Optimizing Spatial filters for Robust EEG Single-Trial Analysis
The DOI matches its Crossref record; 59 of the 62 references it cites were found in a registry or an index.
Abstract
Due to the volume conduction multichannel electroencephalogram (EEG) recordings give a rather blurred image of brain activity. Therefore spatial filters are extremely useful in single-trial analysis in order to improve the signal-to-noise ratio. There are powerful methods from machine learning and signal processing that permit the optimization of spatio-temporal filters for each subject in a data dependent fashion beyond the fixed filters based on the sensor geometry, e.g., Laplacians. Here we elucidate the theoretical background of the common spatial pattern (CSP) algorithm, a popular method in brain-computer interface (BCD research. Apart from reviewing several variants of the basic algorithm, we reveal tricks of the trade for achieving a powerful CSP performance, briefly elaborate on theoretical aspects of CSP, and demonstrate the application of CSP-type preprocessing in our studies of the Berlin BCI (BBCI) project.
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
“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 Blankertz et al., 2008
Citations
Cites
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
Advances in Neural Information Processing Systems 19
(2007) · The MIT Press eBooks · doi:10.52202/085713 · Cited by 15,539
The Elements of Statistical Learning: Data Mining, Inference, and Prediction
John Lu, Z. Q. (2010) · Journal of the Royal Statistical Society Series A: Statistics in Society · doi:10.1111/j.1467-985x.2010.00646_6.x · Cited by 12,390
Introduction to Statistical Pattern Recognition
(1990) · Elsevier eBooks · doi:10.1016/c2009-0-27872-x · Cited by 11,031
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
The Fourier Transform and Its Applications
Bracewell, R., & Kahn, P. B. (1966) · American Journal of Physics · doi:10.1119/1.1973431 · Cited by 5,737
Über das Elektrenkephalogramm des Menschen
Berger, H. (1929) · Archiv für Psychiatrie und Nervenkrankheiten · doi:10.1007/bf01797193 · Cited by 4,235
Introduction to statistical pattern recognition (2nd ed.)
Fukunaga, K. (1990) · Academic Press Professional, Inc. eBooks · Cited by 3,797
An 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
The Fourier Transform and Its Applications
Bracewell (1999) · Cited by 2,102
Research works printed but not linked: 7
- hill, 2007, An evidence-based approach to optimizing feature extraction in EEG signal classification
- dornhege, 2006, Increasing information transfer rates for brain-computer interfacing
- 2007, Toward Brain-Computer Interfacing
- blankertz, 2007, Universal Access in HCI, 4555, 759
- blankertz, 2008, Advances in Neural Information Processing Systems 20
- tomioka, 2007, Advances in Neural Information Processing Systems 19, 1377
- schl�gl, 2007, Towards Brain-Computer Interfacing, 297
Cited by
Items 201–300 of 1,002
Deep Temporal-Spatial Feature Learning for Motor Imagery-Based Brain–Computer Interfaces
Chen, J., Yu, Z., Gu, Z., & Li, Y. (2020) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2020.3023417 · Cited by 96
“Existing representative methods, such as common spatial fil-ter (CSP) [12] and its extensions [4], [13], are used frequently as spatial filters to capture the ERD/ERS patterns of MI EEG.”
MethodMotor Imagery Impairment in Postacute Stroke Patients
Braun, N., Kranczioch, C., Liepert, J., Dettmers, C., Zich, C., Büsching, I., & Debener, S. (2017) · Neural Plasticity · doi:10.1155/2017/4653256 · Cited by 99
Frequency-Optimized Local Region Common Spatial Pattern Approach for Motor Imagery Classification
Park, Y., & Chung, W. (2019) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2019.2922713 · Cited by 98
“For each Rk , we consider a spatial filter ( [7]) p(k) ∈ R|Rk | to convert |Rk | EEG signals in Rk into a single signal p(k) T X (k) i ∈ R1×L .”
BackgroundMethodChu, Y., Zhao, X., Zou, Y., Xu, W., Song, G., Han, J., & Zhao, Y. (2020) · Journal of Neural Engineering · doi:10.1088/1741-2552/aba7cd · Cited by 97
“…(TS features with PCA for reduction and LDA for classification), the TS + LDA (TS features without any reduction followed by LDA for classification), the MDRM method, and two standard baseline methods adopted in traditional MI-based BMI classification (CSP + LDA and FBCSP + LDA) [19, 40, 41].”
MethodBayesian 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
Gaur, P., McCreadie, K. A., Pachori, R. B., Wang, H., & Prasad, G. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.102574 · Cited by 102
Sparse Bayesian Learning for End-to-End EEG Decoding
Wang, W., Qi, F., Wipf, D., Cai, C., Yu, T., Li, Y., Zhang, Y., Yu, Z., & Wu, W. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3299568 · Cited by 99
“The filters corresponding to the 3 largest eigenvalues for each class were chosen as recommended in [8].”
BackgroundMethodInfluentialEEG Data Space Adaptation to Reduce Intersession Nonstationarity in Brain-Computer Interface
Arvaneh, M., Guan, C., Ang, K. K., & Quek, C. H. (2013) · Neural Computation · doi:10.1162/neco_a_00474 · Cited by 102
Jochumsen, M., Niazi, I. K., Taylor, D., Farina, D., & Dremstrup, K. (2015) · Journal of Neural Engineering · doi:10.1088/1741-2560/12/5/056013 · Cited by 100
“The application of a spatial filter has been shown to improve single trial analysis by improving the signal-to-noise ratio [38]; this will make it easier to detect the small differences in the MRCP morphology associated with different levels of force and speed [15].”
Shin, Y., Lee, S., Lee, J.-H., & Lee, H.-N. (2012) · Journal of Neural Engineering · doi:10.1088/1741-2560/9/5/056002 · Cited by 92
“Namely, a classifier could become overfitted to the transient part of the training set and, in such a case, it might not work well with a test signal [17].”
BackgroundMethodInfluentialDecoding subjective emotional arousal from EEG during an immersive virtual reality experience
Hofmann, S., Klotzsche, F., Mariola, A., Nikulin, V. V., Villringer, A., & Gaebler, M. (2021) · eLife · doi:10.7554/elife.64812 · Cited by 110
Dimensionality reduction for the analysis of brain oscillations
Haufe, S., Dähne, S., & Nikulin, V. V. (2014) · NeuroImage · doi:10.1016/j.neuroimage.2014.06.073 · Cited by 101
“A particularly popular spatial filtering technique in the context of MI-BCIs is the so-called common spatial patterns (CSP, Blankertz et al., 2008) algorithm.”
Multivariate Machine Learning Methods for Fusing Multimodal Functional Neuroimaging Data
Dähne, S., Bieszmann, F., Samek, W., Haufe, S., Goltz, D., Gundlach, C., Villringer, A., Fazli, S., & Müller, K. (2015) · Proceedings of the IEEE · doi:10.1109/jproc.2015.2425807 · Cited by 104
“The last equation is the solution to the objective function of the common spatial patterns (CSP) algorithm, which is very popular in the field of brain–computer interfaces (BCIs) [100].”
Recognition of EEG Signal Motor Imagery Intention Based on Deep Multi-View Feature Learning
Xu, J., Zheng, H., Wang, J., Li, D., & Fang, X. (2020) · Sensors · doi:10.3390/s20123496 · Cited by 99
“CSP is a feature extraction algorithm widely apply to motor imagery of EEG signals [29,30].”
MethodAppriou, A., Cichocki, A. S., & Lotte, F. (2020) · IEEE Systems Man and Cybernetics Magazine · doi:10.1109/msmc.2020.2968638 · Cited by 102
“This is the standard way current BCIs are designed, given the large between-subject variability [14].”
BackgroundMethodInfluentialMansour, S., Ang, K. K., Nair, K. P. S., Phua, K. S., & Arvaneh, M. (2021) · Clinical EEG and Neuroscience · doi:10.1177/15500594211009065 · Cited by 109
“CSP is a feature extraction algorithm that assigns different weights to different EEG channels, such that the weighted sum of the powers of brain signals is maximized for one class and minimized for the other class.(14,15) In MI- and IM-based BCIs, the CSP features are the weighted sum of the powers of 8 to 30 Hz band…”
MethodMachine learning based brain signal decoding for intelligent adaptive deep brain stimulation
Merk, T., Peterson, V., Köhler, R. M., Haufe, S., Richardson, R. M., & Neumann, W. (2022) · Experimental Neurology · doi:10.1016/j.expneurol.2022.113993 · Cited by 102
“Along these lines, the common spatial patterns (CSP) method is a well-known and widely used method in the field of brain-computer interfaces (Blankertz et al., 2008; H ¨ am ¨ al ¨ ainen and Hari, 2002).”
A shallow mirror transformer for subject-independent motor imagery BCI
Luo, J., Wang, Y., Xia, S., Lu, N., Ren, X., Shi, Z., & Hei, X. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107254 · Cited by 95
He, L., Hu, Y., Li, Y., & Li, D. (2013) · Neurocomputing · doi:10.1016/j.neucom.2013.05.005 · Cited by 90
RSTFC: A Novel Algorithm for Spatio-Temporal Filtering and Classification of Single-Trial EEG
Qi, F., Li, Y., & Wu, W. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2402694 · Cited by 92
“for notational convenience) is compared with CSP, CSSP, CSSSP, and FBCSP, and the feature selection and classification module are compared with the conventional variance ratiobased feature selection + FLDA approach [2].”
MethodFazli, S., Dähne, S., Samek, W., Bieszmann, F., & Müller, K. (2015) · Proceedings of the IEEE · doi:10.1109/jproc.2015.2413993 · Cited by 97
“While a number of methods have been proposed, if a calibration dataset is available [42], [43], [46], [47], these cannot be applied when there is no calibration data present.”
MethodInfluentialDOSED: A deep learning approach to detect multiple sleep micro-events in EEG signal
Chambon, S., Thorey, V., Arnal, P. J., Mignot, E. J.-M., & Gramfort, A. (2019) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2019.03.017 · Cited by 102
Farquhar, J. D. R., & Hill, N. J. (2012) · Neuroinformatics · doi:10.1007/s12021-012-9171-0 · Cited by 108
“…between spatial filtering and classification, this equivalence no-longer holds and different spatial filtering methods (PCA whitening alone, ICA of various kinds, CSP) may be expected to produce different results, as is familiar from the BCI literature, see for example (Blankertz et al. 2008).”
ResultDynamic frequency feature selection based approach for classification of motor imageries
Luo, J., Feng, Z., Zhang, J., & Lu, N. (2016) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2016.03.004 · Cited by 89
Höhne, J., Holz, E., Staiger-Sälzer, P., Müller, K.-R., Kübler, A., & Tangermann, M. (2014) · PLoS ONE · doi:10.1371/journal.pone.0104854 · Cited by 85
“In analogy to Blankertz and colleagues (2008) [60], offline classification accuracy was estimated using a (standard) cross-validation procedure, where the CSP filters and LDA weights were computed on the training set, and binary accuracy was assessed on the test set.”
MethodSelf-citationMiao, M., Zeng, H., Wang, A., Zhao, C., & Liu, F. (2016) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2016.12.010 · Cited by 89
“When designing an optimal spatial filter with CSP, to the best of our knowledge, a majority of the previous methods considered pairs of the eigenvectors corresponding to the K smallest and K largest eigenvalues of the estimated covariance matrices [1,2,11-15].”
MethodKumar, S., Mamun, K. A., & Sharma, A. K. (2017) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2017.10.025 · Cited by 86
“To this end, common spatial pattern (CSP) has been widely explored [33] and used in BCI research.”
Different Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach
He, H., & Wu, D. (2020) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2020.2980299 · Cited by 86
“For both datasets, the EEG signals were preprocessed using the Matlab EEGLAB toolbox [42], following the guideline in [43].”
MethodFast EEG-Based Decoding Of The Directional Focus Of Auditory Attention Using Common Spatial Patterns
Geirnaert, S., Francart, T., & Bertrand, A. (2020) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2020.3033446 · Cited by 106
Ke, H., Chen, D., Shah, T., Liu, X., Zhang, X., Zhang, L., & Li, X. (2018) · Software Practice and Experience · doi:10.1002/spe.2668 · Cited by 97
EEG Motor Imagery Classification With Sparse Spectrotemporal Decomposition and Deep Learning
Sun, B., Zhao, X., Zhang, H., Bai, R., & Li, T. (2020) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2020.3021456 · Cited by 89
Automatic and Efficient Framework for Identifying Multiple Neurological Disorders From EEG Signals
Tawhid, M. N. A., Siuly, S., Wang, K., & Wang, H. (2023) · IEEE Transactions on Technology and Society · doi:10.1109/tts.2023.3239526 · Cited by 98
“widespread availability for clinicians [7].”
Zander, T., & Jatzev, S. (2011) · Journal of Neural Engineering · doi:10.1088/1741-2560/9/1/016003 · Cited by 96
“Several studies claim that they have to be further investigated to find new solutions of online adaptation, e.g. [14, 23–26].”
BackgroundFeature Weighting and Regularization of Common Spatial Patterns in EEG-Based Motor Imagery BCI
Mishuhina, V., & Jiang, X. (2018) · IEEE Signal Processing Letters · doi:10.1109/lsp.2018.2823683 · Cited by 89
“CSP [3] is one of the most popular algorithms in MI-BCI for spatial filtering to extract features.”
MethodInfluentialUsman, S. M., Khalid, S., Akhtar, R., Bortolotto, Z. A., Bashir, Z. I., & Qiu, H. (2019) · Seizure · doi:10.1016/j.seizure.2019.08.006 · Cited by 98
“by converting a multiple channel EEG signal into a surrogate channel [55, 56] or by applying band-pass filters.”
MethodSparse Representation for Brain Signal Processing: A tutorial on methods and applications
Li, Y., Yu, Z. L., Bi, N., Xu, Y., Gu, Z., & Амари, Ш.-И. (2014) · IEEE Signal Processing Magazine · doi:10.1109/msp.2013.2296790 · Cited by 82
Scherer, R., Faller, J., Friedrich, E. V. C., Opisso, E., Costa, U. M., Kübler, A., & Müller-Putz, G. (2015) · PLoS ONE · doi:10.1371/journal.pone.0123727 · Cited by 98
Nicolas-Alonso, L. F., Corralejo, R., Gómez‐Pilar, J., Álvarez, D., & Hornero, R. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.02.005 · Cited by 87
“CSP calculates the spatial fi lters by solving an eigenvalue decomposition problem that involves the mean spatial covariances for each of the two classes [42].”
MethodUsing single-trial EEG to predict and analyze subsequent memory
Noh, E., Herzmann, G., Curran, T., & de Sa, V. R. (2013) · NeuroImage · doi:10.1016/j.neuroimage.2013.09.028 · Cited by 100
“Common spatial patterns (CSPs) were used to learn spatial filters which maximize the power difference between the two classes (Blankertz et al., 2008).”
EEG-based continuous control of a game using a 3 channel motor imagery BCI: BCI game
Coyle, D., Garcia, J., Satti, A. R., & McGinnity, T. M. (2011) · IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB) · doi:10.1109/ccmb.2011.5952128 · Cited by 88
A Brain-Computer Interface Based on a Few-Channel EEG-fNIRS Bimodal System
Ge, S., Yang, Q., Wang, R., Lin, P., Gao, J., Leng, Y., Yang, Y., & Wang, H. (2017) · IEEE Access · doi:10.1109/access.2016.2637409 · Cited by 89
“multichannel feature extraction [54]–[56].”
Predictive regression modeling with MEG/EEG: from source power to signals and cognitive states
Sabbagh, D., Ablin, P., Varoquaux, G. P., Gramfort, A., & Engemann, D. A. (2020) · NeuroImage · doi:10.1016/j.neuroimage.2020.116893 · Cited by 100
Distributed Signal Processing for Wireless EEG Sensor Networks
Bertrand, A. (2015) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2015.2418351 · Cited by 95
“Spatial filtering is often used for brain-computer interfaces (BCI) [41]–[43], for artifact reduction [17], [18], [34], [44]–[50], or for clinical decision making [51], [52].”
BackgroundInfluentialSpatiotemporal-Filtering-Based Channel Selection for Single-Trial EEG Classification
Qi, F., Wu, W., Yu, Z. L., Gu, Z., Wen, Z., Yu, T., & Li, Y. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2963709 · Cited by 86
“3) Learning Multiple Spatiotemporal Filters: With the selected channels, we use a nonsparse spatiotemporal filter optimization algorithm to learn multiple spatiotemporal filters, as the use of multiple spatiotemporal filters has been indicated to further increase the classification performance [35].”
MethodInfluentialJeong, J.-H., Cho, J.-H., Shim, K.-H., Kwon, B.-H., Lee, B.-H., Lee, D.-Y., Lee, D.-H., & Lee, S. (2020) · GigaScience · doi:10.1093/gigascience/giaa098 · Cited by 97
“CSP feature extraction method and RLDA classifier are generally used as baseline algorithms for decoding EEG-based MI and motor execution in the field of BCI [26, 45, 46].”
Brain–computer interfacing in disorders of consciousness
Chatelle, C., Chennu, S., Noirhomme, Q., Cruse, D., Owen, A. M., & Laureys, S. (2012) · Brain Injury · doi:10.3109/02699052.2012.698362 · Cited by 79
“It is focused on improving the spatial resolution of EEG data at the single-trial level [77].”
BackgroundSpüler, M., Walter, A., Rosenstiel, W., & Bogdan, M. (2014) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2013.2290870 · Cited by 87
“For motor-imagery BCIs, common spatial patterns (CSP) [5] is an established method that is widely used in BCI research.”
MethodRemoval of muscular artifacts in EEG signals: a comparison of linear decomposition methods
Frølich, L., & Dowding, I. (2018) · Brain Informatics · doi:10.1007/s40708-017-0074-6 · Cited by 91
“ERD/ERS is calculated as the increase/decrease in signal power in a given frequency band relative to a reference period [51, 52]: ERDðtÞ :1⁄4 PowerðtÞ Reference power Reference power ð2Þ”
BackgroundPredicting individual decision-making responses based on single-trial EEG
Si, Y., Li, F., Duan, K., Tao, Q., Li, C., Cao, Z., Zhang, Y., Biswal, B. B., Li, P., Yao, D., et al. (2019) · NeuroImage · doi:10.1016/j.neuroimage.2019.116333 · Cited by 91
“The differentiation abilities of the fi lters were denoted by the eigenvalues in Ʃ , and the fi rst and last fi lters corresponding to the largest and smallest eigenvalues consist of the most discriminative DSNP fi lter pair (Benjamin Blankertz et al., 2008).”
Cecotti, H. (2011) · Pattern Recognition Letters · doi:10.1016/j.patrec.2011.02.022 · Cited by 80
Single-Trial Event-Related Potential Correlates of Belief Updating
Bennett, D., Murawski, C., & Bode, S. (2015) · eneuro · doi:10.1523/eneuro.0076-15.2015 · Cited by 78
“…as CSD, are recommended for single-trial EEG analysis because of their ability to extract estimates of activity that are unique to each electrode, which increases the signalto-noise ratio of individual trial CSD-ERPs, thereby augmenting the statistical power of analysis (Blankertz et al., 2008).”
BackgroundIrimia, D.-C., Ortner, R., Poboroniuc, M.-S., Ignat, B. E., & Guger, C. (2018) · Frontiers in Robotics and AI · doi:10.3389/frobt.2018.00130 · Cited by 89
Multivariate cross-frequency coupling via generalized eigendecomposition
Cohen, M. X. (2017) · eLife · doi:10.7554/elife.21792 · Cited by 79
“The GED framework is not limited to CFC; it is also recommended that GED is used to define a spatial filter that maximizes power at the lower frequency ( Blankertz et al., 2008 ; Nikulin et al., 2011 ; Parra and Sajda, 2003 ; Sa¨rela¨ and Valpola, 2005 ).”
InfluentialMultimodal Fuzzy Fusion for Enhancing the Motor-Imagery-Based Brain Computer Interface
Ko, L., Lin, C., Lu, Y., Bustince, H., Chang, Y., Chang, Y., Ferandez, J., Wang, Y., Sanz, J., & Dimuro, G. P. (2019) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2018.2881647 · Cited by 85
“CSp The CSP, which is a well-known mathematical procedure commonly used in EEG signal processing, was used in this study to transform multivariate EEG signals into well-separated subcomponents with maximum spatial variation [30], [31].”
MethodA Deflation Procedure for Subspace Decomposition
Sameni, R., Jutten, C., & Shamsollahi, M. B. (2009) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2009.2037353 · Cited by 75
“…dimensions of the desired subspace is commonly required in advance; d) coplanar (intersecting) subspaces can not be separated; e) full-rank noise is not separated and may even be amplified in the extracted components [12]; f) the rank of the observations are commonly reduced, if used for denoising.”
BackgroundRegularized Linear Discriminant Analysis of EEG Features in Dementia Patients
Neto, E., Bießmann, F., Aurlien, H., Nordby, H., & Eichele, T. (2016) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2016.00273 · Cited by 89
“…spatial filters that maximize the variance of EEG signals of one class while minimizing the variance from the other class (Ramoser et al., 2000; Blankertz et al., 2008), at the same time, this may result on overfitting the model by changing predictor variances (Reuderink and Poel, 2008; Huang…”
BackgroundTsuchimoto, S., Shibusawa, S., Iwama, S., Hayashi, M., Okuyama, K., Mizuguchi, N., Kato, K., & Ushiba, J. (2021) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2021.109089 · Cited by 88
On the effects of data normalization for domain adaptation on EEG data
Apicella, A., Isgrò, F., Pollastro, A., & Prevete, R. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106205 · Cited by 100
“Finally, the Common Spatial Pattern (CSP) [55] was applied since it is a widely recognised feature extraction technique involved in classification tasks on the motor imagery studies [56].”
MethodInfluentialOptimum 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
A Comparison Study on EEG Signal Processing Techniques Using Motor Imagery EEG Data
Oikonomou, V. P., Georgiadis, K., Liaros, G., Nikolopoulos, S., & Kompatsiaris, I. Y. (2017) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms.2017.113 · Cited by 88
Towards a Hybrid BCI Gaming Paradigm Based on Motor Imagery and SSVEP
Wang, Z., Yu, Y., Xu, M., Liu, Y., Yin, E., & Zhou, Z. (2018) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2018.1445068 · Cited by 78
“The details were described in a previous study (Blankertz, Tomioka, Lemm, Kawanabe, & Muller, 2008).”
MethodVisual Feedback Dominates the Sense of Agency for Brain-Machine Actions
Evans, N., Gale, S., Schurger, A., & Blanke, O. (2015) · PLOS ONE · doi:10.1371/journal.pone.0130019 · Cited by 74
“Real-time EEG signals for each electrode were individually weighted using common spatial patterns [38] to create a feature vector and were finally subjected to linear discriminant analysis in order to generate the left or right velocity of the visual cursor.”
MethodInce, N. F., Gupta, R., Arica, S., Tewfik, A. H., Ashe, J., & Pellizzer, G. (2010) · PLoS ONE · doi:10.1371/journal.pone.0014384 · Cited by 74
“tool in multichannel neural activity processing for binary classification paradigms [21].”
MethodAnalyzing Speech Quality Perception Using Electroencephalography
Voigt‐Antons, J., Schleicher, R., Arndt, S., Möller, S., Porbadnigk, A. K., & Curio, G. (2012) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2012.2191936 · Cited by 85
“In the context of EEG-based brain–computer interfaces (BCIs) [15], machine learning methods play a crucial role in extracting relevant information from the high-dimensional data [16] and [17].”
BackgroundRotational data augmentation for electroencephalographic data
Krell, M. M., & Kim, S. K. (2017) · 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2017.8036864 · Cited by 65
“, [2]–[5].”
Tawhid, M. N. A., Siuly, S., & Wang, H. (2020) · Electronics Letters · doi:10.1049/el.2020.2646 · Cited by 78
On Optimal Channel Configurations for SMR-based Brain–Computer Interfaces
Sannelli, C., Dickhaus, T., Halder, S., Hammer, E. M., Müller, K., & Blankertz, B. (2010) · Brain Topography · doi:10.1007/s10548-010-0135-0 · Cited by 81
Self-citationShin, Y., Lee, S., Ahn, M., Cho, H., Jun, S. C., & Lee, H.-N. (2015) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2015.05.007 · Cited by 80
“Then, we reduce the dimension of EEG signal using the common spatial pattern (CSP) filtering, which is a widely used feature selection method for motor imagery based BCI systems [5,11,20].”
An EEG motor imagery dataset for brain computer interface in acute stroke patients
Liu, H., Wei, P., Wang, H., Lv, X., Duan, W., Li, M., Zhao, Y., Wang, Q., Chen, X., Shi, G., et al. (2024) · Scientific Data · doi:10.1038/s41597-023-02787-8 · Cited by 107
“Regarding the features used for EEG decoding, the common spatial pattern (CSP) is an optimal set of spatial filters for projection and is commonly used 16–19 .”
BackgroundMethodDensely Feature Fusion Based on Convolutional Neural Networks for Motor Imagery EEG Classification
Li, D., Wang, J., Xu, J., & Fang, X. (2019) · IEEE Access · doi:10.1109/access.2019.2941867 · Cited by 71
“In order to avoid the main problem of this inherent difference, a common spatial pattern (CSP) is proposed and widely applied to MI-BCI [19]-[20].”
MethodCommon Spatial Pattern revisited by Riemannian geometry
Barachant, A., Bon, S., Congedo, M., & Jutten, C. (2010) · 2010 IEEE International Workshop on Multimedia Signal Processing · doi:10.1109/mmsp.2010.5662067 · Cited by 69
“In the context of a two-class paradigm in EEG-BCI, the Common Spatial Pattern (CSP) algorithm is the technique of choice for spatial filtering [1].”
InfluentialAdaptive Stacked Generalization for Multiclass Motor Imagery-Based Brain Computer Interfaces
Nicolas-Alonso, L. F., Corralejo, R., Gómez‐Pilar, J., Álvarez, D., & Hornero, R. (2015) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2015.2398573 · Cited by 78
“2) Spatial Filtering: The second stage spatially filters each band-pass signal using CSP [53].”
MethodCarino-Escobar, R. I., Carrillo‐Mora, P., Valdés-Cristerna, R., Rodríguez-Barragán, M. A., Hernández-Arenas, C., Quinzaños-Fresnedo, J., Galicia-Alvarado, M. A., & Cantillo-Negrete, J. (2019) · Neural Plasticity · doi:10.1155/2019/7084618 · Cited by 88
“The processing stage’s feature extraction algorithm was a common spatial pattern (CSP) filter, applied to each one of the 6 frequency subbands [24], following a methodology similar to the Filter Bank Common Spatial Patterns (FBCSP) [25].”
MethodComparing Different Classifiers in Sensory Motor Brain Computer Interfaces
Bashashati, H., Ward, R. K., Birch, G. E., & Bashashati, A. (2015) · PLoS ONE · doi:10.1371/journal.pone.0129435 · Cited by 86
“Common Spatial Patterns (CSP) [28][29] is used for spatial filtering.”
MethodProportional estimation of finger movements from high-density surface electromyography
Celadon, N., Dosen, S. S., Jakob, I., Ariano, P., & Farina, D. (2016) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-016-0172-3 · Cited by 76
Exploring dimensionality reduction of EEG features in motor imagery task classification
García-Laencina, P. J., Rodríguez-Bermúdez, G., & Roca‐Dorda, J. (2014) · Expert Systems with Applications · doi:10.1016/j.eswa.2014.02.043 · Cited by 79
“In particular, the CSP method projects the multichannel EEG signals into a subspace (the obtained CSP features) with an optimal variance for the subsequent classification (Blankertz et al., 2008).”
MethodYang, Y., Chevallier, S., Wiart, J., & Bloch, I. (2017) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2017.06.016 · Cited by 76
“…band of sensorimotor rhythm can varies from subject to subject Individual differences in the frequency band of sensorimotor rhythm will deteriorate BCI performances when using a general parameter setting for all subjects (e. . features from the broad frequency band 8–30 Hz), as shown in Fig.”
BackgroundChowdhury, A., Raza, H., Meena, Y. K., Dutta, A., & Prasad, G. (2017) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2017.2787040 · Cited by 79
“not invariant against dynamic intrasession and intersession changes in the signal, as CSP only considers the difference in means between two classes while ignoring the scatter within a particular class [20], [28].”
BackgroundSeparation of stationary and non-stationary sources with a generalized eigenvalue problem
Hara, S., Kawahara, Y., Washio, T., von Bünau, P., Tokunaga, T., & Yumoto, K. (2012) · Neural Networks · doi:10.1016/j.neunet.2012.04.001 · Cited by 77
Bayesian Learning for Spatial Filtering in an EEG-Based Brain–Computer Interface
Zhang, H., Yang, H., & Guan, C. (2013) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2013.2249087 · Cited by 74
“It is recognized that CSP is especially useful in sensorimotor rhythm (SMR)-BCI [21] with motorrelated mental tasks [19], [22].”
BackgroundMethodInfluentialLeamy, D. J., Kocijan, J., Domijan, K., Duffin, J., Roche, R. A. P., Commins, S., Collins, R., & Ward, T. E. (2014) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/1743-0003-11-9 · Cited by 79
“Common spatial patterns The CSP algorithm [23,24] was then applied to the segments of EEG data from each frequency range.”
MethodMaximally reliable spatial filtering of steady state visual evoked potentials
Dmochowski, J., Greaves, A. S., & Norcia, A. M. (2015) · NeuroImage · doi:10.1016/j.neuroimage.2014.12.078 · Cited by 68
Decoding hand movement velocity from electroencephalogram signals during a drawing task
Lv, J., Li, Y., & Gu, Z. (2010) · BioMedical Engineering OnLine · doi:10.1186/1475-925x-9-64 · Cited by 79
Li, Y., & Guan, C. (2006) · Neural Computation · doi:10.1162/neco.2006.18.11.2730 · Cited by 70
Common Spatial Pattern Reformulated for Regularizations in Brain–Computer Interfaces
Wang, B., Wong, C. M., Kang, Z., Liu, F., Shui, C., Wan, F., & Chen, C. L. P. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2982901 · Cited by 77
Efficient CSP Algorithm With Spatio-Temporal Filtering for Motor Imagery Classification
Jiang, A., Shang, J., Liu, X., Tang, Y., Kwan, H. K., & Zhu, Y. (2020) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2020.2979464 · Cited by 76
“Common spatial pattern (CSP) [10]–[12] is widely used in EEG-based MI BCIs.”
MethodRandom Forest and Filter Bank Common Spatial Patterns for EEG-Based Motor Imagery Classification
Bentlemsan, M., Zemouri, E.-T., Bouchaffra, D., Yahya-Zoubir, B., & Ferroudji, K. (2014) · International Conference on Intelligent Systems, Modelling and Simulation · doi:10.1109/isms.2014.46 · Cited by 78
“CSP algorithm is powerful in calculating spatial filters for detecting ERD/ERS [2].”
MethodCan a Subjective Questionnaire Be Used as Brain-Computer Interface Performance Predictor?
Rimbert, S., Gayraud, N., Bougrain, L., Clerc, M., & Fleck, S. (2019) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2018.00529 · Cited by 74
“During training, CSP yields spatial filters W ∈ R F × C which project the signal onto a surrogate space where the inter-class separability is maximized (Blankertz et al., 2008).”
A feasibility study of a complete low-cost consumer-grade brain-computer interface system
Peterson, V., Galván, C. M., Hernández, H., & Spies, R. D. (2020) · Heliyon · doi:10.1016/j.heliyon.2020.e03425 · Cited by 82
“In fact, while the spatial filter maps may resemble the brain patterns associated to a specific MI task, the spatial pattern maps illustrate how the presumed brain sources are projected into the scalp [25].”
BackgroundMethodZhou, B., Wu, X., Lv, Z., Zhang, L., & Guo, X. (2016) · PLoS ONE · doi:10.1371/journal.pone.0162657 · Cited by 104
Extracting features from phase space of EEG signals in brain–computer interfaces
Fang, Y., Chen, M., & Zheng, X. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.10.038 · Cited by 67
Rodríguez-Bermúdez, G., & García-Laencina, P. J. (2012) · Journal of Medical Systems · doi:10.1007/s10916-012-9893-4 · Cited by 75
Using Recent BCI Literature to Deepen our Understanding of Clinical Neurofeedback: A Short Review
Jeunet, C., Lotte, F., Batail, J.-M. V., Philip, P., & Micoulaud‐Franchi, J. (2018) · Neuroscience · doi:10.1016/j.neuroscience.2018.03.013 · Cited by 89
“For instance, ML tools are extensively used to identify user-specific SensoriMotor Rhythm (SMR) frequency bands in SMR-BCI 3 (Pregenzer et al., 1999; Blankertz et al., 2008, Ang et al., 2012).”
Toward Interpretable Machine Learning: Transparent Deep Neural Networks and BeyondPreprint
Samek, W., Montavon, G., Lapuschkin, S., Anders, C. J., & Müller, K. (2020) · arXiv (Cornell University) · Cited by 95
Tcheslavski, G. V., & Gonen, F. F. (2012) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2011.12.006 · Cited by 71
“It has been reported that implementation of such filters may lead to an improved discrimination between EEG produced in different participants’ conditions [34,35].”
BackgroundEpileptic Seizure Detection and Experimental Treatment: A Review
Kim, T.-H., Nguyen, P., Pham, N., Bui, N., Truong, H., Ha, S., & Vu, T. N. (2020) · Frontiers in Neurology · doi:10.3389/fneur.2020.00701 · Cited by 78
“Lastly, if EEG recordings have multi-channel, they give blurred images of brain activity due to the volume conduction (80).”
BackgroundFinding stationary brain sources in EEG data
von Bünau, P., Meinecke, F. C., Scholler, S., & Müller, K. (2010) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.2010.5626537 · Cited by 78
“For classification of EEG data, the state-ofthe-art method consists of two stages: first, discriminative features (usually around 2-8) in the high-dimensional EEG signal (often up to 128 channels) are determined using the Common Spatial Patterns [14], [ 15 ] algorithm, which finds directions such that the signal power…”
MethodMeng, J., Yao, L., Sheng, X., Zhang, D., & Zhu, X. (2014) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2014.2345458 · Cited by 69
“However, the rhythm activity derived by noninvasive EEG recorded from the scalp is blurred due to volume conduction and is easily contaminated by other sources and artifacts [4].”
Morioka, H., Kanemura, A., Morimoto, S., Yoshioka, T., Oba, S., Kawanabe, M., & Ishii, S. (2014) · NeuroImage · doi:10.1016/j.neuroimage.2013.12.035 · Cited by 74
“Many EEG-based decoding methods are based on spatial filtering (Wolpaw andWolpaw, 2012); thus, we show a comparison of the proposed method to common spatial patterns (CSPs) (Blankertz et al., 2008), a major spatial filter.”
Self-citationNeuroadaptive Bayesian Optimization and Hypothesis Testing
Lorenz, R., Hampshire, A., & Leech, R. (2017) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2017.01.006 · Cited by 71
Metadata
- Authors
- Blankertz, B., Tomioka, R., Lemm, S., Kawanabe, M., & Muller, K.-R.
- Affiliations
- University of Florida (US)
- Conexant (United States) (US)
- Fraunhofer Institute for Open Communication Systems (DE)
- Venue
- IEEE Signal Processing Magazine
- Published
- 2008
- Volume
- 25
- Issue
- 1
- Pages
- 41-56
- ISSN
- 1053-5888 (ISSN-L)
- OpenAlex
- W2099509424
- Cited by
- 2,080
- References
- 62
- Citations by year
- 2026: 96 · 2025: 116 · 2024: 109 · 2023: 126 · 2022: 121 · 2021: 154 · 2020: 159 · 2019: 140 · 2018: 130 · 2017: 124 · 2016: 117 · 2015: 120 · 2014: 121 · 2013: 135 · 2012: 89
- FWCI
- 37.89
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Signal Processing Magazine (publishedVersion)
- Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft) (submittedVersion)
- Fraunhofer-Publica (Fraunhofer-Gesellschaft) (submittedVersion)
- Funders
- Bundesministerium für Bildung und Forschung
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Signal Processing › Blind Source Separation Techniques
- Keywords
- common spatial pattern, spatial filtering, brain-computer interface, signal-to-noise ratio, volume conduction, EEG preprocessing
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.