xDAWN Algorithm to Enhance Evoked Potentials: Application to Brain–Computer Interface
Open accessThe DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Abstract
A brain-computer interface (BCI) is a communication system that allows to control a computer or any other device thanks to the brain activity. The BCI described in this paper is based on the P300 speller BCI paradigm introduced by Farwell and Donchin . An unsupervised algorithm is proposed to enhance P300 evoked potentials by estimating spatial filters; the raw EEG signals are then projected into the estimated signal subspace. Data recorded on three subjects were used to evaluate the proposed method. The results, which are presented using a Bayesian linear discriminant analysis classifier , show that the proposed method is efficient and accurate.
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
“They can enhance the P300 component and reduce the data dimensions, which is very suitable to our needs.”
From Transfer Learning Algorithm of P300-EEG Signal Based on XDAWN Spatial Filter and Riemannian Geometry Classifier (2020) · cites this paper as [23]
In the citing paper
“They can enhance the P300 component and reduce the data dimensions, which is very suitable to our needs.”
From Transfer Learning Algorithm of P300-EEG Signal Based on XDAWN Spatial Filter and Riemannian Geometry Classifier (2020) · cites this paper as [23]
In the citing paper
“as the xDAWN estimates the spatial filters by maximizing the difference between the averaged signals of the corresponding category and the whole EEG data[28].”
From A Cascade xDAWN EEGNet Structure for Unified Visual-Evoked Related Potential Detection (2024) · cites this paper as [28]
In the citing paper
“Unmixing of these global patterns using a number of spatial filters is therefore typically applied to the whole set of relevant electrodes as a basic step in many successful examples of EEG decoding [Ang et al., 2008; Blankertz et al., 2008; Rivet et al., 2009].”
From Deep learning with convolutional neural networks for EEG decoding and visualization (2017) · cites this paper as Rivet et al., 2009
In the citing paper
“For all ERP-based data analyses (P300, ERN, MRCP) the traditional approach is the approach which won the Kaggle BCI Competition (code and documentation at http://github.com/alexandrebarachant/bci-challenge-ner-2015), which uses a combination of xDAWN Spatial Filtering [83], Riemannian Geometry [84,85], channel subset selection and L 1 feature regularization”
From EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces (2018) · cites this paper as [84]
Citations
Cites
Brain–computer interfaces for communication and control
Wolpaw, J. R., Birbaumer, N., McFarland, D. J., Pfurtscheller, G., & Vaughan, T. M. (2002) · Clinical Neurophysiology · doi:10.1016/s1388-2457(02)00057-3 · Cited by 7,927 · cited 2×
“See [ 3 ] for a more detailed review of BCIs.”
BackgroundMethodIndependent Component Analysis
(2004) · Independent Component Analysis · doi:10.7551/mitpress/3717.003.0014 · Cited by 7,903
RELATIONS BETWEEN TWO SETS OF VARIATES
HOTELLING, H. (1936) · Biometrika · doi:10.1093/biomet/28.3-4.321 · Cited by 5,263
Independent Component Analysis
Hyvärinen, A., Karhunen, J., & Oja, E. (2001) · Wiley eBooks · doi:10.1002/0471221317 · Cited by 5,007
MacKay, D. J. C. (1992) · Neural Computation · doi:10.1162/neco.1992.4.3.415 · Cited by 4,388 · cited 1×
“Among the proposed classifiers for BCIs, Bayesian linear discriminant analysis (BLDA) [2], [26] is chosen since it was proved to be efficient and was fully automatic (i.e., no hyper-parameters to adjust) [2].”
MethodAn introduction to kernel-based learning algorithms
Muller, K.-R., Mika, S., Ratsch, G., Tsuda, K., & Scholkopf, B. (2001) · IEEE Transactions on Neural Networks · doi:10.1109/72.914517 · Cited by 3,473
Neuronal ensemble control of prosthetic devices by a human with tetraplegia
Hochberg, L. R., Serruya, M. D., Friehs, G. M., Mukand, J. A., Saleh, M., Caplan, A. H., Branner, A., Chen, D., Penn, R. D., & Donoghue, J. P. (2006) · Nature · doi:10.1038/nature04970 · Cited by 3,295
Farwell, L. A., & Donchin, E. (1988) · Electroencephalography and Clinical Neurophysiology · doi:10.1016/0013-4694(88)90149-6 · Cited by 3,228 · cited 2×
“However, these repetitions decrease the number of symbols spelled per minute, e.g., with 15 repetitions, only two characters are typically spelled per minute [1], [8].”
BackgroundMethodBCI2000: A General-Purpose Brain-Computer Interface (BCI) System
Schalk, G., McFarland, D. J., Hinterberger, T., Birbaumer, N., & Wolpaw, J. R. (2004) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2004.827072 · Cited by 3,024 · cited 1×
“The EEG was collected and stored using the BCI2000 system with the P300 speller scenario [24].”
MethodBlind beamforming for non-gaussian signals
Cardoso, J. F., & Souloumiac, A. (1993) · IEE Proceedings F Radar and Signal Processing · doi:10.1049/ip-f-2.1993.0054 · Cited by 2,738
Self-citation
Research works printed but not linked: 2
- rivet, 2007, extraction de potentiels voqus p300 pour les interfaces cerveau-machine, Proc GRETSI, 625
- golub, 1996, Matrix Computation
Cited by
Items 101–200 of 573
Borra, D., Fantozzi, S., & Magosso, E. (2021) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2021.655840 · Cited by 36
“In particular, this solution included a combination of xDAWN spatial filtering (Rivet et al., 2009; Barachant and Congedo, 2014), Riemannian Geometry (Barachant et al., 2012 was adopted also with SOA algorithms to perform post-hoc hyper-parameter evaluation. ii.”
MethodSarafraz, G., Behnamnia, A., Hosseinzadeh, M., Balapour, A., Meghrazi, A., & Rabiee, H. R. (2024) · ACM Computing Surveys · doi:10.1145/3654664 · Cited by 48
Liang, Z., Zheng, Z., Chen, W., Pei, Z., Wang, J., & Chen, J. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106311 · Cited by 37
Omedes, J., Schwarz, A., Müller-Putz, G., & Montesano, L. (2018) · Journal of Neural Engineering · doi:10.1088/1741-2552/aac1a1 · Cited by 38
“To reduce the number of features maximizing the amount of information, examples for error and correct feedback trials were used to compute a set of spatial filters using the xDAWN method [50].”
MethodStandardization of protocol design for user training in EEG-based brain–computer interface
Mladenović, J. (2020) · Journal of Neural Engineering · doi:10.1088/1741-2552/abcc7d · Cited by 44
“…‘oddball’ paradigm, presenting the flashes spatially and temporally as further as possible [72], using famous/familiar faces [69] and smileys [68], 3D instead of 2D grid of letters [64], objects congruent to selection task [62], etc; and X-dawn spatial filter [136] as part of pipeline factors .”
Multivariate temporal dictionary learning for EEG
Barthélemy, Q., Gouy‐Pailler, C., Isaac, Y., Souloumiac, A., Larue, A., & Mars, J. I. (2013) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2013.02.001 · Cited by 46
Self-citationGenerative modeling and augmentation of EEG signals using improved diffusion probabilistic models
Torma, S., & Szegletes, L. (2024) · Journal of Neural Engineering · doi:10.1088/1741-2552/ada0e4 · Cited by 44
“Similarly, evoked potential decoding models can benefit from using xDAWN feature covariates (XCov) [45, 46].”
A comparison of ERP spatial filtering methods for optimal mental workload estimation
Roy, R. N., Bonnet, S., Charbonnier, S., Jallon, P., & Campagne, A. (2015) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2015.7320066 · Cited by 35
“Another interesting method is the xDAWN algorithm designed by Rivet and collaborators to enhance the signal on signal plus noise ratio for the P300 speller BCI application [6].”
MethodKim, S. K., & Kirchner, E. A. (2013) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2013.573 · Cited by 39
“The xDAWN [18] was used as a spatial filter to enhance signal-to-noise ratio.”
MethodKorczowski, L., Congedo, M., & Jutten, C. (2015) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2015.7318721 · Cited by 35
Single-trial EEG RSVP classification using convolutional neural networks
Shamwell, J., Lee, H., Kwon, H., Marathe, A. R., Lawhern, V., & Nothwang, W. (2016) · SPIE Proceedings · doi:10.1117/12.2224172 · Cited by 34
The challenge of controlling an auditory BCI in the case of severe motor disability
Séguin, P., Maby, E., Fouillen, M., Otman, A., Luauté, J., Giraux, P., Morlet, D., & Mattout, J. (2024) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-023-01289-3 · Cited by 36
“Spatial filtering, computed by the xDAWN algorithm [22], was then used to reduce dimensions and maximize the distinction between the “ATTENDED” and “IGNORED” responses. xDAWN yields as many spatial filters (or virtual sensors) as the number of EEG sensors.”
MethodRecording human cortical population spikes non-invasively – An EEG tutorial
Waterstraat, G., Fedele, T., Burghoff, M., Scheer, H.-J., & Curio, G. (2014) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2014.08.013 · Cited by 38
Kirchner, E. A., Kim, S. K., Tabie, M., Wöhrle, H., Maurus, M., & Kirchner, F. (2016) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2016.00291 · Cited by 39
“The segments were further processed with the xDAWN spatial filter (Rivet et al., 2009).”
MethodEEG-FM-Compass: progress, benchmarking and future directions for EEG foundation models
Liu, D., Chen, Y., Chen, Z., Cui, Z., Wen, Y., An, J., Luo, J., & Wu, D. (2026) · National Science Review · doi:10.1093/nsr/nwag466 · Cited by 35
Lu, J., Xie, K., & McFarland, D. J. (2014) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2014.2315717 · Cited by 35
“jection [18], or supervised, such as discriminative spatial pattern (DSP) filtering [19] and its variant local DSP filtering [20].”
BackgroundVourvopoulos, A., & Badia, S. B. I. (2016) · Augmented Human International Conference · doi:10.1145/2875194.2875244 · Cited by 38
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
“In the past 15 years, many learning machines have been introduced for P300 speller recognition, including stepwise linear discriminant analysis (SWLDA) [5], Bayesian LDA (BLDA) [6], support vector machine (SVM) [7], convolutional neural network (CNN) [8], XDAWN [9], etc.”
MethodLearning Discriminative Spatiospectral Features of ERPs for Accurate Brain–Computer Interfaces
Abibullaev, B., & Zollanvari, A. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2018.2883458 · Cited by 32
“This includes spatial whitening [30], common spatial-temporal patterns [40], [41], nonlinear”
BackgroundXiao, X., Xu, M., Han, J. H., Yin, E., Liu, S., Zhang, X., Jung, T., & Ming, D. (2021) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac028b · Cited by 32
“Rivet et al proposed xDAWN to enhance the P300 features for P300-speller by projecting raw EEG on the estimated P300 subspace, and the average spelling accuracy was nearly 30% for only one repetition when using BLDA as a classifier [28].”
InfluentialImpact of Spatial Filters During Sensor Selection in a Visual P300 Brain-Computer Interface
Rivet, B., Cecotti, H., Maby, E., & Mattout, J. (2011) · Brain Topography · doi:10.1007/s10548-011-0193-y · Cited by 34
Self-citationWittevrongel, B., & Hulle, M. M. V. (2017) · Frontiers in Neuroscience · doi:10.3389/fnins.2017.00630 · Cited by 35
“…LDA (Farwell and Donchin, 1988; Krusienski et al., 2006; Manyakov et al., 2011b), have been applied to pre-processed epochs or after feature extraction by Common Spatio-Temporal Pattern (Krusienski et al., 2007), xDAWN (Rivet et al., 2009) and linear predictive coding (Momennezhad et al., 2014).”
MethodNambu, I., Ebisawa, M., Kogure, M., Yano, S., Hokari, H., & Wada, Y. (2013) · PLoS ONE · doi:10.1371/journal.pone.0057174 · Cited by 34
“Some studies showed that feature selection or spatial filtering improved classification accuracy [33,34,35,36,37].”
BackgroundAn improved EEGNet for single-trial EEG classification in rapid serial visual presentation task
Zhang, H., Wang, Z., Yu, Y., Yin, H., Chen, C., & Wang, H. (2022) · Brain Science Advances · doi:10.26599/bsa.2022.9050007 · Cited by 30
“Therefore, not only is the SNR very low, but it is not easy to complete the classification task [25].”
BackgroundMayaud, L., Cabanilles, S., van Langhenhove, A., Congedo, M., Barachant, A., Pouplin, S., Filipe, S., Pétégnief, L., Rochecouste, O., Azabou, É., et al. (2016) · Brain-Computer Interfaces · doi:10.1080/2326263x.2016.1254403 · Cited by 33
Theoretical Analysis Of Xdawn Algorithm: Application To An Efficient Sensor Selection In A P300 Bci
Cecotti, H., Maby, E., Mattout, J., Rivet, B., & Souloumiac, A. (2011) · HAL · doi:10.5281/zenodo.42402 · Cited by 41
Self-citationTime–frequency transform based EEG data augmentation for brain–computer interfaces
Wang, Z., Li, S., Chen, X., & Wu, D. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113074 · Cited by 29
MNE: Software for Acquiring, Processing, and Visualizing MEG/EEG Data
Esch, L., Dinh, C., Larson, E., Engemann, D. A., Jas, M., Khan, S., Gramfort, A., & Hämäläinen, M. (2019) · Springer eBooks · doi:10.1007/978-3-030-00087-5_59 · Cited by 34
“It implements input / output (IO) routines for reading a variety of MEG / EEG file formats ( http://martinos.org/mne/ advanced preprocessing tools such as the Signal Space Separation (SSS) algorithm, and XDAWN (Taulu and Kajola, 2005; Rivet et al., 2009), a dedicated decoding module for MEG / EEG (King et al., 2018), B…”
MethodLi, Z., Sun, S., Zhao, H., Pei, W., Chen, H., Gao, X., Zhang, L., & Wang, Y. (2020) · Frontiers in Neuroscience · doi:10.3389/fnins.2020.579469 · Cited by 29
“Major feature extraction algorithms include xDAWN (Rivet et al., 2009), signal-to-noise ratio (SNR) maximizer for ERP (SIM; Wu and Gao, 2011), common spatial pattern (CSP; Ramoser et al., 2000), independent component analysis (ICA; Makeig et al., 1996), and etc. Typical classification algorithms…”
MethodCross-modal guiding and reweighting network for multi-modal RSVP-based target detection
Mao, J., Qiu, S., Wei, W., & He, H. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.01.009 · Cited by 31
Ferracuti, F., Casadei, V., Marcantoni, I., Iarlori, S., Burattini, L., Monteriù, A., & Porcaro, C. (2020) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2020.105419 · Cited by 28
Optimization of Single-Trial Detection of Event-Related Potentials Through Artificial Trials
Cecotti, H., Marathe, A. R., & Ries, A. J. (2015) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2015.2417054 · Cited by 31
“ing the xDAWN spatial filtering approach [9], [20], [21].”
MethodSong, Y., Yang, L., Jia, X., & Xie, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.04456 · Cited by 32
“The other is to project the original signal into a subspace while obtaining spatial features for better classification, such as optimal spatial filter and xDAWN algorithm [24], [25].”
Li, H., Tang, J., Li, W., Dai, W., Liu, Y., & Zhou, Z. (2024) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2024.3357863 · Cited by 27
“The champion of the Kaggle BCI competition adopted the xDAWN-RG algorithm, which combined the Riemannian geometry [31], xDAWN spatial filtering [30], L1 feature regularization, and channel subset selection.”
MethodLiu, Y., Wang, S., & Hu, M.-R. (2016) · Applied Sciences · doi:10.3390/app6050142 · Cited by 28
“The proposed detector is a generic model and might be applied to other P300 BCIs to further improve their systems’ P300 detection accuracies.”
MethodInfluentialLotte, F., & Congedo, M. (2016) · Wiley eBooks · doi:10.1002/9781119144977.ch7 · Cited by 32
Dehais, F., Castillos, K. C., Ladouce, S., & Clisson, P. (2024) · Journal of Neural Engineering · doi:10.1088/1741-2552/ad8ef7 · Cited by 27
“We then reduced the dimensionality of the EEG data using the xDAWN method [47] with four spatial filters.”
Kristensen, E., Rivet, B., & Guérin-Dugué, A. (2017) · Journal of Eye Movement Research · doi:10.16910/jemr.10.1.7 · Cited by 26
Self-citationDas, N., Vanthornhout, J., Francart, T., & Bertrand, A. (2019) · NeuroImage · doi:10.1016/j.neuroimage.2019.116211 · Cited by 32
A five-state P300-based foot lifter orthosis: Proof of concept
Duvinage, M., Castermans, T., Jiménez-Fabián, R., Hoellinger, T., Saedeleer, C. D., Petieau, M., Seetharaman, K., Cheron, G. A., Verlinden, O., & Dutoit, T. (2012) · ISSNIP Biosignals and Biorobotics Conference: Biosignals and Robotics for Better and Safer Living · doi:10.1109/brc.2012.6222193 · Cited by 26
“Afterwards, a spatial filter is designed thanks to an xDawn algorithm [19].”
MethodUAV Target Detection for IoT via Enhancing ERP Component by Brain–Computer Interface System
Zhang, Y., Zhang, H., Gao, X., Zhang, S., & Yang, C. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3273163 · Cited by 25
Jadav, G. M., Lerga, J., & Štajduhar, I. (2020) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/s13634-020-00667-6 · Cited by 25
Wei, W., Qiu, S., Zhang, Y., Mao, J., & He, H. (2022) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac5eb7 · Cited by 24
“…decoding methods, such as minimum distance to Riemannian mean classifier (MDRM) [18], one convolution layer neural network (OCLNN) [19], and xDAWN [20], and RSVP decoding methods, such as hierarchical discriminant component analysis (HDCA) [21], Manor convolutional neural network (Manor-CNN)…”
General principles of machine learning for brain-computer interfacing
Iturrate, I., Chavarriaga, R., & Millán, J. D. R. (2020) · Handbook of clinical neurology · doi:10.1016/b978-0-444-63934-9.00023-8 · Cited by 26
Single-trial classification of evoked responses to auditory tones using OPM- and SQUID-MEG
Iivanainen, J., Carter, T. R., Trumbo, M., McKay, J., Taulu, S., Wang, J., Stephen, J. M., Schwindt, P. D. D., & Borna, A. (2023) · Journal of Neural Engineering · doi:10.1088/1741-2552/acfcd9 · Cited by 24
“We used both EEGNet (Lawhern et al 2018) and a combination of xDAWN spatial filtering (Rivet et al 2009), Riemannian geometry (Barachant et al 2011), and logistic regression to perform multiclass classification of the responses to the three tones.”
EEG sensor selection by sparse spatial filtering in P300 speller brain-computer interface
Rivet, B., Cecotti, H., Phlypo, R., Bertrand, O., Maby, E., & Mattout, J. (2010) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.2010.5626485 · Cited by 24
“In this section, the principle of the xDAWN algorithm is briefly reprised [7], [8].”
BackgroundSelf-citationCombining multiple features for error detection and its application in brain–computer interface
Tong, J., Lin, Q., Xiao, R., & Ding, L. (2016) · BioMedical Engineering OnLine · doi:10.1186/s12938-016-0134-9 · Cited by 24
“When extracting features in the spatial domain, it is found that other spatial filter method such as xDAWN [47] could also be used to improve performance.”
MethodHajinoroozi, M., Mao, Z., Lin, Y., & Huang, Y. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-58628-1_4 · Cited by 24
Global research on artificial intelligence-enhanced human electroencephalogram analysis
Chen, X., Tao, X., Wang, F. L., & Xie, H. (2021) · Neural Computing and Applications · doi:10.1007/s00521-020-05588-x · Cited by 28
Recreational Applications of OpenViBE: Brain Invaders and Use‐the‐Force
Andreev, A., Barachant, A., Lotte, F., & Congedo, M. (2016) · Wiley eBooks · doi:10.1002/9781119332428.ch14 · Cited by 23
Li, S., Jin, J., Daly, I. P., Liu, C., & Cichocki, A. S. (2021) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac42b4 · Cited by 25
“…2nd, 3rd, 575th, 576th, 577th, 1150th, 1151st, and 1152nd) is plotted (figure 5 The character recognition performance using the proposed feature selection method with an LDA classifier is compared with traditional classification methods, such as xDAWN [38], STDA [39], FC + LDA [40], and SWLDA [41].”
Challenges of neural interfaces for stroke motor rehabilitation
Vidaurre, C., Irastorza-Landa, N., Sarasola-Sanz, A., Insausti-Delgado, A., Ray, A. M., Bibián, C., Helmhold, F., Mahmoud, W. J., Ortego-Isasa, I., López‐Larraz, E., et al. (2023) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2023.1070404 · Cited by 32
“Data-driven means that spatial filters are learnt from data depending on their objective function (Rivet et al., 2009; Pascual et al., 2011; Haufe et al., 2014a; Nakanishi et al., 2017; Jorajuría et al., 2022) increasing thereby the discrimination and signal to noise ratio of the features (Ang et al.”
MethodImproving the performance of P300-based brain–computer interface through subspace-based filtering
Shahriari, Y., & Erfanian, A. (2013) · Neurocomputing · doi:10.1016/j.neucom.2013.05.001 · Cited by 25
“The P300 is a type of brain activity that has been used for BCI [4–22].”
BackgroundMethodAdaptive training session for a P300 speller brain–computer interface
Rivet, B., Cecotti, H., Perrin, M., Maby, E., & Mattout, J. (2011) · Journal of Physiology-Paris · doi:10.1016/j.jphysparis.2011.07.013 · Cited by 23
“A usual step to enhance a particular brain pattern is to use spatial filters: e.g., independent component analysis (Comon and Jutten, 2010; Xu et al., 2004), common spatial pattern (Koles, 1991; Blankertz et al., 2008) or more recently xDAWN algorithm (Rivet et al., 2008, 2009).”
MethodSelf-citationTransfer Learning for SSVEP-based BCI Using Riemannian Similarities Between Users
Kalunga, E. K., Chevallier, S., & Barthélemy, Q. (2018) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco.2018.8553441 · Cited by 27
“The XDAWN spatial filter [8] focuses on maximizing the signal-to-signal plus noise ratio by finding components best correlated with the ERP timings.”
MethodYang, C., Zhang, H., Zhang, S., Han, X., Gao, S., & Gao, X. (2019) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2019.2961743 · Cited by 23
“We compared the performance difference between the standard xDAWN-BLDA method and the STE-xDAWN-BLDA algorithm with spatio-temporal equalization as preprocessing.”
MethodInfluentialComparison of Sensor Selection Mechanisms for an ERP-Based Brain-Computer Interface
Feess, D., Krell, M. M., & Metzen, J. H. (2013) · PLoS ONE · doi:10.1371/journal.pone.0067543 · Cited by 23
“Especially CSP and xDAWN have proven to be useful in different BCI scenarios [10,12].”
BackgroundMethodChoo, S., Park, H., Jung, J., Flores, K., & Nam, C. S. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106665 · Cited by 24
Enhanced visibility graph for EEG classification
Belhadi, A., Lind, P. G., Djenouri, Y., & Yazidi, A. (2025) · Frontiers in Neuroscience · doi:10.3389/fnins.2025.1541062 · Cited by 22
“2009) presented, xDAWN algorithm, an unsupervised algorithm for enhancing P300 evoked potentials through optimized spatial filter estimation.”
Higashi, H., Rutkowski, T. M., Tanaka, T., & Tanaka, Y. (2016) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2016.2599297 · Cited by 23
“The SMLDA method was compared with LDA, including a dimensionality reduction by PCA; common spatial pattern (CSP) spatial filter [9]; xDAWN spatial filter [39], LDA with the shrunk covariance matrix, and UMLDA.”
MethodOptimal Transport Applied To Transfer Learning For P300 Detection
Gayraud, N. T. H., Rakotomamonjy, A., & Clerc, M. (2017) · Verlag der Technischen Universität Graz · doi:10.3217/978-3-85125-533-1-28
“From { M i } N e i =1 = M e and the corresponding labels Y e , we learn spatial filters us-ing the X-DAWN algorithm [16], and project each M i onto the first N f X-DAWN filters, yielding feature vectors x i ∈ R N f × T .”
Errors in Human-Robot Interactions and Their Effects on Robot Learning
Kim, S. K., Kirchner, E. A., Schloßmüller, L., & Kirchner, F. (2020) · Frontiers in Robotics and AI · doi:10.3389/frobt.2020.558531 · Cited by 28
“We used the xDAWN spatial filter (Rivet et al., 2009) for feature extraction and 8 pseudo channels were obtained after spatial filtering.”
MethodSpatial filtering based on Riemannian distance to improve the generalization of ErrP classification
Cruz, A., Pires, G., & Nunes, U. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.10.078 · Cited by 22
Pires, G., Cruz, A., Jesús, D., Yasemin, M., Nunes, U., Sousa, T., & Castelo-Branco, M. S. (2022) · Journal of Neural Engineering · doi:10.1088/1741-2552/aca798 · Cited by 22
“For example, in [33], using 64 channels the authors attained a 91% accuracy detecting oErrPs in a human-robot interaction task, using the xDAWN spatial filter [56] combined with a data augmentation approach to which the authors attributed the very good classification accuracy.”
MethodEEG-based emergency braking intention detection during simulated driving
Liang, X., Yu, Y., Liu, Y., Liu, K., Liu, Y., & Zhou, Z. (2023) · BioMedical Engineering OnLine · doi:10.1186/s12938-023-01129-4 · Cited by 24
“As traditional classification algorithms, CSP + LDA is widely used in spontaneous activity-based BCIs, while xDAWN + LDA has a wide range of applications in event related potential (ERP)based BCIs, where CSP and xDAWN act as adaptive filters that serve to improve the signal-to-noise ratio and reduce its feature dimens…”
MethodInfluentialLuo, J., Cui, W., Xu, S., Wang, L., Chen, H., & Li, Y. (2024) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2024.3359191 · Cited by 22
“For the framework structure, a spatial filtering algorithm xDAWN [20] is first used to filter raw EEG signals to enhance the P300 evoked potentials and the CWT is adopted to convert the EEG data into multi-channel spectrogram images.”
MethodA subjective assessment of a P300 BCI system for lower-limb rehabilitation purposes
Duvinage, M., Castermans, T., Petieau, M., Seetharaman, K., Hoellinger, T., Cheron, G. A., & Dutoit, T. (2012) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2012.6346806 · Cited by 22
“Following [10], providing the EEG signals downsampled at 32 Hz, the pipeline was composed of several main components: a temporal high-pass filter, an xDAWN-based spatial filter [13], an epoch averaging and a Linear Discriminant Analysis (LDA) classifier using a voting rule for the final decision sent to a Virtual Real…”
MethodSingle-paradigm and hybrid brain computing interfaces and their use by disabled patients
de Neeling, M. G. J., & Hulle, M. M. V. (2019) · Journal of Neural Engineering · doi:10.1088/1741-2552/ab2706 · Cited by 23
Enhancing LSTM Models with Self-attention and Stateful Training
Katrompas, A., & Metsis, V. (2021) · Lecture notes in networks and systems · doi:10.1007/978-3-030-82193-7_14 · Cited by 29
“For example, the data cannot be EEG data in ordered experimental events such as hearing a noise on the left/right, or a vision event on the left/right [20].”
BackgroundIdentification of spatial and temporal features of EEG
Jrad, N., & Congedo, M. (2012) · Neurocomputing · doi:10.1016/j.neucom.2012.02.032 · Cited by 22
“Signal-processing criteria like the Signal-to-Noise Ratio and ratio of class variances [3, 6, 7] have been often employed for Evoked Response Potential (ERP).”
BackgroundMethodActive inference as a unifying, generic and adaptive framework for a P300-based BCI
Mladenović, J., Frey, J., Joffily, M., Maby, E., Lotte, F., & Mattout, J. (2019) · Journal of Neural Engineering · doi:10.1088/1741-2552/ab5d5c · Cited by 22
A Cascade xDAWN EEGNet Structure for Unified Visual-Evoked Related Potential Detection
Wang, H., Wang, Z., Sun, Y., Yuan, Z., Xu, T., & Li, J. (2024) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2024.3415474 · Cited by 20
“…of the domain information, it might be more suitable to process the ERP signals by xDAWN spatial filtering before sent to neural networks, as the xDAWN estimates the spatial filters by maximizing the difference between the averaged signals of the corresponding category and the whole EEG data [28].”
MethodKueper, N., Kim, S. K., & Kirchner, E. A. (2024) · Scientific Reports · doi:10.1038/s41598-024-65910-8 · Cited by 21
Robust Brain-computer Interface for virtual Keyboard (RoBIK): Project results
Mayaud, L., Filipe, S., Pétégnief, L., Rochecouste, O., & Congedo, M. (2013) · IRBM · doi:10.1016/j.irbm.2013.01.013 · Cited by 24
“Signals were filtered and transformed with the xDAWN spatial filter [55] prior to SVM voting classifier [56] .”
MethodSpatial filters yield stable features for error-related potentials across conditions
Iwane, F., Chavarriaga, R., Iturrate, I., & Millán, J. D. R. (2016) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2016.7844316 · Cited by 23
“In the remaining two cases, we compared two preprocessing methods previously used in the literature: xDAWN [15] and Canonical Correlation Analysis, CCA [16].”
MethodTanaka, H., & Miyakoshi, M. (2019) · NeuroImage · doi:10.1016/j.neuroimage.2019.04.049 · Cited by 20
“xDAWN decomposes measured EEG time series into a component that occurs every trial and was demonstrated to enhance P300 wave forms (Rivet et al., 2009).”
MethodAdversarial filtering based evasion and backdoor attacks to EEG-based brain-computer interfaces
Meng, L., Jiang, X., Chen, X., Liu, W., Luo, H., & Wu, D. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102316 · Cited by 29
Lee, C.-H., Ahn, D., Kim, H., Ha, E. J., Kim, J. B., & Kim, D. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125364 · Cited by 21
Cecotti, H. (2015) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2015.2478695 · Cited by 19
“The next step consisted of enhancing the relevant signal using the xDAWN spatial filtering approach [36], which was also used for sensor selection in BMI [37]–[39].”
MethodHuman-autonomy sensor fusion for rapid object detection
Robinson, R. M., Lee, H., McCourt, M. J., Marathe, A. R., Kwon, H., Ton, C. T., & Nothwang, W. D. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353390 · Cited by 19
“• XDAWN+Bayesian Linear Discriminant Analysis (XD+BLDA): XDAWN spatial filtering identifies a linear combination of the raw neural signals that maximizes the signal-to-signal+noise ratio (SSNR) with regard to typical target and non-target responses, then uses the weighted signal in a Bayesian linear discriminant class…”
BackgroundMethodChau, J. M., Achanccaray, D., Villota, E., & Chevallier, S. (2020) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2020.3043418 · Cited by 19
“2) xDAWN Filtering With Riemannian Classifiers: Another spatial filtering option for P300 components is the xDAWN algorithm, which calculates a space in which most of the evoked potentials are contained by performing a least squares optimization, leading to easier class differentiation [44].”
MethodFrom Euclidean to Riemannian Means: Information Geometry for SSVEP Classification
Kalunga, E. K., Chevallier, S., Barthélemy, Q., Djouani, K., Hamam, Y., & Monacelli, É. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-25040-3_64 · Cited by 19
“Consequently, spatial filtering methods are used, such as xDAWN [17], Independent Component Analysis (ICA) [20], Common Spatial Pattern (CSP) [10] and Canonical Correlation Analysis (CCA) [12].”
Su, K., Hairston, W. D., & Robbins, K. A. (2017) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2017.10.011 · Cited by 21
DelPreto, J., Salazar-Gómez, A. F., Gil, S., Hasani, R., Guenther, F. H., & Rus, D. L. (2018) · Robotics: Science and Systems · doi:10.15607/rss.2018.xiv.063 · Cited by 18
Cecotti, H., Sato-Reinhold, J., Sy, J. L., Elliott, J. C., Eckstein, M. P., & Giesbrecht, B. (2011) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.2011.6091575 · Cited by 18
Martens, S., & Leiva, J. M. (2010) · Journal of Neural Engineering · doi:10.1088/1741-2560/7/2/026003 · Cited by 21
“Lately, good results have been achieved with discriminative approaches which treat the decoding as a perbit classification problem [5] [6] [7] [8] [9].”
BackgroundClassification of error-related potentials evoked during stroke rehabilitation training
Kumar, A., Pirogova, E., Mahmoud, S. S., & Fang, Q. (2021) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac1d32 · Cited by 17
“The true TE signal A can be estimated through least square estimation using the pseudoinverse [32]”
BackgroundMethodInfluentialAn open-source human-in-the-loop BCI research framework: method and design
Nilsson, M. G., Tufvesson, P., Heskebeck, F., & Johansson, M. (2023) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2023.1129362 · Cited by 20
“This aspect is reflected not only in the use of machine learning for the classification of data, but also by using data-dependent methods for individualized feature extraction such as common spatial patterns (CSP; Koles, 1991), and xDAWN (Rivet et al., 2009).”
MethodSadras, N., Sani, O. G., Ahmadipour, P., & Shanechi, M. M. (2023) · Journal of Neural Engineering · doi:10.1088/1741-2552/acec14 · Cited by 20
“This approach involves dimensionality reduction via xDAWN spatial filtering [76], a nonlinear transformation based on RG [71, 72], and classification via logistic regression.”
MethodOnline movement prediction in a robotic application scenario
Seeland, A., Wöhrle, H., Straube, S., & Kirchner, E. A. (2013) · International IEEE/EMBS Conference on Neural Engineering · doi:10.1109/ner.2013.6695866 · Cited by 17
“The number of channels of the remaining data was reduced to four retained channels by applying the xDAWN spatial filter [15].”
MethodConfidence metrics improve human-autonomy integration
Marathe, A. R., Lance, B. J., McDowell, K., Nothwang, W. D., & Metcalfe, J. S. (2014) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/2559636.2563721 · Cited by 17
“Three different state-of-theart neural classification algorithms were applied: hierarchical discriminant component analysis (HDCA; [2]), XDawn with a Bayesian linear discriminant classifier (XD+BLDA; [4]), and common spatial patterns (CSP; [5]).”
MethodMultirapid Serial Visual Presentation Framework for EEG-Based Target Detection
Lin, Z., Zeng, Y., Gao, H., Tong, L., Zhang, C., Wang, X., Wu, Q., & Yan, B. (2017) · BioMed Research International · doi:10.1155/2017/2049094 · Cited by 17
“[10, 11] proposed the xDawn algorithmdesigned tomaximize the difference in the signal-to-noise ratio between target and nontarget classes.”
BackgroundBahners, B. H., Waterstraat, G., Kannenberg, S., Curio, G., Schnitzler, A., Nikulin, V. V., & Florin, E. (2022) · Experimental Neurology · doi:10.1016/j.expneurol.2022.114031 · Cited by 18
Multimodal target detection using single trial evoked EEG responses in single and dual-tasks
Cecotti, H., Kasper, R. W., Elliott, J. C., Eckstein, M. P., & Giesbrecht, B. (2011) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.2011.6091557 · Cited by 17
Cecotti, H., & Rivet, B. (2014) · Brain Sciences · doi:10.3390/brainsci4020335 · Cited by 18
“Spatial filters are obtained through the Rayleigh quotient by maximizing the SSNR [34].”
MethodSelf-citationThe privileged sensing framework: A principled approach to improved human-autonomy integration
Marathe, A. R., Metcalfe, J. S., Lance, B. J., Lukos, J. R., Jangraw, D. C., Lai, K.-T., Touryan, J., Stump, E., Sadler, B. M., Nothwang, W. D., et al. (2018) · Theoretical Issues in Ergonomics Science · doi:10.1080/1463922x.2017.1297865 · Cited by 16
“…fi ltering to identify a linear combination of the raw neural signals that maximises the signal to noise ratio between targets and non-targets (Rivet et al. 2009; Cecotti et al. 2011) and then classi fi es the fi ltered signals using BLDA; and (3) Common Spatial Patterns (CSP), another spatial…”
MethodSpinnato, J., Roubaud, M. C., Burle, B., & Torrésani, B. (2015) · Journal of Neural Engineering · doi:10.1088/1741-2560/12/3/036013 · Cited by 19
“Concerning the spatial dimension reduction, well-established spatial filtering methods have been developed for specific BCI tasks: for example common spatial pattern (CSP) is a especially suited spatial filters for motor imagery [50] whereas xDAWN has been developed for P300 data [48].”
MethodDeep Learning Methods in Electroencephalography
Kotowski, K., Stąpor, K., & Ochab, J. K. (2020) · Learning and analytics in intelligent systems · doi:10.1007/978-3-030-49724-8_8 · Cited by 16
Ni, Z., Xu, J., Wu, Y., Li, M., Xu, G., & Xu, B. (2022) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3150007 · Cited by 18
Asynchronous Video Target Detection Based on Single-Trial EEG Signals
Song, X., Yan, B., Tong, L., Shu, J., & Zeng, Y. (2020) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2020.3009978 · Cited by 17
“Therefore, multiple channel signals were reduced to various time series by spatial filtering based on xDAWN [27], [41].”
BackgroundMethod
Metadata
- Authors
- Rivet, B., Souloumiac, A., Attina, V., & Gibert, G.
- Affiliations
- Institut polytechnique de Grenoble (FR)
- Commissariat à l'Énergie Atomique et aux Énergies Alternatives (FR)
- Lyon 1 Université (FR)
- Venue
- IEEE Transactions on Biomedical Engineering
- Published
- 2009-08
- Volume
- 56
- Issue
- 8
- Pages
- 2035-2043
- ISSN
- 0018-9294 (ISSN-L)
- 1558-2531
- OpenAlex
- W2104063964
- Cited by
- 537
- References
- 29
- Citations by year
- 2026: 21 · 2025: 37 · 2024: 50 · 2023: 43 · 2022: 31 · 2021: 37 · 2020: 44 · 2019: 35 · 2018: 38 · 2017: 32 · 2016: 36 · 2015: 33 · 2014: 23 · 2013: 34 · 2012: 16
- FWCI
- 6.96
- Type
- journal article
- Language
- en
- Open access
- green
- hal.science
- Locations
- IEEE Transactions on Biomedical Engineering (publishedVersion)
- PubMed (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 › Signal Processing › Blind Source Separation Techniques
- Keywords
- P300 speller, brain-computer interface, EEG signal processing, event-related potentials
- MeSH terms
- Adult, Algorithms, Artificial Intelligence, Brain, Electroencephalography, Evoked Potentials, Humans, Male, Man-Machine Systems, Signal Processing, Computer-Assisted
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.