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 401–500 of 1,002
Vavoulis, A., Figueiredo, P., & Vourvopoulos, A. (2023) · Signals · doi:10.3390/signals4010004 · Cited by 67
A hybrid brain-computer interface control strategy in a virtual environment
Su, Y., Qi, Y., Luo, J., Wu, B., Yang, F., Yi, L., Zhuang, Y., Zheng, X., & Chen, W. (2011) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/jzus.c1000208 · Cited by 55
ℓ1-penalized linear mixed-effects models for high dimensional data with application to BCI
Fazli, S., Danóczy, M., Schelldorfer, J., & Müller, K. (2011) · NeuroImage · doi:10.1016/j.neuroimage.2011.03.061 · Cited by 57
“Modern machine learning techniques have enabled the BCI-user to operate a high-speed BCI system with no training on the user side and short calibration sessions for training data generation (Cheng et al., 2002; Wang et al., 2006; Blankertz et al., 2008; Parra et al., 2008; Thomas et al., 2009), as compared to classica…”
BackgroundMethodEEG feature descriptors and discriminant analysis under Riemannian Manifold perspective
Nguyen, C. H., & Artemiadis, P. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.10.013 · Cited by 54
“Among the linear transform techniques, Common Spatial Pattern CSP) [28,29] has been successfully used in BCI contest.”
MethodBrain‐Computer Interfaces With Multi‐Sensory Feedback for Stroke Rehabilitation: A Case Study
Irimia, D.-C., Cho, W., Ortner, R., Allison, B. Z., Ignat, B. E., Edlinger, G., & Guger, C. (2017) · Artificial Organs · doi:10.1111/aor.13054 · Cited by 55
“Then, common spatial patterns (CSP) (8) were applied to transform the data to a new matrix with minimal variance of one class and maximal variance of the other class.”
MethodInfluentialComparison of EEG measurement of upper limb movement in motor imagery training system
Suwannarat, A., Pan-ngum, S., & Israsena, P. (2018) · BioMedical Engineering OnLine · doi:10.1186/s12938-018-0534-0 · Cited by 55
Delisle-Rodríguez, D., Cardoso, V. F., Gurve, D., Loterio, F. A., Romero-Laiseca, M. A., Krishnan, S., & Bastos-Filho, T. (2019) · Journal of Neural Engineering · doi:10.1088/1741-2552/ab08c8 · Cited by 52
“Although previous works have reported promising results using BCIs based on bandpass filter of Butterworth from 8 to 30 Hz for motor imagery recognition [47, 66], low performance (average Kappa = 65.”
BackgroundMethodResultInfluentialA review of EEG features for emotion recognition
Minjing, Y. U., Zhang, D., Zhang, G., Zhao, G., Liu, Y., Han, Y., & Guo, C. H. E. N. (2019) · Scientia Sinica Informationis · doi:10.1360/n112018-00337 · Cited by 60
Tang, F., Fan, M., & Tiňo, P. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2978514 · Cited by 60
“This is corroborated by the most commonly used common spatial pattern (CSP) [4] algorithm, which is completely based on the estimation of the spatial covariance matrices, where spatial filters can be derived to enhance the class separability.”
MethodDecoding Intention at Sensorimotor Timescales
Salvaris, M., & Haggard, P. (2014) · PLoS ONE · doi:10.1371/journal.pone.0085100 · Cited by 52
“Spatial filtering is an important part of detecting neuromodulatory changes over the motor cortex [23].”
BackgroundMethodResultInfluentialGwon, D., & Ahn, M. (2021) · NeuroImage · doi:10.1016/j.neuroimage.2021.118403 · Cited by 54
“We also used a Common Spatial Pattern (CSP), which is known to emonstrate good performance ( Blankertz et al., 2008 ), in classifying otor imagery EEG. CSP was used in the original paper ( Cho et al., 017 ) that published dataset 1 and was widely employed in various otor imagery studies ( Fu et…”
MethodJu, C., & Guan, C. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3307470 · Cited by 74
Yang, Y., Bloch, I., Chevallier, S., & Wiart, J. (2016) · Cognitive Computation · doi:10.1007/s12559-015-9379-z · Cited by 49
“The classical solution is to use a multi-channel recording and spatial filtering algorithms, such as common spatial patterns (CSP), to improve the SNR and extract discriminative features from overlapping signals [7].”
MethodEmbodied neurofeedback with an anthropomorphic robotic hand
Braun, N., Emkes, R., Thorne, J. D., & Debener, S. (2016) · Scientific Reports · doi:10.1038/srep37696 · Cited by 48
A Stimulus-Independent Hybrid BCI Based on Motor Imagery and Somatosensory Attentional Orientation
Yao, L., Sheng, X., Zhang, D., Jiang, N., Mrachacz‐Kersting, N., Zhu, X., & Farina, D. (2017) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2017.2684084 · Cited by 50
Zarubin, G., Gundlach, C., Nikulin, V. V., Villringer, A., & Bogdan, M. (2020) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2020.00366 · Cited by 48
“…established and efficient methods for extraction of modulated brain activity is the Common Spatial Patterns (CSP) approach, which was introduced in (Blankertz et al., 2008) for single-trial analysis and is commonly used in brain-computer interface (BCI) applications to differentiate between…”
MethodMachine learning accelerates quantum mechanics predictions of molecular crystals
Han, Y., Ali, I., Wang, Z., Cai, J., Wu, S., Tang, J., Zhang, L., Ren, J., Xiao, R., Lu, Q., et al. (2021) · Physics Reports · doi:10.1016/j.physrep.2021.08.002 · Cited by 53
Zhong, X.-C., Wang, Q., Liu, D., Liao, J.-X., Yang, R., Duan, S., Ding, G., & Sun, J. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107235 · Cited by 55
A practical guide to EEG hyperscanning in joint action research: from motivation to implementation
Zamm, A., Loehr, J. D., Vesper, C., Konvalinka, I., Kappel, S. L., Heggli, O. A., Vuust, P., & Keller, P. E. (2024) · Social Cognitive and Affective Neuroscience · doi:10.1093/scan/nsae026 · Cited by 58
“These spatial patterns could then be used to create ROIs or spatial filters (see Blankertz et al ., 2007, for further information about spatial filtering) that can be applied when analyzing data from the joint task.”
MethodLiu, Y., Huang, S., & Huang, Y.-D. (2017) · Sensors · doi:10.3390/s17071557 · Cited by 50
“However, this decomposition relies on at least two EEG channels; otherwise the spatial covariance matrix of CSP cannot be decomposed (see [55] for detailed formulation).”
BackgroundGurve, D., Delisle-Rodríguez, D., Romero-Laiseca, M. A., Cardoso, V. F., Loterio, F. A., Bastos-Filho, T., & Krishnan, S. (2019) · Journal of Neural Engineering · doi:10.1088/1741-2552/ab4dba · Cited by 48
“…pattern (CSP) algorithm [11 – 15] is an effective method to discriminate inter-class separability for BCI applications, but several parameters need to be specified (e.g. the frequency band, the time interval of the stimuli, and the subset of CSP filters) to achieve the optimal performance [13].”
MethodFatigue driving detection based on electrooculography: a review
Tian, Y., & Cao, J. (2021) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-021-00575-1 · Cited by 50
“Different from the approach methods mentioned above, traditional linear spatial filters include principal component analysis (PCA), independent component analysis (ICA) [61], common spatial patterns for BCI applications [62] or beamforming methods for source localization [63].”
MethodRithwik, P., Benzy, V. K., & Vinod, A. P. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103241 · Cited by 51
Peng, P., Xie, L., Zhang, K., Zhang, J., Yang, L., & Wei, H. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.103555 · Cited by 57
Jeong, J.-H., Cho, J.-H., Lee, B.-H., & Lee, S. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2022.3211694 · Cited by 48
“To compare the PVC performance between the baseline methods and the proposed deep neurolinguistic learning, we implemented the machine learning methods presented in [42] and [43] and the deep learning models in [44], [45], and [46].”
MethodTransfer learning promotes acquisition of individual BCI skills
Kumar, S., Alawieh, H., Rácz, F. S., Fakhreddine, R., & Millán, J. D. R. (2024) · PNAS Nexus · doi:10.1093/pnasnexus/pgae076 · Cited by 62
“Having demonstrated transfer learning with Riemannian MDM decoders, we also investigated the adaptability of the GR framework to common spatial pattern-based (CSP) classifiers, which is widely used in MI – BCIs (35, 36).”
MethodInfluentialThought-based row-column scanning communication board for individuals with cerebral palsy
Scherer, R., Billinger, M., Wagner, J., Schwarz, A., Hettich, D. T., Bolinger, E., García, M. L., Navarro, J. J., & Müller-Putz, G. (2015) · Annals of Physical and Rehabilitation Medicine · doi:10.1016/j.rehab.2014.11.005 · Cited by 52
Time-series discrimination using feature relevance analysis in motor imagery classification
Álvarez-Meza, A. M., Velasquez-Martinez, L. F., & Castellanos-Dominguez, G. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.07.077 · Cited by 47
The LDA beamformer: Optimal estimation of ERP source time series using linear discriminant analysis
Treder, M. S., Porbadnigk, A. K., Avarvand, F. S., Müller, K., & Blankertz, B. (2016) · NeuroImage · doi:10.1016/j.neuroimage.2016.01.019 · Cited by 51
“By applying a spatial filter w, estimates s of cortical sources can be formed as a linear combination of sensor data (Parra et al., 2005; Tomioka and Müller, 2010; Müller et al., 2003; Blankertz et al., 2008; Kawanabe et al., 2014; Blankertz et al., 2011; Gross and Ioannides, 1999; Lemm et al., 2011):”
InfluentialSelf-citationMultiband tangent space mapping and feature selection for classification of EEG during motor imagery
Islam, M. R., Tanaka, T., & Molla, M. K. I. (2018) · Journal of Neural Engineering · doi:10.1088/1741-2552/aac313 · Cited by 53
“In MI-based BCI, several studies used the frequency band within 7 to 30 Hz for effective use of the CSP algorithm [44 – 46].”
MethodAcross-subject offline decoding of motor imagery from MEG and EEG
Halme, H.-L., & Parkkonen, L. T. (2018) · Scientific Reports · doi:10.1038/s41598-018-28295-z · Cited by 52
Feature subset and time segment selection for the classification of EEG data based motor imagery
Wang, J., Feng, Z., Ren, X., Lü, N., Luo, J., & Sun, L. (2020) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2020.102026 · Cited by 47
Robust learning from corrupted EEG with dynamic spatial filtering
Banville, H. J., Wood, S. U. N., Aimone, C., Engemann, D. A., & Gramfort, A. (2022) · NeuroImage · doi:10.1016/j.neuroimage.2022.118994 · Cited by 57
Adaptive Methods in BCI Research - An Introductory Tutorial
Schlögl, A., Vidaurre, C., & Müller, K. (2009) · The frontiers collection · doi:10.1007/978-3-642-02091-9_18 · Cited by 60
“Bandpower [23, 25, 27], AR-based spectra in [18], slow cortical potentials by [2], or CSP combined with Bandpower [ 4 , 6, 7, 16]).”
BackgroundMethodInfluentialFirst Demonstration of a Musical Emotion BCI
Makeig, S., Leslie, G. A., Mullen, T. R., Sarma, D., Bigdely-Shamlo, N., & Kothe, C. A. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24571-8_61 · Cited by 52
“So far, the nascent field of BCI systems based on EEG signals has focused on providing subjects with profound loss of motor control with the ability to perform binary or smooth prosthetic device control [13] and to communicate by spelling-out words [15] or actuating musical tones [10].”
BackgroundMethodCSP patches: an ensemble of optimized spatial filters. An evaluation study
Sannelli, C., Vidaurre, C., Müller, K., & Blankertz, B. (2011) · Journal of Neural Engineering · doi:10.1088/1741-2560/8/2/025012 · Cited by 47
“CSP is a discriminative algorithm (see [4]) which determines spatial filters W from band-pass filtered EEG data X such that the difference between the variances of the filtered data X CSP = X · W for the two classes is maximized.”
BackgroundInfluentialSelf-citationAdaptive Laplacian filtering for sensorimotor rhythm-based brain–computer interfaces
Lu, J., McFarland, D. J., & Wolpaw, J. R. (2012) · Journal of Neural Engineering · doi:10.1088/1741-2560/10/1/016002 · Cited by 50
“As spatial filtering, with CSP, we used m pairs of the most discriminative filters, where m is determined by fivefold CV (Blankertz et al 2008).”
MethodCognitive workload modulation through degraded visual stimuli: a single-trial EEG study
Yu, K., Prasad, I., Mir, H., Thakor, N. V., & Al-Nashash, H. A. (2015) · Journal of Neural Engineering · doi:10.1088/1741-2560/12/4/046020 · Cited by 54
“The CSP method is found to be very successful in motor imagery applications by targeting rhythmic event-related de-synchronization and eventrelated synchronization signals [39].”
MethodHsu, W.-C., Lin, L., Chou, C.-W., Hsiao, Y.-T., & Liu, Y.-H. (2016) · International Journal of Fuzzy Systems · doi:10.1007/s40815-016-0259-9 · Cited by 53
“Ifm is too small, the extracted features will not carry discriminating information; on the other hand, the overfitting problem would occur ifm is too large [49], which should be determined experimentally.”
BackgroundEmotional state detection based on common spatial patterns of EEG
Başar, M. D., Duru, A. D., & Akan, A. (2019) · Signal Image and Video Processing · doi:10.1007/s11760-019-01580-8 · Cited by 46
Optimization of preprocessing stage in EEG based BCI systems in terms of accuracy and timing cost
Dağdevır, E., & Tokmakçı, M. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.102548 · Cited by 55
Mohamed, A.-K., Marwala, T., & John, L. R. (2011) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.2011.6091552 · Cited by 48
“om a limited number of EEG electrodes (even with high resolution EEG e.g 128 electrodes) [1, 18]. This results in a considerable mixing of information sources from all over the head at each electrode [1, 17, 19]. However, clinical research has increased the understanding of EEG signals and numerous studies have shown…”
BackgroundBauer, R. H., & Gharabaghi, A. (2015) · Frontiers in Behavioral Neuroscience · doi:10.3389/fnbeh.2015.00021 · Cited by 47
“By contrast, during assistive BCI, the feature weights are calculated so as to allow maximal separation (Blankertz et al., 2008; Theodoridis and Koutroumbas, 2009) and the classification output is used for communication or robotic control (Wolpaw et al., 2002).”
Brain–computer interface treatment for gait rehabilitation in stroke patients
Sebastián-Romagosa, M., Cho, W., Ortner, R., Sieghartsleitner, S., von Oertzen, T. J., Kamada, K., Laureys, S., Allison, B. Z., & Guger, C. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2023.1256077 · Cited by 54
EEG motor imagery decoding: a framework for comparative analysis with channel attention mechanisms
Wimpff, M., Gizzi, L., Zerfowski, J., & Yang, B. (2024) · Journal of Neural Engineering · doi:10.1088/1741-2552/ad48b9 · Cited by 62
“Hence, most of the experts still rely on classical algorithms like CSP [23, 24] or on the somewhat out-dated but well explored shallow architectures EEGNet or ShallowNet.”
Regularized common spatial patterns with subject-to-subject transfer of EEG signals
Cheng, M., Lu, Z., & Wang, H. (2016) · Cognitive Neurodynamics · doi:10.1007/s11571-016-9417-x · Cited by 48
“In order to obtain satisfied BCI performance, it is prescriptively required to collect approximately 40 training trials per class, as suggested in (Blankertz et al. 2008a).”
BackgroundMethodHerman, P. A., Prasad, G., & McGinnity, T. M. (2016) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2016.2637934 · Cited by 48
Park, S.-H., & Lee, S.-G. (2017) · IEEE Sensors Journal · doi:10.1109/jsen.2017.2671842 · Cited by 46
“Technologies that utilize BCI have attracted an increasing amount of attention in areas as diverse as medicine and engineering [3].”
BackgroundDeep recurrent spatio-temporal neural network for motor imagery based BCI
Ko, W., Yoon, J. S., Kang, E., Jun, E., Choi, J.-S., & Suk, H. (2018) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/iww-bci.2018.8311535 · Cited by 44
“Methodological variations can be summarized as defining different frequency band(s), either manual specification or datadriven, regularized versions of the standard CSP, etc. Unlike the previous work that mostly concerned their framework of motor imagery classification in feature extraction and classifier learning, se…”
BackgroundInfluentialBian, Y., Qi, H., Li, Z., Ming, D., Guo, T., & Fu, X. (2018) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2018.03.018 · Cited by 47
Experimenters' Influence on Mental-Imagery based Brain-Computer Interface User Training
Pillette, L., Roc, A., N’Kaoua, B., & Lotte, F. (2021) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2021.102603 · Cited by 53
Malan, N. S., & Sharma, S. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.102550 · Cited by 51
Jiang, X., Gu, X., Xu, K., Ren, H., & Chen, W. (2019) · IEEE Access · doi:10.1109/access.2019.2953535 · Cited by 47
“This algorithm has proven to be a powerful tool in EEG-based BCIs, which reduces the high feature dimensionality for classification assignments [49].”
MethodRotaru, I., Geirnaert, S., Heintz, N., de Ryck, I. V., Bertrand, A., & Francart, T. (2024) · Journal of Neural Engineering · doi:10.1088/1741-2552/ad2214 · Cited by 53
“Thus, following the conventional CSP recipes from the BCI literature (Blankertz et al 2008), we chose to train a moderate number of K = 6 CSP filters per frequency band.”
InfluentialZhang, R., Xu, P., Liu, T., Zhang, Y., Guo, L., Li, P., & Yao, D. (2013) · Computational and Mathematical Methods in Medicine · doi:10.1155/2013/591216 · Cited by 43
“Feature extraction and classification algorithms play important roles for the performance of ERD/ERS based BCI, and there are various methods have been proposed to extract ERD/ERS related features [11, 12], such as the laplacian method [13], autoregressive spectral analysis [14], common spatial pattern (CSP) [15], dis…”
MethodAPPLICATION OF QUANTUM-BEHAVED PARTICLE SWARM OPTIMIZATION TO MOTOR IMAGERY EEG CLASSIFICATION
Hsu, W. (2013) · International Journal of Neural Systems · doi:10.1142/s0129065713500263 · Cited by 43
Cho, H., Ahn, M., Kim, K., & Jun, S. C. (2015) · Journal of Neural Engineering · doi:10.1088/1741-2560/12/6/066009 · Cited by 52
“The first optimization problem (left of Equation (4)) comes to the CSP method [43].”
MethodUser-customized brain computer interfaces using Bayesian optimization
Bashashati, H., Ward, R. K., & Bashashati, A. (2016) · Journal of Neural Engineering · doi:10.1088/1741-2560/13/2/026001 · Cited by 49
“Common spatial patterns (CSPs) [8, 30] is used for spatial filtering.”
MethodCortical and subcortical mechanisms of brain‐machine interfaces
Marchesotti, S., Martuzzi, R., Schurger, A., Blefari, M. L., Millán, J. D. R., Bleuler, H., & Blanke, O. (2017) · Human Brain Mapping · doi:10.1002/hbm.23566 · Cited by 44
“The data were then used to compute a set of spatial filters (common spatial patterns [CSP], [Blankertz et al., 2008; Guger et al., 2000]) as well as the coefficients for a binary linear classifier able to discriminate between the two imagined directions.”
BackgroundMethodInfluentialBinias, B., Myszor, D., & Cyran, K. A. (2018) · Computational Intelligence and Neuroscience · doi:10.1155/2018/2703513 · Cited by 50
“A logarithm of the variance of signal’s amplitude is a very common feature used for the description of EEG signal’s power [10, 25].”
BackgroundMethodInfluentialAppriou, A., Cichocki, A. S., & Lotte, F. (2018) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3170427.3188617 · Cited by 51
“As baseline, we use two standard methods for workload classification: 1) Common Spatial Pattern (CSP) spatial filters with a Linear Discriminant Analysis (LDA) classifier [3] and 2) the Filter Bank CSP (FBCSP) [1], which is an improved variant of the CSP.”
MethodBrain–Computer Interface Contributions to Neuroergonomics
Lotte, F., & Roy, R. N. (2018) · Elsevier eBooks · doi:10.1016/b978-0-12-811926-6.00007-5 · Cited by 53
Nierula, B., Spanlang, B., Martini, M., Borrell, M., Nikulin, V. V., & Sanchez-Vives, M. V. (2019) · The Journal of Physiology · doi:10.1113/jp278167 · Cited by 53
“No ICA was applied because prior application of another spatial filtering could lead to possible deterioration in the performance of CSP (Blankertz et al., 2008; Nierula et al., 2013).”
MethodFundamentals of EEG Signal Processing
Sanei, S., & Chambers, J. A. (2007) · Wiley eBooks · doi:10.1002/9780470511923.ch2 · Cited by 53
Wang, H., Tang, C., Xu, T., Li, T., Xu, L., Yue, H., Chen, P., Li, J., & Bezerianos, A. (2020) · IEEE Access · doi:10.1109/access.2020.2992631 · Cited by 46
“In this paper, the first four pairs and the last four pairs of eigenvalues in the projection matrix were selected, and CSP filters are used for spatial filtering to form eight eigenvalues in each trial of the training dataset [30].”
MethodComparison of subject-independent and subject-specific EEG-based BCI using LDA and SVM classifiers
Santos, E., San-Martin, R., & Fraga, F. J. (2023) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-023-02769-3 · Cited by 51
“CSP tries to attain the best discrimination for BCI systems based on the power distribution over the scalp [11, 20], considering variation in the bandpass power of the EEG signal.”
BackgroundAutoregressive model in the Lp norm space for EEG analysis
Li, P., Wang, X., Li, F., Zhang, R., Ma, T., Peng, Y., Lei, X., Tian, Y., Guo, D., Liu, T., et al. (2014) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2014.11.007 · Cited by 42
Rivet, B., & Souloumiac, A. (2012) · Signal Processing · doi:10.1016/j.sigpro.2012.07.019 · Cited by 44
“3(b)). provide very good performance on the spatial filters estimate compared to classical CSP or FastICA, even with very confusing configurations.”
BackgroundMethodInfluentialUnsupervised classification of operator workload from brain signals
Schultze-Kraft, M., Dähne, S., Gugler, M. F., Curio, G., & Blankertz, B. (2016) · Journal of Neural Engineering · doi:10.1088/1741-2560/13/3/036008 · Cited by 46
“The corresponding spatial-filter-based model SFCla (spatial filtering and classification) uses the common spatial patterns (CSPs) algorithm (Blankertz et al 2008) to train the spatial filters and LDA to combine the resulting logvar features.”
MethodSelf-citationComparing Features for Classification of MEG Responses to Motor Imagery
Halme, H.-L., & Parkkonen, L. T. (2016) · PLoS ONE · doi:10.1371/journal.pone.0168766 · Cited by 47
Enhanced Motor Imagery-Based BCI Performance via Tactile Stimulation on Unilateral Hand
Shu, X., Yao, L., Sheng, X., Zhang, D., & Zhu, X. (2017) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2017.00585 · Cited by 46
Improving Brain–Computer Interfaces Using Independent Component Analysis
Wang, Y., & Jung, T. (2012) · Biological and medical physics series · doi:10.1007/978-3-642-29746-5_4 · Cited by 47
“2) identificati cation of the c steps of the ough linearly elated EEG s adopted in re thod [41], the ssfully applie”
BackgroundBenchmarking Brain-Computer Interfaces Outside the Laboratory: The Cybathlon 2016
Novak, D., Sigrist, R., Gerig, N. J., Wyss, D., Bauer, R., Götz, U., & Riener, R. (2018) · Frontiers in Neuroscience · doi:10.3389/fnins.2017.00756 · Cited by 41
“Thus, EEG signals are almost always filtered to remove noise and artifacts prior to further analysis (Ramoser et al., 2000; Blankertz et al., 2008).”
BackgroundEffect of power feature covariance shift on BCI spatial-filtering techniques: A comparative study
Miladinović, A., Ajčević, M., Jarmolowska, J., Marušič, U., Colussi, M., Silveri, G., Battaglini, P. P., & Accardo, A. (2020) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2020.105808 · Cited by 46
Yang, H., Guan, C., Chua, K. S. G., Chok, S. S., Wang, C. C., Phua, K. S., Tang, C. K. Y., & Ang, K. K. (2014) · Journal of Neural Engineering · doi:10.1088/1741-2560/11/3/035016 · Cited by 44
“While previous studies have documented comparable accuracies of motor imagery of hand/arm classification for healthy and stroke patients [29, 31, 32], our findings imply that obtaining similar classification accuracies is possible for the detection of MI-SW and MI-Ton for healthy subjects, despite the facts that perfo…”
MethodResultSingle-trial analysis of the neural correlates of speech quality perception
Porbadnigk, A. K., Treder, M. S., Blankertz, B., Voigt‐Antons, J., Schleicher, R., Möller, S., Curio, G., & Müller, K. (2013) · Journal of Neural Engineering · doi:10.1088/1741-2560/10/5/056003 · Cited by 50
“Such a setting necessitates robust machine learning methods [4, 5], which can be adapted from the field of EEG-based brain–computer interfaces7 (BCIs, [8, 9]).”
BackgroundSelf-citationTam, W.-K., Ke, Z., & Tong, R. K. (2011) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.2011.6091566 · Cited by 46
Navarro-Sune, X., Hudson, A. L., Fallani, F. D. V., Martinerie, J., Witon, A., Pouget, P., Raux, M., Similowski, T., & Chavez, M. (2017) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2016.2592820 · Cited by 41
“A standard procedure to extract features in EEG epoched data ( X i ) by CSP consists of computation of the log-variances of projected X i on the spatial filters [28].”
MethodInfluentialA multivariate empirical mode decomposition based filtering for subject independent BCI
Gaur, P., Pachori, R. B., Wang, H., & Prasad, G. (2016) · Irish Signals and Systems Conference · doi:10.1109/issc.2016.7528480 · Cited by 42
“As discussed in introduction, the CSP algorithm has shown promising results in calculating spatial filters for detecting (ERD/ERS) [17],[11].”
BackgroundMethodInvestigating EEG Patterns for Dual-Stimuli Induced Human Fear Emotional State
Masood, N., & Farooq, H. (2019) · Sensors · doi:10.3390/s19030522 · Cited by 44
“…as input to the common spatial pattern (CSP) algorithm, a technique that is widely used to obtain spatial filters for classification of EEG data [ 42 , 43 ]. work, we used band power features that are provided as input to the common spatial pattern (CSP) algorithm, a technique that is widely…”
MethodEnhancing sensorimotor BCI performance with assistive afferent activity: An online evaluation
Vidaurre, C., Ramos‐Murguialday, A., Haufe, S., Gómez, M., Müller, K. R., & Nikulin, V. V. (2019) · NeuroImage · doi:10.1016/j.neuroimage.2019.05.074 · Cited by 44
Multi-View Multi-Scale Optimization of Feature Representation for EEG Classification Improvement
Jiao, Y., Zhou, T., Yao, L., Zhou, G., Wang, X., & Zhang, Y. (2020) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2020.3040984 · Cited by 44
“In particular, common spatial pattern (CSP) is most widely applied to SMR feature extraction [15].”
BackgroundMethodGao, C., Liu, W., & Yang, X. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.08.024 · Cited by 42
Shi, J., Tang, J., Lu, Z., Zhang, R., Yang, J., Guo, Q., & Zhang, D. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106401 · Cited by 46
Elnady, A. M., Zhang, X., Xiao, Z. G., Yong, X., Randhawa, B. K., Boyd, L. A., & Menon, C. (2015) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2015.00168 · Cited by 50
“In this study, we used the common spatial pattern (CSP) algorithm (Ramoser et al., 2000; Blankertz et al., 2008) to extract features from the EEG signals.”
MethodGonzalez, A., Nambu, I., Hokari, H., & Wada, Y. (2014) · The Scientific World JOURNAL · doi:10.1155/2014/350270 · Cited by 44
“There are also algorithms that employ methods based on Principal Component Analysis (PCA) to extract spatial features [6, 11, 12], but these typically disregard channel selection and employ all the channels available to identify the most discriminative spatial information.”
MethodA BCI System Based on Somatosensory Attentional Orientation
Yao, L., Sheng, X., Zhang, D., Jiang, N., Farina, D., & Zhu, X. (2016) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2016.2572226 · Cited by 43
“The spatial filters were determined with the Common Spatial Pattern (CSP) procedure, which has been extensively validated for BCI [36], [37].”
MethodAlimardani, F., Boostani, R., & Blankertz, B. (2017) · Neural Networks · doi:10.1016/j.neunet.2017.02.014 · Cited by 41
Self-citationBosse, S., Acqualagna, L., Samek, W., Porbadnigk, A. K., Curio, G., Blankertz, B., Müller, K., & Wiegand, T. (2017) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2694807 · Cited by 45
“Reference [4] studies the detection of perceived quality degradation in images using electroencephalography (EEG) [7] and common spatial patterns (CSP) [8] for dimensionality reduction.”
BackgroundInfluentialSelf-citationHossain, I., Khosravi, A., Hettiarachchi, I. T., & Nahavandi, S. (2018) · Computational Intelligence and Neuroscience · doi:10.1155/2018/6323414 · Cited by 42
“CSP is used for feature extraction combined with LDA classifier since this combination is very successful for MI-based BCI [16, 46].”
MethodTaheri, S., Ezoji, M., & Sakhaei, S. M. (2020) · SN Applied Sciences · doi:10.1007/s42452-020-2378-z · Cited by 48
A novel multi-scale convolutional neural network for motor imagery classification
Riyad, M., Khalil, M., & Adib, A. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.102747 · Cited by 39
Gaur, P., Chowdhury, A., McCreadie, K. A., Pachori, R. B., & Wang, H. (2021) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2021.3099988 · Cited by 44
“To obtain effective discrimination, CSP analysis is applied to band-pass filtered EEG signals [20] and then the co-variance matrix is obtained [21], [22].”
MethodLearning discriminative patterns for self-paced EEG-based motor imagery detection
Ang, K. K. (2012) · Frontiers in Neuroscience · doi:10.3389/fnins.2012.00007 · Cited by 50
“At the beginning of each task, a visual cue was displayed in a computer screen to the subject who then started to perform a motor imagery task accordingly for 4 s.”
BackgroundMethodInfluentialZhang, H., Zhu, Y., Maniyeri, J., & Guan, C. (2014) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2014.6944250 · Cited by 48
“The minimization can be solved using a generalized eigen value solution [11].”
BackgroundMethodHwang, J., Park, S., & Chi, J. (2023) · Electronics · doi:10.3390/electronics12051186 · Cited by 48
Brunner, C., Billinger, M., Vidaurre, C., & Neuper, C. (2011) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-011-0828-x · Cited by 39
pySPACE—a signal processing and classification environment in Python
Krell, M. M., Straube, S., Seeland, A., Wöhrle, H., Teiwes, J., Metzen, J. H., Kirchner, E. A., & Kirchner, F. (2013) · Frontiers in Neuroinformatics · doi:10.3389/fninf.2013.00040 · Cited by 51
“…classes Standard and Target , is to investigate the effect of different spatial filters, i.e., ICA (Hyvärinen, 1999), PCA (Abdi and Williams, 2010), xDAWN (Rivet et al., 2009), and CSP (Blankertz et al., 2008), on the classification performance, or whether one should not use any spatial filter at all.”
BackgroundA clinical evaluation of non-invasive motor imagery-based brain-computer interface in stroke
Ang, 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.2008.4650130 · Cited by 43
“To the best of our knowledge, there exists only one study performed on BCI-naive healthy subjects [ 14 ], and a limited number performed on stroke patients operating MI-BCI [11],[15],[16].”
BackgroundL1 Norm based common spatial patterns decomposition for scalp EEG BCI
Li, P., Xu, P., Zhang, R., Guo, L., & Yao, D. (2013) · BioMedical Engineering OnLine · doi:10.1186/1475-925x-12-77 · Cited by 43
“L2 Norm based CSP The basic idea of CSP is to find a group of spatial filters that maximize the variance of band-pass filtered EEG signals from one class [20,21], while the variance from the other”
Background
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.