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 801–900 of 1,002
Machine-Learning Based Co-adaptive Calibration: A Perspective to Fight BCI Illiteracy
Vidaurre, C., Sannelli, C., Müller, K., & Blankertz, B. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-13769-3_50 · Cited by 20
“Machine Learning based BCIs use EEG features of larger complexity that can be fitted better to the individual characteristics of brain patterns of each user (see [9,13,18,1,19,20]).”
BackgroundSelf-citationChoo, S., Park, H., Jung, J., Flores, K., & Nam, C. S. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106665 · Cited by 25
Wang, D., & Wei, Q. (2025) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2025.3560993 · Cited by 24
“CSP efficiently isolates spatially discriminative components from multichannel EEG data pertaining to each class, thus facilitating analysis and classification [12].”
Cantillo-Negrete, J., Rodríguez-García, M. E., Carrillo‐Mora, P., Arias-Carrión, Ó., Ortega‐Robles, E., Galicia-Alvarado, M. A., Valdés-Cristerna, R., Ramirez-Nava, A. G., Hernández-Arenas, C., Quinzaños-Fresnedo, J., et al. (2025) · Frontiers in Neuroscience · doi:10.3389/fnins.2025.1579988 · Cited by 29
Fuzzy Divergence Based Analysis for Eeg Drowsiness Detection Brain Computer Interfaces
Reddy, T. K., Arora, V., Behera, L., Wang, Y., & Lin, C. (2020) · IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzz48607.2020.9177833 · Cited by 23
Deep-Learning-Based Automatic Selection of Fewest Channels for Brain–Machine Interfaces
Kim, H.-S., Ahn, M.-H., & Min, B. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3052813 · Cited by 19
“an algorithm for selecting a discriminative time interval [56].”
MethodA Novel Ensemble Learning Approach for Classification of EEG Motor Imagery Signals
Echtioui, A., Zouch, W., Ghorbel, M., Mhiri, C., & Hamam, H. (2021) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc51323.2021.9498833 · Cited by 23
Giles, J., Ang, K. K., Phua, K. S., & Arvaneh, M. (2022) · Frontiers in Neuroergonomics · doi:10.3389/fnrgo.2022.837307 · Cited by 23
“The final co-variance matrices are then used for training the Common Spatial Patterns (CSP) features (Blankertz et al., 2008), as further elaborated in Section 3.”
MethodAdaptive Multimodel Knowledge Transfer Matrix Machine for EEG Classification
Liang, S., Hang, W., Lei, B., Wang, J., Qin, J., Choi, K., & Zhang, Y. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3220551 · Cited by 24
“The first and last three spatial filters of CSP were used, as recommended in [44].”
MethodEnhancing motor imagery detection efficacy using multisensory virtual reality priming
Gougeh, R. A., & Falk, T. H. (2023) · Frontiers in Neuroergonomics · doi:10.3389/fnrgo.2023.1080200 · Cited by 29
Two modes of midfrontal theta suggest a role in conflict and error processing
Muralidharan, V., Aron, A. R., Cohen, M. X., & Schmidt, R. (2023) · NeuroImage · doi:10.1016/j.neuroimage.2023.120107 · Cited by 22
Mutual information-based optimization of sparse spatio-spectral filters in brain–computer interface
Arvaneh, M., Guan, C., Ang, K. K., & Quek, C. H. (2013) · Neural Computing and Applications · doi:10.1007/s00521-013-1523-7 · Cited by 20
“The CSP algorithm [12,14] is an effective technique in discriminating two classes of EEG data.”
BackgroundMethodInfluentialAndrade, J., Cecílio, J., Simões, M. A., Sales, F., & Castelo-Branco, M. S. (2017) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-017-0276-4 · Cited by 24
“We also applied the steps described by [32] with similar results.”
ResultMotor Rehabilitation for Hemiparetic Stroke Patients Using a Brain-Computer Interface Method
Cho, W., Guger, C., Heilinger, A., Ortner, R., Murovec, N., Xu, R., Swift, J. R., Zehetner, M., Schobesberger, S., & Edlinger, G. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00178 · Cited by 25
“Then common spatial patterns (CSP) were applied to transform the data to a new matrix with minimal variance of one class and maximal variance of the other class [13].”
MethodSemi-Supervised Deep Adversarial Learning for Brain-Computer Interface
Ko, W., Jeon, E., Lee, J., & Suk, H. (2019) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/iww-bci.2019.8737345 · Cited by 20
“That is, in our framework, instead of training a discriminator to distinguish between real and artificial EEG samples only, we now put an additional role on the discriminator to identify the class labels of real EEG signals.”
BackgroundInfluentialResting-State-Based Spatial Filtering for an fNIRS-Based Motor Imagery Brain-Computer Interface
Zheng, Y., Zhang, D., Wang, L., Wang, Y., Deng, H. J., Zhang, S., Li, D., & Wang, D. (2019) · IEEE Access · doi:10.1109/access.2019.2936434 · Cited by 19
“CSP [13], [14] is a very popular algorithm applied on the EEG-based BCI applications also on the fNIRS-based BCI applications to obtain the task-specific spatial filters [48].”
MethodRadman, M., Chaibakhsh, A., Nariman-zadeh, N., & He, H. (2019) · International Conference on Computer and Knowledge Engineering · doi:10.1109/iccke48569.2019.8965159 · Cited by 19
“In this method, firstly, the normalized covariance matrix of EEG data is calculated [19]: = ( ) (1) Where E is data associated with a test which sits in an × matrix.”
MethodWang, F., Xu, Z., Zhang, W., Wu, S., Zhang, Y., Ping, J., & Wu, C. (2020) · Review of Scientific Instruments · doi:10.1063/1.5142343 · Cited by 24
Zuo, C., Miao, Y., Wang, X., Wu, L., & Jin, J. (2020) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2020.108725 · Cited by 19
Jochumsen, M., Knoche, H. O., Kjær, T. W., Dinesen, B., & Kidmose, P. (2020) · Sensors · doi:10.3390/s20102804 · Cited by 19
“One way to do this is by applying a spatial filter [20,54]; however, this can only be done when multiple channels are recorded.”
BackgroundSolis‐Escalante, T., de Kam, D., & Weerdesteyn, V. (2020) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2020.3028966 · Cited by 22
“patterns algorithm (CSP) [22], [23].”
Feng, Y., Li, M., Lou, S., Zheng, H., Gao, Y., & Tan, J. (2021) · Journal of Computing and Information Science in Engineering · doi:10.1115/1.4049895 · Cited by 19
EEG classification for multiclass motor imagery BCI
Liu, C., Wang, H., & Lü, Z. (2013) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2013.6561736 · Cited by 24
Common spatial patterns for steady-state somatosensory evoked potentials
Nam, Y., Cichocki, A. S., & Choi, S. (2013) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2013.6609986 · Cited by 22
“The CSP is one of the most intensively studied feature extraction method for the motor imagery BCI paradigm [5].”
MethodMental State Estimation for Brain--Computer Interfaces
Das, K., Rizzuto, D. S., & Nenadić, Z. (2009) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2009.2022948 · Cited by 18
Performance monitoring for brain-computer-interface actions
Schurger, A., Gale, S., Gozel, O., & Blanke, O. (2016) · Brain and Cognition · doi:10.1016/j.bandc.2016.09.009 · Cited by 19
A Fast, Open EEG Classification Framework Based on Feature Compression and Channel Ranking
Han, J., Zhao, Y., Sun, H., Chen, J., Ke, A., Xu, G., Zhang, H., Zhou, J., & Wang, C. (2018) · Frontiers in Neuroscience · doi:10.3389/fnins.2018.00217 · Cited by 21
“CSP utilizes covariance analysis to amplify the class disparity in the spatial domain, to combine signals from different channels (Blankertz et al., 2007; Li et al., 2013).”
MethodParallel Mechanism of Spectral Feature-Enhanced Maps in EEG-Based Cognitive Workload Classification
Zhang, Y., & Shen, Y. (2019) · Sensors · doi:10.3390/s19040808 · Cited by 21
“Of the classical feature extraction methods, common space mode (CSP)-based methods are widely used to identify features [11–13], such as common sparse spectral pattern (CSSP) [14], sub-band common spatial pattern (SBCSP) [15], filter bank CSP (FBCSP) [16], discriminative CSP (DCSP) [17], and shrinkage regularized filt…”
MethodStatistical Pattern Recognition and Machine Learning in Brain–Computer Interfaces
Rao, R. P. N., & Scherer, R. (2010) · Elsevier eBooks · doi:10.1016/b978-0-12-375027-3.00010-7 · Cited by 23
Robust Brain-Computer Interfaces
Reuderink, B. (2011) · University of Twente Research Information · doi:10.3990/1.9789461910585 · Cited by 38
“[69, 7]), which reduces the investment of time needed for the first use of a BCI from weeks to minutes.”
BackgroundChen, S., Xie, N., Tang, Y., Ji, Y., He, Z., Wang, Y., Huang, X., Fu, J., Ge, M., Liu, Q., et al. (2025) · Research · doi:10.34133/research.0984 · Cited by 31
“Based on Cohen’s d , the effect size was calculated to facilitate an intuitive assessment of the magnitude of the inter-group differences (Table S3 ) [ 37 , 38 ].”
Miao, M., Hu, W., & Zhang, W. (2021) · Signal Image and Video Processing · doi:10.1007/s11760-021-01924-3 · Cited by 19
“Several previous studies [3,20] have shown that ERD/ERS phenomenon evoked by MI always appears in or close to left/right primary motor cortex (i.e., C3 and C4 electrodes) and both mu and beta rhythms are affected during MI.”
Multi-view optimization of time-frequency common spatial patterns for brain-computer interfaces
Huang, Y., Jin, J., Xu, R., Miao, Y., Liu, C., & Cichocki, A. S. (2021) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2021.109378 · Cited by 20
Nakra, A., & Duhan, M. (2022) · International Journal of Information Technology · doi:10.1007/s41870-021-00857-x · Cited by 18
“The CSP is defined as an optimization problem for enhancing positive class variance while at the same time minimising negative class variance [6].”
BackgroundEuler common spatial patterns for EEG classification
Sun, J., Wei, M., Luo, N., Li, Z., & Wang, H. (2022) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-021-02488-7 · Cited by 19
“Some studies have also indicated that motor imagery tasks are associated with attenuation or increase in localized brain rhythm activity called ERD/ERS [13].”
BackgroundInfluentialKhanam, T., Siuly, S., & Wang, H. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-08027-1 · Cited by 24
“This method is very useful for band-passing EEG signals with multiple channels [28, 29].”
MethodYamamoto, M. S., Sadatnejad, K., Tanaka, T., Islam, M. R., Dehais, F., Tanaka, Y., & Lotte, F. (2023) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2023.3295769 · Cited by 26
“The EEG signals were filtered by using a 4 th order Butterworth filter in a frequency band selected for each user according to the algorithm proposed in [43].”
MethodKhan, R. A., Rashid, N., Shahzaib, M., Malik, U. F., Arif, A., Iqbal, J., Saleem, M., Khan, U. S., & Tiwana, M. I. (2023) · PLoS ONE · doi:10.1371/journal.pone.0276133 · Cited by 25
“CSP can effectively extract the features of ERS and ERD in the motor imagery signals, so it has been widely used in BCI systems [36].”
BackgroundMethodManifold Learning-Based Common Spatial Pattern for EEG Signal Classification
Cai, G., Zhang, F., Yang, B., Huang, S., & Ma, T. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3357995 · Cited by 20
Sieghartsleitner, S., Sebastián-Romagosa, M., Cho, W., Grünwald, J., Ortner, R., Scharinger, J., Kamada, K., & Guger, C. (2024) · Frontiers in Neuroscience · doi:10.3389/fnins.2024.1346607 · Cited by 21
Smoothing of spatial filter by graph Fourier transform for EEG signals
Higashi, H., Tanaka, T., & Tanaka, Y. (2014) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2014.7041710 · Cited by 20
Harmonic Mean of Kullback–Leibler Divergences for Optimizing Multi-Class EEG Spatio-Temporal Filters
Wang, H. (2012) · Neural Processing Letters · doi:10.1007/s11063-012-9228-y · Cited by 20
“The representative filtering approach is the common spatial patterns (CSP) [5], which uses the variances of the filtered EEG courses as features [17], [19], [20], [21].”
BackgroundMethodEEG-based fuzzy cognitive load classification during logical analysis of program segments
Chatterjee, D., Sinharay, A., & Konar, A. (2013) · IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzz-ieee.2013.6622508 · Cited by 19
“Variances of EEG signal thus provides an important measure of brain activity [18].”
BackgroundA multimodal fNIRS and EEG-based BCI study on motor imagery and passive movement
Yu, J., Ang, K. K., Guan, C., & Wang, C. (2013) · International IEEE/EMBS Conference on Neural Engineering · doi:10.1109/ner.2013.6695857 · Cited by 19
Optimal Spatio-spectral Variable Size Subbands Filter for Motor Imagery Brain Computer Interface
Kirar, J. S., & Agrawal, R. K. (2016) · Procedia Computer Science · doi:10.1016/j.procs.2016.04.060 · Cited by 20
Unmixing Oscillatory Brain Activity by EEG Source Localization and Empirical Mode Decomposition
Hansen, S. T., Hemakom, A., Safeldt, M. G., Krohne, L. G., Madsen, K. H., Siebner, H. R., Mandic, D. P., & Hansen, L. K. (2019) · Computational Intelligence and Neuroscience · doi:10.1155/2019/5618303 · Cited by 21
“, making brain-computer interfaces (BCIs) [4, 5] and neurofeedback [6], and for optimizing brain stimulation [7], e.”
BackgroundMethodECG-Based Subject Identification Using Common Spatial Pattern and SVM
Alotaiby, T. N., Alshebeili, S. A., Aljafar, L. M., & Alsabhan, W. M. (2019) · Journal of Sensors · doi:10.1155/2019/8934905 · Cited by 18
Kim, J., Park, Y., & Chung, W. (2020) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/bci48061.2020.9061635 · Cited by 18
“The common spatial pattern (CSP) is well known method extracting discriminative features from EEG signals [11]–[15].”
BackgroundMethodRobust Motor Imagery Classification Using Sparse Representations and Grouping Structures
Oikonomou, V. P., Nikolopoulos, S., & Kompatsiaris, I. Y. (2020) · IEEE Access · doi:10.1109/access.2020.2997116 · Cited by 20
“Similarly, in addition to the limited amount of training trials the performance of the system can be affected by various operational conditions related to the time duration of the trials, the type of CSP filter, as well as the type of imaginary task [8], [17].”
BackgroundMethodAsEmo: Automatic Approach for EEG-Based Multiple Emotional State Identification
Kim, S., Yang, H.-J., Nguyen, N. A. T., & Lee, S. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3032678 · Cited by 19
“[46]proposedtousespatialfiltersbydetermining a common basis for the classes, and Lotte [47] determined the number of filters using a waveform length optimal spatial filter (WOSF).”
MethodInfluentialPrototype Design and Implementation of an Automatic Control System Based on a BCI
Choi, S., & Kang, B.-G. (2014) · Wireless Personal Communications · doi:10.1007/s11277-014-1861-5 · Cited by 18
“Although relatively accurate brain wave measurements are possible, this approach is generally not appropriate for general use because of the need for surgical procedures and associated side effects [9,10].”
BackgroundKnowledge 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
“We used Bayesian model averaging [15], which is a data dependent classifiers combination technique, in order to find the optimal weights for base classification models.”
BackgroundMethodMulticlass Filters by a Weighted Pairwise Criterion for EEG Single-Trial Classification
Wang, H. (2011) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2011.2105869 · Cited by 19
“One trivial extension was to divide the multiclass problem into many two-class situations followed by applying CSP repeatedly [ 4 ], [7].”
BackgroundMethodInfluentialKalantar, G., Sadreazami, H., Mohammadi, A., & Asif, A. A. (2017) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip.2017.8309109 · Cited by 20
“On the other hand, unprocessed EEG signals are known to have a poor spatial resolution owing to volume conduction [10].”
BackgroundKlotzsche, F., Mariola, A., Hofmann, S., Nikulin, V. V., Villringer, A., & Gaebler, M. (2018) · IEEE Conference on Virtual Reality and 3D User Interfaces (VR) · doi:10.1109/vr.2018.8446275 · Cited by 22
“4-devel) [6], we applied the common spatial patterns (CSP) [2] algorithm to extract band-power based features from the signal.”
MethodExploring Self-Paced Embodiable Neurofeedback for Post-stroke Motor Rehabilitation
Spychała, N., Debener, S., Bongartz, E., Müller, H., Thorne, J. D., Philipsen, A., & Braun, N. (2020) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2019.00461 · Cited by 23
“Briefly described, given two time windows of a multivariate signal, CSP finds spatial filters that minimize the variance for one class and simultaneously maximize the variance for the other class (for reviews, see Ramoser et al., 2000; Blankertz et al., 2008).”
BackgroundAng, K. K., Guan, C., Chua, K. S. G., Ang, B. T., Kuah, C. W. K., Wang, C., Phua, K. S., Chin, Z. Y., & Zhang, H. (2008) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.2008.4650129 · Cited by 21
“Hence, if there is a strong focus of the spatial pattern on the left hemisphere motor area that corresponds to the right hand imagery, it can be due to two possible reasons: It can either originate from an ERD during right hand imagery, or an ERS during left hand imagery or foot imagery due to an increase in the idle…”
BackgroundMethodA correntropy-based classifier for motor imagery brain-computer interfaces
Uribe, L. F. S., Filho, C. A. S., de Oliveira, V. A., Costa, T. B. D. S., Rodrigues, P. G., Soriano, D. C., Boccato, L., Castellano, G., & Attux, R. (2019) · Biomedical Physics & Engineering Express · doi:10.1088/2057-1976/ab5145 · Cited by 19
Improving motor imagery classification during induced motor perturbations
Vidaurre, C., Jorajuría, T., Ramos‐Murguialday, A., Müller, K.-R., Gómez, M., & Nikulin, V. V. (2021) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac123f · Cited by 19
Robust common spatial filters with a maxmin approach
Kawanabe, M., Vidaurre, C., Scholler, S., & Müller, K. R. (2009) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.2009.5334786 · Cited by 21
“One of the most popular tools to extract information from the brain signals is the calculation of common spatial filters (CSP) [5].”
MethodSelf-citationAssessment and Communication for People with Disorders of Consciousness
Ortner, R., Allison, B. Z., Pichler, G., Heilinger, A., Sabathiel, N., & Guger, C. (2017) · Journal of Visualized Experiments · doi:10.3791/53639 · Cited by 21
Wairagkar, M., Hayashi, Y., & Nasuto, S. J. (2018) · PLoS ONE · doi:10.1371/journal.pone.0193722 · Cited by 39
Meinel, A., Castaño-Candamil, S., Blankertz, B., Lotte, F., & Tangermann, M. (2018) · Neuroinformatics · doi:10.1007/s12021-018-9396-7 · Cited by 20
Self-citationZhou, B., Wu, X., Ruan, J., Zhao, L. V., & Zhang, L. (2019) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2019.01.017 · Cited by 19
Information Theoretic Feature Transformation Learning for Brain Interfaces
Özdenizci, O., & Erdogmus, D. (2019) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2019.2908099 · Cited by 19
“State-of-the-art discriminative spatial filtering of EEG in motor imagery paradigms highlights the common spatial patterns (CSP) algorithm [28], [29], which aims to identify a discriminative basis for a multichannel signal recorded under different conditions, where signal representations maximally differ in variance b…”
BackgroundMethodZhang, L., & Wei, Q. (2019) · Journal of Integrative Neuroscience · doi:10.31083/j.jin.2019.02.17 · Cited by 19
“Among them, EEG and fNIRS have been attractive due to their low cost and portability (Arvaneh et al., 2011; Aydemir et al., 2018; Blankertz et al., 2008; Ehrsson et al., 2003; Hong et al., 2017, 2015; Khan and Hong, 2017; Naseer and Hong, 2015; Shin et al., 2012).”
BackgroundSpinnato, J., Roubaud, M. C., Burle, B., & Torrésani, B. (2015) · Journal of Neural Engineering · doi:10.1088/1741-2560/12/3/036013 · Cited by 19
“Each column of U , denoted u j , can be referred to as spatial filters (see [38, 8, 7, 42]).”
BackgroundIdentifying EEG Parameters to Monitor Stroke Rehabilitation using Individual Analysis
Setiawan, H., Islamiyah, W. R., Wibawa, A. D., & Purnomo, M. H. (2019) · International Seminar on Intelligent Technology and Its Applications · doi:10.1109/isitia.2019.8937238 · Cited by 17
“Xuefeng Lei and Luyun Wang et al. [17] presented the identification EEG feature on stroke patient and normal subject based on CSP algorithm.”
BackgroundInfluentialVelasquez-Martinez, L. F., Caicedo-Acosta, J., & Castellanos-Dominguez, G. (2020) · Entropy · doi:10.3390/e22060703 · Cited by 17
“Specifically, to address the volume conduction problem, we perform a Laplacian filter that improves the spatial resolution of EEG recordings, avoiding the influence of noise from neighboring channels [48].”
MethodDiscrimination of Tourette Syndrome Based on the Spatial Patterns of the Resting–State EEG Network
Duan, K., Wu, Q., Liao, Y., Si, Y., Bore, J. C., Li, F., Tao, Q., Li, L., Lei, W., Hu, X., et al. (2020) · Brain Topography · doi:10.1007/s10548-020-00801-5 · Cited by 20
McGeady, C., Vučković, A., Zheng, Y., & Alam, M. (2021) · Sensors · doi:10.3390/s21196593 · Cited by 17
“To determine the feasibility of classifying movements from sensorimotor rhythms during tSCS we used the current state-of-the-art: Band-pass and common spatial pattern (CSP) filtering, followed by band-power feature extraction and linear discriminant analysis (LDA) classification [17].”
MethodComplex-valued spatial filters for task discrimination
Falzon, O., Camilleri, K. P., & Muscat, J. (2010) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.2010.5626381 · Cited by 17
“A comprehensive review on the method of CSP and a number of variants can be found in [ 5 ].”
MethodLiparas, D., Dimitriadis, S. I., Laskaris, N., Tzelepi, A., Charalambous, K., & Angelis, L. (2014) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2014.04.032 · Cited by 19
“The CSP algorithm aims, mainly, at spatial discrimination (Blankertz et al., 2008).”
Wu, B., Yang, F., Zhang, J., Wang, Y., Zheng, X., & Chen, W. (2012) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2011.11.014 · Cited by 18
“CSP is an optimization method which has been proven in recent years to be very useful in extracting the spatial information of EEG activity and effectively reducing channel number [23].”
BackgroundMethodInfluentialYu, Y., Zhou, Z., Jiang, J., Yin, E., Liu, K., Wang, J., Liu, Y., & Hu, D. (2016) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2016.1267450 · Cited by 18
“…accurate detection and recognition of brain patterns associated with MI in multichannel EEG data, one of the most successful approaches is Common Spatial Patterns (CSP), which worked well for discriminating between two classes (Blankertz, Tomioka, Lemm, Kawanabe, & Müller, 2008; Xu et al., 2013).”
BackgroundMethodOn robust parameter estimation in brain–computer interfacing
Samek, W., Nakajima, S., Kawanabe, M., & Müller, K. (2017) · Journal of Neural Engineering · doi:10.1088/1741-2552/aa8232 · Cited by 24
“Common Spatial Patterns (CSP) [38, 39] is a popular algorithm for optimizing spatial filters in motor imaginary BCIs.”
BackgroundMethodSelf-citationCommon Mode Patterns for Supervised Tensor Subspace Learning
Makantasis, K., Doulamis, A. D., Doulamis, N. D., & Voulodimos, A. S. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8682616 · Cited by 16
Pourali, H., & Omranpour, H. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118621 · Cited by 19
Fumanal-Idocin, J., Takáč, Z., Horanská, Ľ., Asmus, T. D. C., Dimuro, G. P., Vidaurre, C., Fernández, J., & Bustince, H. (2022) · Fuzzy Sets and Systems · doi:10.1016/j.fss.2022.10.003 · Cited by 16
“Another common step is the application of an optimized spatial filtering method such as common spatial patterns (CSP, [34, 35, 36, 37, 38]).”
MethodEEG feature selection for thought driven robots using evolutionary Algorithms
Amarasinghe, K., Sivils, P., & Manic, M. (2016) · Conference on Human System Interactions · doi:10.1109/hsi.2016.7529657 · Cited by 16
“Common Spatial Patterns were used as features in [18] and [19] in order to find the maximum variance in signals between multiple classes.”
MethodEvolutionary Algorithm Based Feature Optimization for Multi-Channel EEG Classification
Wang, Y., & Veluvolu, K. C. (2017) · Frontiers in Neuroscience · doi:10.3389/fnins.2017.00028 · Cited by 16
“Due to the volume conduction of skull and scalp, the signal generated by the cortex of interest may be distributed to a vicinity of the area on the scalp and picked up by surrounding electrodes with different amplitude (Blankertz et al., 2008).”
BackgroundConstraints and Adaptation of Closed-Loop Neuroprosthetics for Functional Restoration
Bauer, R. H., & Gharabaghi, A. (2017) · Frontiers in Neuroscience · doi:10.3389/fnins.2017.00111 · Cited by 18
“, pooled covariance estimation (Friedman, 1989), rejection of eigenvectors (Blankertz et al., 2008), shrinkage estimators (Beltrachini et al.”
Assessing the Depth of Cognitive Processing as the Basis for Potential User-State Adaptation
Nicolae, I.-E., Acqualagna, L., & Blankertz, B. (2017) · Frontiers in Neuroscience · doi:10.3389/fnins.2017.00548 · Cited by 22
“To enhance the discrimination of activity in the frequency band of interest, we performed SSD (Nikulin et al., 2011) and Common Spatial Pattern (CSP) (Blankertz et al., 2008) for the corresponding frequency bands.”
BackgroundMethodSelf-citationImproving Generalization Based on l1-Norm Regularization for EEG-Based Motor Imagery Classification
Zhao, Y., Han, J., Chen, Y., Sun, H., Chen, J., Ke, A., Han, Y. F., Zhang, P., Zhang, Y., Zhou, J., et al. (2018) · Frontiers in Neuroscience · doi:10.3389/fnins.2018.00272 · Cited by 17
“Wellknown CSP methods combined signals from multiple channels by amplifying the class disparity in the spatial domain by covariance analysis (Blankertz et al., 2007; Li et al., 2013).”
MethodEEG Sensorimotor Correlates of Speed During Forearm Passive Movements
Iwane, F., Lisi, G., & Morimoto, J. (2019) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2019.2934231 · Cited by 17
“75] s, as in the original algorithm [45].”
BackgroundMethodInfluentialSimar, C., Cebolla, A.-M., Chartier, G., Petieau, M., Bontempi, G., Berthoz, A., & Cheron, G. A. (2020) · Frontiers in Neuroscience · doi:10.3389/fnins.2020.588357 · Cited by 19
“…first determines discriminative spatial filters W by the joint diagonalization of the two covariance matrices (cid:54) ( 1 ) and ( 2 ) as follows (Blankertz et al., 2008; Barachant et al., 2010a): Subsequently, the n most discriminative spatial filters ( n being a parameter of the algorithm)…”
BackgroundGeorge, L., Marchal, M., Glondu, L., & Lécuyer, A. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-31401-8_12 · Cited by 16
Exploring gaze-motor imagery hybrid brain-computer interface design
O'Doherty, D., Meena, Y. K., Raza, H., Cecotti, H., & Prasad, G. (2014) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm.2014.6999180 · Cited by 22
“CSP is used as a spatial filtering method in discriminating different classes in brain response detection problems [19]–[21].”
MethodYang, H., Guan, C., Wang, C. C., & Ang, K. K. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6637838 · Cited by 16
“We compare the classification results of our proposed method of using 22 selected LAD channels with several existing methods, which include: filter bank common spatial pattern (FBCSP)-based EEG signal classification method [11], filter bank with power features (FBPF), common spatial pattern (CSP) method [12, 13] and s…”
MethodTu, Y., Hung, Y. S., Hu, L., Huang, G., Hu, Y. S., & Zhang, Z. (2014) · Clinical Neurophysiology · doi:10.1016/j.clinph.2014.03.028 · Cited by 17
“Blankertz et al. (2008) showed that CSP could serve as a powerful technique in BCI for discriminating EEG signals with different mental intentions, and since then CSP has gradually gained popularity in BCI research.”
BackgroundMethodInfluentialEEG denoising with a recurrent quantum neural network for a brain-computer interface
Gandhi, V., Arora, V., Behera, L., Prasad, G., Coyle, D., & McGinnity, T. M. (2011) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2011.6033413 · Cited by 19
“It is quite wellknown that there are always subject dependent parameters [36], [37] and hence it seems as of now that the results can be greatly improved by selecting more suitable parameters.”
BackgroundA Brain Computer Interface methodology based on a visual P300 paradigm
Pires, G., & Nunes, U. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5354384 · Cited by 17
“Some variants of CSP were also already proposed for the multiclass problem [18], [19], [20].”
BackgroundTeam PhyPA: Brain-Computer Interfacing for Everyday Human-Computer Interaction
Zander, T. O., & Krol, L. R. (2017) · Periodica Polytechnica Electrical Engineering and Computer Science · doi:10.3311/ppee.10435 · Cited by 22
“This performance is in line with other, partially later conducted, motor imagery experiments [13, 16, 17].”
ResultBlair, C. D., Capozzi, F., & Ristic, J. (2017) · Vision · doi:10.3390/vision1030019 · Cited by 18
Togha, M. M., Salehi, M. R., & Abiri, E. (2019) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2019.01.008 · Cited by 18
Tariq, M., Trivailo, P. M., & Simić, M. (2019) · Procedia Computer Science · doi:10.1016/j.procs.2019.09.256 · Cited by 18
Musluoglu, C. A., & Bertrand, A. (2023) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2023.3275272 · Cited by 20
“In practical settings, the expectation operators in the objective and constraint functions of (3) are usually approximated using sample averages [55], [56], [57], [58], [59].”
BackgroundUsing chemosensory-induced EEG signals to identify patients with de novo Parkinson’s disease
Olcay, B. O., Onay, F., Öztürk, G. A., Öniz, A., Özgören, M., Hummel, T. R., & Güdücü, Ç. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105438 · Cited by 17
Liu, X., Sun, Y. Z., Zheng, D., & Na, R. (2023) · Measurement · doi:10.1016/j.measurement.2023.113673 · Cited by 14
Moufassih, M., Tarahi, O., Hamou, S., Agounad, S., & Azami, H. I. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17118-7 · Cited by 17
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.