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 901–1,000 of 1,002
The Convergence of AI and BCIs
Jaber, W., Jaber, H. A. H., Jaber, R. A., & Saleh, Z. S. (2023) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-0368-9.ch006 · Cited by 19
Measuring neuronal avalanches to inform brain-computer interfaces
Corsi, M., Sorrentino, P., Schwartz, D., George, N., Gollo, L. L., Chevallier, S., Hugueville, L., Kahn, A. E., Dupont, S., Bassett, D. S., et al. (2023) · iScience · doi:10.1016/j.isci.2023.108734 · Cited by 21
Rácz, F. S., Kumar, S., Kaposzta, Z., Alawieh, H., Liu, D. H., Liu, R., Czoch, A., Mukli, P., & Millán, J. D. R. (2024) · Frontiers in Neuroscience · doi:10.3389/fnins.2024.1271831 · Cited by 16
Grabowska, A., Zabielski, J., & Senderecka, M. (2024) · Scientific Reports · doi:10.1038/s41598-024-58031-9 · Cited by 19
“Single-electrode EEG signals are characterized by a low signal-to-noise ratio, thus predictive analyses based on these signals entail a high risk of overfitting and low model sensitivity 59 .”
InfluentialAn Artificial Neural Network Based Robot Controller that Uses Rat’s Brain Signals
Mano, M., Capi, G., Tanaka, N., & Kawahara, S. (2013) · Robotics · doi:10.3390/robotics2020054 · Cited by 15
“Usually, in non-invasive BMI applications, this is addressed by increasing the number of electrodes and applying spatial and temporal filtering to the acquired multichannel signal [12,13].”
BackgroundRevealing the neural response to imperceptible peripheral flicker with machine learning
Porbadnigk, A. K., Scholler, S., Blankertz, B., Ritz, A., Born, M., Scholl, R., Müller, K. R., Curio, G., & Treder, M. S. (2011) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.2011.6090625 · Cited by 21
“For details on the use of these spatial filters in the context of single-trial EEG analysis, refer to [11].”
BackgroundMethodSelf-citationYang, Y., Chevallier, S., Wiart, J., & Isabelle Bloch, A. (2012) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2012.6346532 · Cited by 15
“visual related) common modulations at C3 and C4 [5].”
BackgroundClassification Scheme for Arm Motor Imagery
Tavakolan, M., Yong, X., Zhang, X., & Menon, C. (2016) · Journal of Medical and Biological Engineering · doi:10.1007/s40846-016-0102-7 · Cited by 17
“The classification scheme was performed using the CSP, FBCSP and band power methods [22, 26].”
MethodPrediction of Difficulty Levels in Video Games from Ongoing EEG
Naumann, L., Schultze-Kraft, M., Dähne, S., & Blankertz, B. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-57753-1_11 · Cited by 15
“A well-established approach for the extraction of EEG features in this setting is the Common Spatial Patterns (CSP) analysis [8] which finds spatial filters that maximize the power contrast between the two classes and has become one of the corner stones of sensorimotor rhythm based BCIs.”
BackgroundSelf-citationJalalvandi, M., Alam, N. R., Sharini, H., Hashemi, H., & Nadimi, M. (2021) · Journal of Biomedical Physics and Engineering · doi:10.31661/jbpe.v0i0.1051 · Cited by 18
Park, Y., & Chung, W. (2020) · IEEE Access · doi:10.1109/access.2020.2993318 · Cited by 16
“CSP produces output powers maximizing the difference between two MI-tasks by using optimal spatial filters that indirectly suppress the volume conduction effect [10].”
MethodZhou, L., Tao, X., He, F., Zhou, P., & Qi, H. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3066610 · Cited by 17
Amplitude-Phase Information Measurement on Riemannian Manifold for Motor Imagery-Based BCI
Huang, S., Cai, G., Wang, T., & Ma, T. (2021) · IEEE Signal Processing Letters · doi:10.1109/lsp.2021.3087099 · Cited by 18
Multi-Time and Multi-Band CSP Motor Imagery EEG Feature Classification Algorithm
Yang, J. L., Ma, Z., & Shen, T. (2021) · Applied Sciences · doi:10.3390/app112110294 · Cited by 14
Motor Imagery Classification for BCI Using Common Spatial Patterns and Feature Relevance Analysis
Velasquez-Martinez, L. F., Álvarez-Meza, A. M., & Castellanos-Dominguez, G. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-38622-0_38 · Cited by 15
“The CSP method is employed to analyze multi-channel EEG data based on recordings from two classes [5], producing spatial filters W ∈ RC×C , which project the original signal to a space where the differences in variances of two kinds of tasks can be maximized [1].”
MethodLiu, G., Huang, G., Meng, J., & Zhu, X. (2010) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2010.02.004 · Cited by 21
Shiratori, T., Tsubakida, H., Ishiyama, A., & Ono, Y. (2015) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/iww-bci.2015.7073053 · Cited by 20
Wang, H. (2011) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-011-0766-7 · Cited by 17
“Common spatial patterns (CSP) [4] is probably the most well-known technique of spatial filtering.”
BackgroundMethodInfluentialCommon Spatial Pattern Ensemble Classifier and Its Application in Brain-Computer Interface
Lei, X., Lei, L., Ping, P., Yang, Peng, Tiejun, ., L., De-Zhong, & -, Y. (2009) · Journal of Electronic Science and Technology · Cited by 14
Movement imagery classification in EMOTIV cap based system by Naïve Bayes
Stock, V. N., & Balbinot, A. (2016) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2016.7591711 · Cited by 15
“Feature Extraction Factors selected in this study for extraction were RMS value, variance and the CSP features obtained by (4) for both generated channels [11].”
BackgroundMethodInfluentialWasserstein Stationary Subspace Analysis
Kaltenstadler, S., Nakajima, S., Müller, K., & Samek, W. (2018) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2018.2873987 · Cited by 16
“Common spatial pattern (CSP) algorithms [33] are another class of subspace algorithms enjoying popularity in the EEG community.”
Abdallah, I. B., Bouteraa, Y., & Alotaibi, A. (2025) · Scientific Reports · doi:10.1038/s41598-025-24831-w · Cited by 26
“Electrode locations on the 10–20 system. tasks, as it efficiently extracts discriminative features from multi-channel EEG signals recorded over the motor cortex 31 .”
Minimizing Calibration Time for Brain Reading
Metzen, J. H., Kim, S. K., & Kirchner, E. A. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23123-0_37 · Cited by 16
“[5] for a discussion of why spatial filtering is an important step).”
BackgroundKo, W., Jeon, E., Yoon, J. S., & Suk, H. (2022) · Scientific Reports · doi:10.1038/s41598-022-08490-9 · Cited by 20
“Edelman et al. 1 used principal component analysis to classify complex motor imagery EEG tasks, whereas Blankertz et al. 3 and Ang et al. 4 both used a spatial filtering based method, i.e., common spatial pattern (CSP), for MI-based BCI.”
MethodVisual short‐term memory‐related EEG components in a virtual reality setup
Klotzsche, F., Gaebler, M., Villringer, A., Sommer, W., Nikulin, V. V., & Ohl, S. (2023) · Psychophysiology · doi:10.1111/psyp.14378 · Cited by 20
Cross-Subject Motor Imagery Decoding by Transfer Learning of Tactile ERD
Zhong, Y., Yao, L., Pan, G., & Wang, Y. (2024) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2024.3358491 · Cited by 18
“The performance of our calibration method has been verified using both the classical Common Spatial Pattern (CSP) algorithm [52] and one of the state-of-the-art deep transfer learning algorithms [38].”
MethodMultiview Contrastive Learning for Unsupervised Domain Adaptation in Brain–Computer Interfaces
Asgarian, S., Wang, Z., Wan, F., Wong, C. M., Liu, F., Mohsenzadeh, Y., Wang, B., & Ling, C. X. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3366285 · Cited by 18
“Furthermore, due to the nonstationary characteristic of EEG signals, the distributions of spatial and temporal features exhibit significant variations across different sessions and subjects [15], [16].”
BackgroundJin, C., Song, A. H., & Kim, S. (2024) · IEEE Access · doi:10.1109/access.2024.3406736 · Cited by 17
“CSP methods extract maximally discriminative band power across different classes and then employ classical machine learning algorithms for subsequent classifications [40], [41].”
MethodAhmadi, H., & Mesin, L. (2024) · IEEE Access · doi:10.1109/access.2024.3434654 · Cited by 17
“This optimization amplifies the distinctiveness of the signals associated with various MI tasks and significantly improves the spatial pattern recognition critical for accurate classification [32].”
BackgroundCardiac cycle modulates alpha and beta suppression during motor imagery
Lai, G., Landi, D., Vidaurre, C., Bhattacharya, J., & Ruiz, M. H. (2024) · Cerebral Cortex · doi:10.1093/cercor/bhae442 · Cited by 21
Dalhoumi, S., Dray, G., Montmain, J., Derosière, G., & Perrey, S. (2015) · International IEEE/EMBS Conference on Neural Engineering · doi:10.1109/ner.2015.7146576 · Cited by 14
“In this work, we used Common Spatial Patterns (CSP) algorithm for feature extraction [9], but our approach applies to other feature extraction techniques for EEG classification.”
MethodChoi, D., Ryu, Y., Lee, Y. B., & Lee, M. (2011) · BioMedical Engineering OnLine · doi:10.1186/1475-925x-10-91 · Cited by 16
Design of a brain-controlled robot arm system based on upper-limb movement imagery
Jeong, J.-H., Kim, K.-T., Yun, Y., & Lee, S. (2018) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/iww-bci.2018.8311514 · Cited by 14
Hossny, A. H., Moschuo, T., Osborne, G., Mitchell, L., & Lothian, N. (2018) · Social Network Analysis and Mining · doi:10.1007/s13278-018-0519-9 · Cited by 14
Zhao, X., Zhao, J., Cai, W., & Wu, S. (2019) · IEEE Access · doi:10.1109/access.2019.2913154 · Cited by 14
“Results in [19], [22], [23], [31] have shown that people”
BackgroundMOTANA: study protocol to investigate motor cerebral activity during a propofol sedation
Rimbert, S., Schmartz, D., Bougrain, L., Meistelman, C., Baumann, C., & Guerci, P. (2019) · Trials · doi:10.1186/s13063-019-3596-9 · Cited by 14
Fu, R., Wang, H., Bao, T., & Han, M. (2020) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2020.101998 · Cited by 14
Cho, Y., Kim, P., & Kim, K.-S. (2020) · IEEE Access · doi:10.1109/access.2020.3012741 · Cited by 14
“In addition, a previous study proportionally estimated the fingertip force of the index finger and the middle finger through a common spatial pattern (CSP)-basedmodel [22], [23].”
MethodGeorge, L., Marchal, M., Glondu, L., & Lécuyer, A. (2013) · Cited by 14
Fumanal-Idocin, J., Takáč, Z., Fernández, J., Sanz, J., Goyena, H., Lin, C., Wang, Y., & Bustince, H. (2021) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2021.3092824 · Cited by 16
Liu, C., Jin, J., Xu, R., Li, S., Zuo, C., Sun, H., Wang, X., & Cichocki, A. S. (2021) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac1d36 · Cited by 16
“In MI-based BCI, CSP features are commonly extracted from EEG to detect ERD/ERS [18].”
Tang, Y., Zhao, Z., Zhang, S., Li, Z., Mo, Y., & Guo, Y. Q. (2022) · Mathematical Problems in Engineering · doi:10.1155/2022/2856818 · Cited by 16
CovMix: Covariance Mixing Regularization for Motor Imagery Decoding
Zoumpourlis, G., & Patras, I. (2022) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/bci53720.2022.9734883 · Cited by 15
“Early works on MI decoding include spatial filtering techniques, such as Common Spatial Patterns (CSP) [5], [14], where the variances of the filtered signals are maximized/minimized over certain conditions (i.e. classes).”
MethodAutomatic selection of the number of spatial filters for motor-imagery BCI
Yang, Y., Chevallier, S., Wiart, J., & Bloch, I. (2012) · HAL · Cited by 19
Alain De Cheveigné, A. (2011) · NeuroImage · doi:10.1016/j.neuroimage.2011.10.084 · Cited by 14
“DSS closely resembles the Filtering by Optimal Projection (FOP) and Common Spatial Pattern (CSP) algorithms (Blankertz et al., 2008; Boudet et al., 2007; Koles et al., 1990) that have beenwidely used for classification in the Brain Computer Interface (BCI) literature, see also Cichocki (2004), Fukunaga (1990), Parra e…”
MethodDiscriminative Learning of Propagation and Spatial Pattern for Motor Imagery EEG Analysis
Li, X., Zhang, H., Guan, C., Ong, S. H., Ang, K. K., & Pan, Y. (2013) · Neural Computation · doi:10.1162/neco_a_00500 · Cited by 14
Yang, H., Guan, C., Ang, K. K., Phua, K. S., & Wang, C. (2014) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2014.6943680 · Cited by 15
“The CSP projection matrix was obtained by maximizing the variance of the filtered signal under one condition while minimizing it for another condition [7], [13].”
MethodMulti-direction hand movement classification using EEG-based source space analysis
Handiru, V. S., Vinod, A. P., & Guan, C. (2016) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2016.7591740 · Cited by 15
“Formulation of CSP is as shown in (3) [18]:”
BackgroundAdaptive Epileptic Seizure Prediction Based on EEG Synchronization
Ibrahim, S., & Majzoub, S. (2017) · Journal of biomimetics, biomaterials and biomedical engineering · doi:10.4028/www.scientific.net/jbbbe.33.52 · Cited by 14
Cho, W., Heilinger, A., Xu, R., Zehetner, M., Schobesberger, S., Murovec, N., Ortner, R., & Guger, C. (2017) · International Journal of Physical Medicine & Rehabilitation · doi:10.4172/2329-9096.1000411 · Cited by 14
“Common spatial pattern (CSP) [18] was applied to transform the preprocessed data to a new matrix with minimal variance of one class and maximal variance of the other class.”
MethodBotrel, L., & Kübler, A. (2019) · Behavioural Brain Research · doi:10.1016/j.bbr.2019.111993 · Cited by 17
Rimbert, S., Guerci, P., Gayraud, N., Meistelman, C., & Bougrain, L. (2019) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2019.8914666 · Cited by 14
“We used a Linear Discriminant Analysis (LDA) trained and evaluated using Common Spatial Pattern (CSP) features generated from the first and last 4 CSP filters [28] (referred to as CSP+LDA).”
Bagging Adversarial Neural Networks for Domain Adaptation in Non-Stationary EEG
Raza, H., & Samothrakis, S. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852284 · Cited by 16
“without muscle exertion, provided that the brain signals are properly translated into computer commands [2], [3].”
Mousavi, M., & de Sa, V. R. (2019) · Brain-Computer Interfaces · doi:10.1080/2326263x.2019.1671040 · Cited by 17
“CSP filters for each frequency band were estimated by simultaneous diagonalization of the two covariance matrices: where Λ g and Λ b are diagonal matrices such that Λ g + Λ b = I [27].”
MethodEnhanced Multiple Instance Representation Using Time-Frequency Atoms in Motor Imagery Classification
Collazos-Huertas, D. F., Caicedo-Acosta, J., Duque, G. A. C., & Acosta-Medina, C. D. (2020) · Frontiers in Neuroscience · doi:10.3389/fnins.2020.00155 · Cited by 18
ADHD diagnosis in children using Common spatial pattern and Nonlinear Analysis of Filter banked EEG
TaghiBeyglou, B., Hasanzadeh, N., Bagheri, F., & Jahed, M. (2020) · Iranian Conference on Electrical Engineering · doi:10.1109/icee50131.2020.9260711 · Cited by 15
“W which is applied to the raw observation, and attempts to maximize discriminancy [20]:”
When should MI-BCI feature optimization include prior knowledge, and which one?
Benaroch, C., Yamamoto, M. S., Roc, A., Dreyer, P., Jeunet, C., & Lotte, F. (2022) · Brain-Computer Interfaces · doi:10.1080/2326263x.2022.2033073 · Cited by 16
Feedback Strategies for BCI Based Stroke Rehabilitation: Evaluation of Different Approaches
Lechner, A., Ortner, R., & Guger, C. (2014) · Biosystems & biorobotics · doi:10.1007/978-3-319-08072-7_75 · Cited by 14
“The method of CSP creates a set of spatial filter that are optimized for each user separately and hence increase classification accuracy in comparison to fixed filter setups [11 - 12].”
MethodOrtner, R., Irimia, D.-C., Scharinger, J., & Guger, C. (2012) · IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob) · doi:10.1109/biorob.2012.6290800 · Cited by 16
Pan, L., Wang, K., Huang, Y., Sun, X., Meng, J., Yi, W., Xu, M., Jung, T., & Ming, D. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107511 · Cited by 20
DBConformer: Dual-Branch Convolutional Transformer for EEG Decoding
Wang, Z., Wang, H., Jia, T., He, X., Li, S., & Wu, D. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3622725 · Cited by 41
“A review of current EEG decoding models is shown in Table I. Early approaches to MI classification heavily relied on spatial filtering [23] to maximize inter-class variance.”
A multi-classification algorithm based on multi-domain information fusion for motor imagery BCI
Wang, J., Chen, W., & Li, M. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.104252 · Cited by 15
BrainWave-Scattering Net: a lightweight network for EEG-based motor imagery recognition
Barmpas, K., Panagakis, Y., Adamos, D. A., Laskaris, N., & Zafeiriou, S. P. (2023) · Journal of Neural Engineering · doi:10.1088/1741-2552/acf78a · Cited by 18
“The technique of common spatial pattern (CSP) algorithm [35] and the Filter-Bank CSP (FBCSP) [36] have gained high popularity since they are simple to understand and implement, and they are fast to run, which makes them attractive to BCI researchers.”
MethodA comprehensive guide to BCI-based stroke neurorehabilitation interventions
Cantillo-Negrete, J., Carino-Escobar, R. I., Ortega‐Robles, E., & Arias-Carrión, Ó. (2023) · MethodsX · doi:10.1016/j.mex.2023.102452 · Cited by 18
“For addressing the complexity of decoding MI information from the EEG, signal processing techniques and machine learning algorithms have been employed, with the Common Spatial Patterns (CSP) algorithm being one of the most widely utilized for MI [ 16 , 17 ].”
MethodPacini, F., Pacini, T., Lai, G., Zocco, A. M., & Fanucci, L. (2024) · Electronics · doi:10.3390/electronics13091646 · Cited by 22
What are the Causes of Performance Variation in Brain-Computer Interfacing?
Grosse‐Wentrup, M. (2011) · Max Planck Institute for Plasma Physics · Cited by 19
EEG Classification for BCI Based on CSP and SVM-GA
Yang, H., & Wu, S. (2013) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.459.228 · Cited by 13
“Frequently adopted methods are surface laplacian (SL), independent component analysis (ICA) and common spatial pattern (CSP) [2].”
MethodFoldes, S. T., & Taylor, D. M. (2011) · Journal of Neural Engineering · doi:10.1088/1741-2560/8/4/046022 · Cited by 15
“Therefore, unlike the other spatial filtering options, CSP analysis creates linear combinations of signals that maximize the difference in signal variance between two known conditions (e.g. moving versus resting the hand) (Blankertz et al 2008).”
BackgroundBotrel, L., Acqualagna, L., Blankertz, B., & Kübler, A. (2017) · International Journal of Psychophysiology · doi:10.1016/j.ijpsycho.2017.08.007 · Cited by 14
Self-citationModeling EEG-based Motor Imagery with Session to Session Online Adaptation
Zhang, Z., Foong, R., Phua, K. S., Wang, C., & Ang, K. K. (2018) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2018.8512706 · Cited by 13
“One of the key ML techniques developed for BCI is Common Spatial Pattern (CSP) [8], designed to increase the signal-to-noise ratio [9] of the inherently low spatial resolution of standard EEG [1].”
MethodMulticlass Classification Based on Combined Motor Imageries
Lindig-León, C., Rimbert, S., & Bougrain, L. (2020) · Frontiers in Neuroscience · doi:10.3389/fnins.2020.559858 · Cited by 13
“The CSP algorithm is one of the most popular and efficient approaches for analyzing oscillatory activity (Koles et al., 1990; Blankertz et al., 2008b).”
InfluentialTemporal Pyramid Pooling for Decoding Motor-Imagery EEG Signals
Ha, K.-W., & Jeong, J.-W. (2020) · IEEE Access · doi:10.1109/access.2020.3047678 · Cited by 14
“Experimental results revealed that CNN-based methods could successfully work without any feature engineering, and outperform the classic decoding methods [13], [14].”
BackgroundMethodTrial Regeneration With Subband Signals for Motor Imagery Classification in BCI Paradigm
Molla, M. K. I., Saha, S. K., Yasmin, S., Islam, M. R., & Shin, J. (2021) · IEEE Access · doi:10.1109/access.2021.3049191 · Cited by 16
“The electroencephalography (EEG) based BCI system is cost effective and easy to implement with minimal clinical risk as well as invasive in nature [4], [5].”
BackgroundHehenberger, L., Batistić, L., Sburlea, A. I., & Müller-Putz, G. (2021) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2021.687252 · Cited by 14
“Power feature CSPs show that in both µ and β frequency bands, there is a decrease in power during the MI period.”
MethodInfluentialBataineh, A. S. A., & Jarrah, A. A. (2021) · International Journal of Applied Metaheuristic Computing · doi:10.4018/ijamc.292500 · Cited by 14
“The following ranges from general methods such as independent component analysis and principal component analysis, to more specific EEG methods such as CSPs (Blankertz et al. 2008) and (Ang et al. 2008) for energy features and (Rivet et al. 2009) for the temporal ones.”
MethodPredicting Dominant Beat Frequency from Brain Responses While Listening to Music
Pandey, P., Ahmad, N., Miyapuram, K. P., & Lomas, D. (2021) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm52615.2021.9669750 · Cited by 13
Relation Learning Using Temporal Episodes for Motor Imagery Brain-Computer Interfaces
Huang, X., Liang, S., Zhang, Y., Zhou, N., Pedrycz, W., & Choi, K. (2022) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3228216 · Cited by 14
“Common spatial pattern (CSP) is one of the most well-known methods [7].”
MethodImportance-weighted covariance estimation for robust common spatial pattern
Balzi, A., Yger, F., & Sugiyama, M. (2015) · Pattern Recognition Letters · doi:10.1016/j.patrec.2015.09.003 · Cited by 14
Design of driving fatigue detection system based on hybrid measures using wavelet-packets transform
Wang, F., Wang, S., Wang, X., Peng, Y., & Yang, Y. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907445 · Cited by 13
“4.”
Waterstraat, G., Scheuermann, M., & Curio, G. (2015) · Clinical Neurophysiology · doi:10.1016/j.clinph.2015.12.005 · Cited by 12
“Analogous to the Common Spatial Pattern (CSP) algorithm (Blankertz et al., 2008), temporal filters were optimized to maximize the discriminability between these target segments and directly neighboring segments of equal length (with a lag of 1 or 1 sample, i.”
MethodFilter bank common spatial patterns in mental workload estimation
Arvaneh, M., Umiltà, A. M., & Robertson, I. H. (2015) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2015.7319455 · Cited by 18
“Among various spatial filters, CSP has been highly successful in classification of two classes of EEG dat a [15].”
MethodSource-space ICA for MEG source imaging
Jonmohamadi, Y., & Jones, R. D. (2015) · Journal of Neural Engineering · doi:10.1088/1741-2560/13/1/016005 · Cited by 11
“While we have determined how the order the application of two conventional techniques (beamforming+ICA versus ICA+ beamforming) can change the outcome in sourcelocalization, such comparisons could be extended to more recent signal separation techniques, such as common spatial pattern analysis [55–58] and tensor deco…”
MethodÖzbeyaz, A., & Arıca, S. (2017) · TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES · doi:10.3906/elk-1608-130 · Cited by 13
“Common spatial pattern This method amounts to maximizing the variance of the (spatially) filtered signal under one condition while minimizing it for the opposite condition [23].”
MethodIncremental Adaptive EEG Classification of Motor Imagery-based BCI
Rong, H.-J., Li, C., Bao, R.-J., & Chen, B. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489283 · Cited by 14
“And it has been developed fast recently in the widespread applications of therapeutic and nontherapeutic [1], [2] due to its significant advances of usability, information transfer and robustness [3].”
BackgroundInfluentialEEG-based Endogenous Online Co-Adaptive Brain-Computer Interfaces: Strategy for Success?
Scherer, R., Faller, J., Sajda, P., & Vidaurre, C. (2018) · Computer Science and Electronic Engineering Conference · doi:10.1109/ceec.2018.8674198 · Cited by 16
“Indeed, sophisticated machine learning and pattern recognition methods were able to identify user-specific EEG pattern features within minutes or hours of time, depending on the type of algorithm used, and hence improve pattern recognition performance [40], [41].”
BackgroundChakraborty, B., Ghosh, L., & Konar, A. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2968625 · Cited by 17
Li, Y., Li, F., Zheng, H., Jiang, L., Peng, Y., Zhang, Y., Yao, D., Xu, T., Yuan, T., & Xu, P. (2021) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac27fc · Cited by 14
“For SPN, the differentiation abilities of m SPN filters are represented by the eigenvalues involved in Σ (Blankertz et al 2008).”
Detecting Mental States by Machine Learning Techniques: The Berlin Brain–Computer Interface
Blankertz, B., Tangermann, M., Vidaurre, C., Dickhaus, T., Sannelli, C., Popescu, F., Fazli, S., Danóczy, M., Curio, G., & Müller, K. (2009) · The frontiers collection · doi:10.1007/978-3-642-02091-9_7 · Cited by 23
“For details on the technique of CSP analysis and its extensions, please see [21, 29–32] and Chapter 17 of this book.”
BackgroundMethodSelf-citationDesign of an asynchronous brain-computer interface for control of a virtual Avatar
An, H.-S., Kim, J.-W., & Lee, S. (2016) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/iww-bci.2016.7457463 · Cited by 17
“The recorded the EEG signals are used for the training of the classifier and assessment of generalization error by cross-validation [2].”
Method[The importance of Strongyloides stercoralis revisited].
Pires, M., & Dreyer, G. (1993) · PubMed · Cited by 46
Electroencephalography-based brain–Computer interface motor imagery classification
Daneshmand, P. G., Mohammadi, E., & Khorzooghi, S. M. S. M. (2022) · Journal of Medical Signals & Sensors · doi:10.4103/jmss.jmss_74_20 · Cited by 15
Decoding locomotion speed and slope from local field potentials of rat motor cortex
Mirfathollahi, A., Ghodrati, M. T., Shalchyan, V., & Daliri, M. R. (2022) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2022.106961 · Cited by 12
Tensor decomposition-based channel selection for motor imagery-based brain-computer interfaces
Huang, Z., & Wei, Q. (2023) · Cognitive Neurodynamics · doi:10.1007/s11571-023-09940-4 · Cited by 15
“N c by maximizing the following function This optimization problem is solved by generalized eigenvalue decomposition (GEVD) of the two matrices Q 1 and Q 2 (Blankertz et al. 2007).”
Chu, C., Zhu, L., Huang, A., Xu, P., Ying, N., & Zhang, J. (2024) · Journal of Neural Engineering · doi:10.1088/1741-2552/ad1f7a · Cited by 15
“Research shows that EEG signals associated with MI are µ frequency (8–13 Hz) and β frequency (14– 30 Hz) [29].”
EEG-Oriented Self-Supervised Learning With Triple Information Pathways Network
Ko, W., Jeong, S., Song, S.-K., & Suk, H. (2024) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2024.3410844 · Cited by 17
“2) Spatial Noise Recognition Pretext Task: Spatial distributional differences in EEG signals, especially in the traditional machine learning-based EEG analysis methods, such as spon-taneous BCIs [12], [50] and pathology detection [51] are frequently adopted as class-discriminative features.”
BackgroundMethodA Novel CNN With Sliding Window Technique for Enhanced Classification of MI-EEG Sensor Data
Singh, K. J., Singha, N., Jaswal, G., & Bhalaik, S. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3515252 · Cited by 17
Proficiency in motor imagery is linked to the lateralization of focused ERD patterns and beta PDC
Angulo-Sherman, I. N., León-Domínguez, U., Martínez‐Torteya, A., Fragoso-González, G. A., & Martínez-Pérez, M. V. (2025) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-025-01571-6 · Cited by 20
“It should be mentioned that a more recent study decreased the percentage of users without control to 14% by increasing up to 64 the number of electrodes that are available for SMR detection and through the use of the common spatial patters technique [74, 75].”
A Riemannian Convolutional Neural Network for EEG-based motor imagery decoding
Li, C., & Gu, Z. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130206 · Cited by 13
Motor imagery classification for brain-computer interfaces through a chaotic neural network
Piazentin, D. R. D. M., & Rosa, J. L. G. (2014) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2014.6889636 · Cited by 13
“See [21] for a thorough review on the subject.”
BackgroundEEG-based usability assessment of 3D shutter glasses
Wenzel, M. A., Schultze-Kraft, R., Meinecke, F. C., Cardinaux, F., Kemp, T., Müller, K., Curio, G., & Blankertz, B. (2015) · Journal of Neural Engineering · doi:10.1088/1741-2560/13/1/016003 · Cited by 16
Self-citation
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.