match the feature distribution of the target user and thus increase the number of training data.”
MethodBayoudh, S., Mouchère, H., Miclet, L., & Anquetil, É. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-74958-5_49 · Cited by 22
Review of Brain-Computer Interfaces based on the P300 evoked potential
Elshout, J. A. (2009) · Utrecht University Repository (Utrecht University) · Cited by 21
Knowledge Transfer for Reducing Calibration Time in Brain-Computer Interfacing
Dalhoumi, S., Dray, G., & Montmain, J. (2014) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai.2014.100 · Cited by 18 · cited 1×
“In [45], classifiers were optimized on different users and combined in a weighted scheme whose weights depend on how well the classifier can perform on the data available for the target user.”
BackgroundReview of the Use of Electroencephalography as an Evaluation Method for Human-Computer Interaction
Frey, J., Mühl, C., Lotte, F., & Hachet, M. (2013) · elib (German Aerospace Center) · doi:10.48550/arxiv.1311.2222 · Cited by 18 · cited 1×
“…for a number of applications for which ERP-based BCI cannot be used, including (but not limited to) self-paced BCI control [23], [24], stroke rehabilitation [25], [26] or passive BCI that monitor and adapt an application based on users’ mental states such as attention or workload [7], [27], [28].”
MethodSelf-citationCalibration Time Reduction through Source Imaging in Brain Computer Interface (BCI)
Ahn, M., Cho, H., & Jun, S. C. (2011) · Communications in computer and information science · doi:10.1007/978-3-642-22095-1_55 · Cited by 17 · cited 1×
“For instance, inverse solutions or beamforming have been used to specify prior regions of interest from which relevant features are likely to be found, hence making BCI calibration possible with fewer training trials [53], [54].”
MethodMinimizing Calibration Time for Brain Reading
Metzen, J. H., Kim, S. K., & Kirchner, E. A. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23123-0_37 · Cited by 16 · cited 1×
“[20] J.”
Pattern rejection strategies for the design of self-paced EEG-based Brain-Computer Interfaces
Lotte, F., Mouchère, H., & Lécuyer, A. (2008) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2008.4761454 · Cited by 15 · cited 1×
“Moreover, oscillatory activity-based BCI can be useful for a number of applications for which ERP-based BCI cannot be used, including (but not limited to) self-paced BCI control [23][24], stroke rehabilitation [25][26] or passive BCI that monitor and adapt an application based on users’ mental states such as attention…”
MethodSelf-citationSynthetic On-line Handwriting Generation by Distortions and Analogy
Mouchère, H., Bayoudh, S., Anquetil, É., & Miclet, L. (2007) · HAL · Cited by 13
Jeunet, C., Lotte, F., & Mühl, C. (2014) · International Conference on Physiological Computing Systems (PhyCS) · doi:10.5220/0004724100980106 · Cited by 12 · cited 2×
“This data set is described in more detail in [27] and [71].”
MethodSelf-citationHeger, D., Putze, F., Herff, C., & Schultz, T. (2013) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2013.6610823 · Cited by 8
Jeunet, C., Lotte, F., Hachet, M., & N’Kaoua, B. (2014) · International Journal of Psychophysiology · doi:10.1016/j.ijpsycho.2014.08.789 · Cited by 4 · cited 1×
“3) Data Set 3, Mental Imagery Data: This last data set is another in-house data set which comprises EEG data from N 3 ¼ 20 users who performed mental imagery tasks [72].”
MethodSelf-citationRole of Synthetically Generated Samples on Speech Recognition in a Resource-Scarce Language
Chakraborty, R., & Garain, U. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.400 · Cited by 3
Jeunet, C., Mühl, C., & Lotte, F. (2014) · HAL (Le Centre pour la Communication Scientifique Directe) · Cited by 2
Self-citation
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
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.