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 301–400 of 1,002
Unimodal Versus Bimodal EEG-fMRI Neurofeedback of a Motor Imagery Task
Perronnet, L., Lécuyer, A., Mano, M., Bannier, É., Lotte, F., Clerc, M., & Barillot, C. (2017) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2017.00193 · Cited by 74
“If the eigenvalue of f rest > nf was greater than the inverse of the eigenvalue of f nf > rest (Blankertz et al., 2008), the data was filtered with f rest > nf ; the band power in the µ band was then computed on this filtered data using the periodogram and it was normalized with an event-related…”
MethodStieger, J., Engel, S. A., Jiang, H., Cline, C. C., Kreitzer, M. J., & He, B. (2020) · Cerebral Cortex · doi:10.1093/cercor/bhaa234 · Cited by 76
Noninvasive Brain–Machine Interfaces for Robotic Devices
Tonin, L., & Millán, J. D. R. (2020) · Annual Review of Control Robotics and Autonomous Systems · doi:10.1146/annurev-control-012720-093904 · Cited by 75
Spatially Regularized Common Spatial Patterns for EEG Classification
Lotte, F., & Guan, C. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.904 · Cited by 70
Channel selection procedure using riemannian distance for BCI applications
Barachant, A., & Bonnet, S. (2011) · International IEEE/EMBS Conference on Neural Engineering · doi:10.1109/ner.2011.5910558 · Cited by 66
“Such second-order information has been shown to be well adapted to catch the relevant information between two mental tasks [8].”
BackgroundInfluentialOptimal Channel Selection Using Correlation Coefficient for CSP Based EEG Classification
Park, Y., & Chung, W. (2020) · IEEE Access · doi:10.1109/access.2020.3003056 · Cited by 67
“Especially, the common spatial pattern (CSP) approach [1], [4]–[6] has been used successfully in MI classification by extracting ERD/ERS-related features.”
MethodSubject independent EEG-based BCI decoding
Fazli, S., Grozea, C., Danóczy, M., Blankertz, B., Popescu, F., & Müller, K. (2009) · Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft) · Cited by 76
Self-citationEEG-based BCI for the linear control of an upper-limb neuroprosthesis
Vidaurre, C., Klauer, C., Schauer, T., Ramos‐Murguialday, A., & Müller, K. (2016) · Medical Engineering & Physics · doi:10.1016/j.medengphy.2016.06.010 · Cited by 73
Marathe, A. R., Lawhern, V. J., Wu, D., Slayback, D., & Lance, B. J. (2016) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2015.2502323 · Cited by 64
Estimation of task workload from EEG data: New and current tools and perspectives
Kothe, C. A., & Makeig, S. (2011) · 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/iembs.2011.6091615 · Cited by 64
Coyle, D. (2009) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2009.934560 · Cited by 68
EEG Single-Trial Detection of Gait Speed Changes during Treadmill Walk
Lisi, G., & Morimoto, J. (2015) · PLoS ONE · doi:10.1371/journal.pone.0125479 · Cited by 68
“In order to decompose different neural and artifactual sources [28, 29], Infomax ICA is computed on the preprocessed EEG signal of the training set.”
Methodvon Lühmann, A., Herff, C., Heger, D., & Schultz, T. (2015) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2015.00617 · Cited by 72
A classification method for EEG motor imagery signals based on parallel convolutional neural network
Han, Y., Wang, B., Luo, J., Li, L., & Li, X. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103190 · Cited by 65
Amiri, M., Aghaeinia, H., & Amindavar, H. R. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.104022 · Cited by 72
A Convolutional Long Short-Term Memory-Based Neural Network for Epilepsy Detection From EEG
Tawhid, M. N. A., Siuly, S., & Li, T. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3217515 · Cited by 63
An Enhanced Probabilistic LDA for Multi-Class Brain Computer Interface
Xu, P., Yang, P., Lei, X., & Yao, D. (2011) · PLoS ONE · doi:10.1371/journal.pone.0014634 · Cited by 68
“CSP has been proved to be an effective method to extract ERD/ERS related features from multi-channel EEG data of a two-motor imaginary task [15,16].”
MethodWireless EEG with individualized channel layout enables efficient motor imagery training
Zich, C., Vos, M. D., Kranczioch, C., & Debener, S. (2014) · Clinical Neurophysiology · doi:10.1016/j.clinph.2014.07.007 · Cited by 69
Wang, Y., Wang, Y.-T., & Jung, T. (2012) · PLoS ONE · doi:10.1371/journal.pone.0037665 · Cited by 68
“In previous studies, the CSP method has been more commonly used for classifying motor imagery EEG due to its simplicity in computation and high performance in classification [33].”
Lotte, F., van Langhenhove, A., Lamarche, F., Ernest, T., Renard, Y., Arnaldi, B., & Lécuyer, A. (2010) · PRESENCE Virtual and Augmented Reality · doi:10.1162/pres.19.1.54 · Cited by 63
Li, H., Huang, G., Lin, Q., Zhao, J.-L., Lo, W. L. A., Mao, Y., Chen, L., Zhang, Z., Huang, D., & Li, L. (2018) · Frontiers in Neurology · doi:10.3389/fneur.2018.00822 · Cited by 70
“It has been proved that the Laplacian method, compared with other fixed spatial filter, such as bipolar and common average reference, can effectively improve the SignalNoise-Ratio of the EEG signal for the ERD/ERS analysis (40).”
MethodVIGNet: A Deep Convolutional Neural Network for EEG-based Driver Vigilance Estimation
Ko, W., Oh, K., Jeon, E., & Suk, H. (2020) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/bci48061.2020.9061668 · Cited by 69
“In the past decade, machine learning methods [4], [2] have played important roles in the BCI society.”
BackgroundComplex common spatial patterns on time-frequency decomposed EEG for brain-computer interface
Mishuhina, V., & Jiang, X. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.107918 · Cited by 67
Leaf-inspired homeostatic cellulose biosensors
Kim, J.-Y., Yun, Y. J., Jeong, J., Kim, C., Müller, K., & Lee, S. (2021) · Science Advances · doi:10.1126/sciadv.abe7432 · Cited by 64
On the Deep Learning Models for EEG-Based Brain-Computer Interface Using Motor Imagery
Zhu, H., Forenzo, D., & He, B. (2022) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3198041 · Cited by 67
“There are lots of successful feature extraction methods, such as common spatial patterns (CSP) methods [13], [14].”
Three-Class EEG-Based Motor Imagery Classification Using Phase-Space Reconstruction Technique
Djemal, R., Baziyad, A. G., Belwafi, K., Gannouni, S., & Kaaniche, W. (2016) · Brain Sciences · doi:10.3390/brainsci6030036 · Cited by 67
“One of the most widely used techniques in BCIs for reducing the high-dimensionality issue is filtering using the common spatial pattern (CSP) algorithm [8].”
MethodAdaptive Seizure Onset Detection Framework Using a Hybrid PCA–CSP Approach
Khanmohammadi, S., & Chou, C.-A. (2017) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2017.2703873 · Cited by 66
“For more detailed explanation of PCA and CSP methods and their extensions, readers can refer to [18]–[20].”
MethodRupawala, M., Dehghani, H., Lucas, S. J. E., Tiňo, P., & Cruse, D. (2018) · Frontiers in Neurology · doi:10.3389/fneur.2018.00350 · Cited by 75
“The common spatial patterns method in multichannel EEG (155) efficiently reduces the number of features for classification to those that have highly discriminative properties between tasks.”
MethodCao, L., Li, G., Yang, X., Zhang, H., Shu, X., & Zhang, D. (2021) · Journal of Neural Engineering · doi:10.1088/1741-2552/abf8cb · Cited by 68
“As to the two parallel decoders in the second layer, for MI decoding, the common spatial pattern (CSP) algorithm (Blankertz et al 2007) was implemented to extract the feature vectors and LDA classifier was employed for final classification over the selected fourteen channels.”
Robustness of the Common Spatial Patterns algorithm in the BCI-pipeline
Reuderink, B., & Poel, M. (2008) · University of Twente Research Information · Cited by 71
Tariq, M., Trivailo, P. M., & Simić, M. (2020) · PLoS ONE · doi:10.1371/journal.pone.0230184 · Cited by 68
Motor-Imagery-Based Brain–Computer Interface Using Signal Derivation and Aggregation Functions
Fumanal-Idocin, J., Wang, Y., Lin, C., Fernández, J., Sanz, J., & Bustince, H. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3073210 · Cited by 78
“The CSP is used to transform multivariate EEG signals into well-separated subcomponents with maximum spatial variation using the labels for each example [42], [43],”
MethodA hybrid brain-computer interface for closed-loop position control of a robot arm
Rakshit, A., Konar, A., & Nagar, A. K. (2020) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2020.1003336 · Cited by 66
“Though any other standard pattern classifier could have served the purpose, LSVM is selected for its high classification accuracy and low computational overhead [37].”
Grigorev, N., Savosenkov, A., Lukoyanov, M. V., Udoratina, A., Shusharina, N. N., Kaplan, A., Hramov, A. E., Kazantsev, V., & Gordleeva, S. (2021) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2021.3102304 · Cited by 65
Classifying visuomotor workload in a driving simulator using subject specific spatial brain patterns
Dijksterhuis, C., de Waard, D., Brookhuis, K., Mulder, B., & de Jong, R. (2013) · Frontiers in Neuroscience · doi:10.3389/fnins.2013.00149 · Cited by 71
“This technique determines CSP filters in such a way that they maximize the variances of spatially filtered signals for one training set while minimizing them for the other (Blankertz et al., 2008).”
BackgroundMethodInfluentialChristoforou, C., Papadopoulos, T. C., Constantinidou, F., & Theodorou, M. (2017) · Frontiers in Neuroinformatics · doi:10.3389/fninf.2017.00072 · Cited by 72
“Resulting metrics have been used in different applications such as Brain-computer interfaces (Blankertz et al., 2008), Robotic-telepresence (Christoforou et al., 2010) and maximization of throughput in performance tasks (Parra et al., 2008).”
MethodMeng, J., & He, B. (2019) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2019.00128 · Cited by 68
“…of traditional MI-based BCI, studies were conducted to improve BCI performance including developing advanced signal processing algorithms (Blankertz et al., 2008; Ang et al., 2012; Meng et al., 2015; Edelman et al., 2016), designing new experimental paradigms such as providing physical…”
MethodMohseni, M., Shalchyan, V., Jochumsen, M., & Niazi, I. K. (2019) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2019.105076 · Cited by 66
EEG-Based Brain-Computer Interfaces
Wang, Y., Nakanishi, M., & Zhang, D. (2019) · Advances in experimental medicine and biology · doi:10.1007/978-981-13-2050-7_2 · Cited by 70
An Adaptive Spatial Filter for User-Independent Single Trial Detection of Event-Related Potentials
Woehrle, H., Krell, M. M., Straube, S., Kim, S. K., Kirchner, E. A., & Kirchner, F. (2015) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2015.2402252 · Cited by 59
“Examples for SFs are the common spatial patterns (CSP) filter for sensorimotor rhythms [6] and the xDAWN [7], πSF [8], or”
BackgroundHsu, W. (2013) · International Journal of Neural Systems · doi:10.1142/s012906571350007x · Cited by 59
EEG Channel Selection Techniques in Motor Imagery Applications: A Review and New Perspectives
Abdullah, Faye, I., & Islam, M. R. (2022) · Bioengineering · doi:10.3390/bioengineering9120726 · Cited by 75
M-FANet: Multi-Feature Attention Convolutional Neural Network for Motor Imagery Decoding
Qin, Y., Yang, B., Ke, S., Liu, P., Rong, F., & Xia, X. (2024) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2024.3351863 · Cited by 66
“For instance, the Common Spatial Pattern (CSP) is a spatial-domain filtering feature extraction method that distills spatially distributed components from multichannel EEG signals corresponding to each class [17].”
MethodActive Data Selection for Motor Imagery EEG Classification
Tomida, N., Tanaka, T., Ono, S., Yamagishi, M., & Higashi, H. (2014) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2014.2358536 · Cited by 61
“Although the solution of (2) is given by the eigenvector corresponding to the largest eigenvalue in (5), we can use the other eigenvectors for classification [41].”
Combining Spatial Filtering and Wavelet Transform for Classifying Human Emotions Using EEG Signals
Murugappan, M., Nagarajan, R., & Yaacob, S. (2011) · Journal of Medical and Biological Engineering · Cited by 75
Large-Scale Assessment of a Fully Automatic Co-Adaptive Motor Imagery-Based Brain Computer Interface
Acqualagna, L., Botrel, L., Vidaurre, C., Kübler, A., & Blankertz, B. (2016) · PLoS ONE · doi:10.1371/journal.pone.0148886 · Cited by 74
“Data recorded in runs 1 – 3 were used to select subject-specific settings (according to the tutorial in [40]), which were used in runs 4 – 5.”
MethodSelf-citationGeometry-aware principal component analysis for symmetric positive definite matrices
Horev, I., Yger, F., & Sugiyama, M. (2016) · Machine Learning · doi:10.1007/s10994-016-5605-5 · Cited by 77
“For both datasets we reduce the matrices from their original size to 6×6 as it corresponds to the number of sources recommended in Blankertz et al. (2008) for common spatial pattern (CSP).”
BackgroundMethodKarimi, F., Kofman, J., Mrachacz‐Kersting, N., Farina, D., & Jiang, N. (2017) · Frontiers in Neuroscience · doi:10.3389/fnins.2017.00356 · Cited by 61
“However, the performance of CSP is very sensitive to outliers, which are inevitable in real-time BCI applications (Blankertz et al., 2008).”
BackgroundMethodInfluentialTactile Stimulation Improves Sensorimotor Rhythm-Based BCI Performance in Stroke Patients
Shu, X., Chen, S., Meng, J., Yao, L., Sheng, X., Jia, J., Farina, D., & Zhu, X. (2018) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2018.2882075 · Cited by 60
“pattern (CSP) algorithm, which has been extensively validated for BCI decoding [25].”
MethodTan, P., Wang, X., & Wang, Y. (2019) · Swarm and Evolutionary Computation · doi:10.1016/j.swevo.2019.100597 · Cited by 64
“In motor imagery BCI, common spatial patterns (CSP) algorithm is a successful feature extraction method for detecting ERD and ERS [26–30].”
BackgroundMethodA Systematic Review on Motor-Imagery Brain-Connectivity-Based Computer Interfaces
Brusini, L., Stival, F., Setti, F., Menegatti, E., Menegaz, G., & Storti, S. F. (2021) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2021.3115094 · Cited by 61
Hu, Z., Chen, L., Luo, Y., & Zhou, J. (2022) · Applied Sciences · doi:10.3390/app122111255 · Cited by 75
“Therefore, spatial filters are needed to increase spatial resolution and improve the spatial information contained in the signal [26].”
BackgroundAcqualagna, L., Bosse, S., Porbadnigk, A. K., Curio, G., Müller, K., Wiegand, T., & Blankertz, B. (2015) · Journal of Neural Engineering · doi:10.1088/1741-2560/12/2/026012 · Cited by 63
“For a more detailed review on CSP analysis and its application to EEG signal processing, please refer to Lemm et al (2005), Lotte et al (2007), Blankertz et al (2008), Sannelli et al (2011), Samek et al (2012).”
MethodInfluentialSelf-citationComparison of different wavelet features from EEG signals for classifying human emotions
Murugappan, M., Nagarajan, R., & Yaacob, S. (2009) · IEEE Symposium on Industrial Electronics & Applications (ISIEA) · doi:10.1109/isiea.2009.5356339 · Cited by 62
“Potentially useful information from the middle frequencies may be filtered out by the analytical Laplacian filters [18].”
MethodYang, X., Zhang, H., Cao, L., Shu, X., & Zhang, D. (2020) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2020.3034826 · Cited by 66
Das, K., & Pachori, R. B. (2022) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2022.3214081 · Cited by 61
“small Laplacian [12], large Laplacian [12], common average [31], CSP [2], [12], [32] were studied to improve the spatial resolution of EEG.”
BackgroundA subject-independent brain-computer interface based on smoothed, second-order baselining
Reuderink, B., Farquhar, J., Poel, M., & Nijholt, A. (2011) · 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/iembs.2011.6091139 · Cited by 54
“[2]).”
Automated selecting subset of channels based on CSP in motor imagery brain-computer interface system
Meng, J., Liu, G., Huang, G., & Zhu, X. (2009) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2009.5420462 · Cited by 63
“has no direct association to signs because the signs of the pattern vectors are irrelevant to the analysis [8].”
BackgroundEnsembles of adaptive spatial filters increase BCI performance: an online evaluation
Sannelli, C., Vidaurre, C., Müller, K., & Blankertz, B. (2016) · Journal of Neural Engineering · doi:10.1088/1741-2560/13/4/046003 · Cited by 61
Self-citationYu, Y., Zhou, Z., Yin, E., Jiang, J., Tang, J., Liu, Y., & Hu, D. (2016) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2016.08.010 · Cited by 62
“were used, following previously described procedures [27].”
BackgroundMethodBrain-Switches for Asynchronous Brain–Computer Interfaces: A Systematic Review
Han, C. H., Müller, K., & Hwang, H.-J. (2020) · Electronics · doi:10.3390/electronics9030422 · Cited by 59
EEG classification for the detection of mental states
Vézard, L., Legrand, P., Chavent, M., Faïta-Aïnseba, F., & Trujillo, L. (2015) · Applied Soft Computing · doi:10.1016/j.asoc.2015.03.028 · Cited by 58
Benefits of deep learning classification of continuous noninvasive brain–computer interface control
Stieger, J. R., Engel, S. A., Suma, D., & He, B. (2021) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac0584 · Cited by 55
“Common spatial patterns may be a technique that requires additional calibration to each individual and each dataset (Guger et al 2000, Ang et al 2008, Blankertz et al 2008, Wu et al 2013).”
Quantifying Limb Movements in Epileptic Seizures Through Color-Based Video Analysis
Lu, H., Pan, Y., Mandal, B., Eng, H., Guan, C., & Chan, D. W. S. (2012) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2012.2228649 · Cited by 59
Pre-Stimulus Sensorimotor Rhythms Influence Brain–Computer Interface Classification Performance
Maeder, C. L., Sannelli, C., Haufe, S., & Blankertz, B. (2012) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2012.2205707 · Cited by 63
Self-citationImproving brain–computer interface classification using adaptive common spatial patterns
Song, X., & Yoon, S.-C. (2015) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2015.03.023 · Cited by 61
A subject-independent pattern-based Brain-Computer Interface
Ray, A. M., Sitaram, R., Rana, M., Pasqualotto, E., Buyukturkoglu, K., Guan, C., Ang, K.-K., Tejos, C., Zamorano, F., Aboitiz, F., et al. (2015) · Frontiers in Behavioral Neuroscience · doi:10.3389/fnbeh.2015.00269 · Cited by 53
“…spatial filters from the data that, when projected, identify important parts of the data, i.e., regions on the scalp that contain information for the discrimination of two classes (see Koles et al., 1990; Koles, 1991; Müller-Gerking et al., 1999; Ramoser et al., 2000; Blankertz et al., 2008).”
BackgroundBCI and FES Based Therapy for Stroke Rehabilitation Using VR Facilities
Lupu, R. G., Irimia, D.-C., Ungureanu, F., Poboroniuc, M.-S., & Moldoveanu, A. D. B. (2018) · Wireless Communications and Mobile Computing · doi:10.1155/2018/4798359 · Cited by 61
“The EEG data are bandpass filtered between 8 and 30Hz and then fed to the processing algorithm that performs spatial filtering with the Common Spatial Patterns (CSP) method [30, 31] and Linear Discriminant Analysis (LDA) classification [22, 32].”
MethodPeterson, V., Wyser, D., Lambercy, O., Spies, R. D., & Gassert, R. (2019) · Journal of Neural Engineering · doi:10.1088/1741-2552/aaf046 · Cited by 62
Shajil, N., Sasikala, M., Srinivasan, P., Arivudaiyanambi, J., & Arunnagiri, A. M. (2020) · Journal of Medical and Biological Engineering · doi:10.1007/s40846-020-00538-3 · Cited by 57
Han, C. H., Müller, K., & Hwang, H.-J. (2020) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2020.3017167 · Cited by 56
“For CSPs, subject-specific band-pass filter coefficients were estimated by the means of a commonly used heuristic procedure which estimates a frequency band showing the highest absolute signed squared point biserial correlation coefficient (signed r 2 ) value [69], [70].”
MethodHiremath, S. V., Chen, W., Wang, W., Foldes, S., Yang, Y., Tyler-Kabara, E. C., Collinger, J. L., & Boninger, M. L. (2015) · Frontiers in Integrative Neuroscience · doi:10.3389/fnint.2015.00040 · Cited by 53
“Research has demonstrated that visual feedback plays a key role in skill learning (Hinterberger et al., 2004; Abbott, 2006; Leeb et al., 2006; Blankertz et al., 2008; Barbero and Grosse-Wentrup, 2010).”
BackgroundMotor imagery EEG decoding using manifold embedded transfer learning
Cai, Y., She, Q., Ji, J., Ma, Y., Zhang, J., & Zhang, Y. (2022) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2022.109489 · Cited by 53
2020 International brain–computer interface competition: A review
Jeong, J.-H., Cho, J.-H., Lee, Y.-E., Lee, S., Shin, G.-H., Kweon, Y.-S., Millán, J. D. R., Müller, K., & Lee, S.-W. (2022) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2022.898300 · Cited by 88
“…by recognizing human intentions through specific patterns of neural signals (Kao et al., 2015; Pearson, 2019) using modern signal processing and machine learning (Pascual-Marqui, 2002; Delorme and Makeig, 2004; Blankertz et al., 2008, 2011, 2016; Lemm et al., 2011; Lee M. H. et al., 2019).”
BackgroundMethodWu, W., Chen, Z. S., Gao, S., & Brown, E. N. (2011) · NeuroImage · doi:10.1016/j.neuroimage.2011.03.032 · Cited by 55
“In other words, CSP is prone to overfitting noisy observations due to under-constrained estimation (Blankertz et al., 2008; Hill et al., 2007).”
BackgroundMethodInfluentialThe analytic common spatial patterns method for EEG-based BCI data
Falzon, O., Camilleri, K. P., & Muscat, J. (2012) · Journal of Neural Engineering · doi:10.1088/1741-2560/9/4/045009 · Cited by 55
“The efficacy of the method in the field is evident from the popularity of the CSP technique in the BCI community [5–7] where it ranks amongst the best performing algorithms.”
MethodSimultaneous EEG-fNIRS reveals how age and feedback affect motor imagery signatures
Zich, C., Debener, S., Thoene, A.-K., Chen, L.-C., & Kranczioch, C. (2016) · Neurobiology of Aging · doi:10.1016/j.neurobiolaging.2016.10.011 · Cited by 65
Common Spatial Pattern Technique With EEG Signals for Diagnosis of Autism and Epilepsy Disorders
Alturki, F. A., Aljalal, M., Abdurraqeeb, A. M., AlSharabi, K., & Al-Shamma’a, A. A. (2021) · IEEE Access · doi:10.1109/access.2021.3056619 · Cited by 61
“Weused the CSP algorithm as a spatial filter that leads to peak variances for differentiating between the two classes of EEGs (normal and epilepsy/autism) [31].”
Cantillo-Negrete, J., Carino-Escobar, R. I., Carrillo‐Mora, P., Rodríguez-Barragán, M. A., Hernández-Arenas, C., Quinzaños-Fresnedo, J., Hernandez-Sanchez, I. R., Galicia-Alvarado, M. A., Miguel‐Puga, J. A., & Arias-Carrión, Ó. (2021) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2021.656975 · Cited by 61
Brain–computer interfacing: more than the sum of its parts
Scherer, R., Faller, J., Balderas, D., Friedrich, E. V. C., Pröll, M., Allison, B. Z., & Müller-Putz, G. (2012) · Soft Computing · doi:10.1007/s00500-012-0895-4 · Cited by 59
“The CSP method projects multi-channel EEG data from two classes into a low-dimensional spatial subspace in such a way that the variances of the time series (equals the power in the spectral domain) are optimal for discrimination (Blankertz et al. 2008; Müller-Gerking et al. 1999).”
MethodPlacidi, G., Avola, D., Petracca, A., Sgallari, F., & Spezialetti, M. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.02.034 · Cited by 56
“Moreover, efforts will be dedicated to use optimization algorithms, such as the common spatial pattern and its variants [39,40], as classification strategies (on the same data), Fig.”
BackgroundMethodMiao, M., Wang, A., & Liu, F. (2017) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-017-1622-1 · Cited by 53
Motor Imagery EEG Signal Processing and Classification Using Machine Learning Approach
Sreeja, S. R., Rabha, J., Nagarjuna, K., Samanta, D., Mitra, P., & Sarma, M. (2017) · International Conference on New Trends in Computing Sciences (ICTCS) · doi:10.1109/ictcs.2017.15 · Cited by 64
“The performance of the proposed approach is compared with two conventional calssifiers such as linear discriminant analysis (LDA) [27] and support vector machine (SVM) [28].”
MethodInfluentialIndividualized pattern recognition for detecting mind wandering from EEG during live lectures
Dhindsa, K., Acai, A., Wagner, N., Bosynak, D., Kelly, S., Bhandari, M., Petrisor, B. A., & Sonnadara, R. (2019) · PLoS ONE · doi:10.1371/journal.pone.0222276 · Cited by 60
Malan, N. S., & Sharma, S. (2021) · IRBM · doi:10.1016/j.irbm.2021.01.002 · Cited by 61
Continuous sensorimotor rhythm based brain computer interface learning in a large population
Stieger, J., Engel, S. A., & He, B. (2021) · Scientific Data · doi:10.1038/s41597-021-00883-1 · Cited by 75
Multi-class filter bank common spatial pattern for four-class motor imagery BCI
Chin, Z. Y., Ang, K. K., Wang, C., Guan, C., & Zhang, H. (2009) · 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/iembs.2009.5332383 · Cited by 107
“Although a wideband of 8-30Hz was suggested [5], evidence showed that selecting subject-specific frequency bands could yield an improvement in the recognition rate of MI-BCI [ 8 ].”
BackgroundA binary harmony search algorithm as channel selection method for motor imagery-based BCI
Shi, B., Wang, Q., Yin, S., Yue, Z., Huai, Y., & Wang, J. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.02.051 · Cited by 49
A predictive speller controlled by a brain-computer interface based on motor imagery
D’Albis, T., Blatt, R., Tedesco, R., Sbattella, L., & Matteucci, M. (2012) · ACM Transactions on Computer-Human Interaction · doi:10.1145/2362364.2362368 · Cited by 58
Bipolar electrode selection for a motor imagery based brain–computer interface
Lou, B., Hong, B., Gao, X., & Gao, S. (2008) · Journal of Neural Engineering · doi:10.1088/1741-2560/5/3/007 · Cited by 55
“Thus, the poor spatial resolution of raw EEG scalp potentials and the overlap of the alpha and mu rhythms’ frequency bands increase the complexity of classification when using band power to classify motor imagery [21].”
BackgroundMethodTowards a holistic assessment of the user experience with hybrid BCIs
Lorenz, R., Pascual, J., Blankertz, B., & Vidaurre, C. (2014) · Journal of Neural Engineering · doi:10.1088/1741-2560/11/3/035007 · Cited by 58
“After this, the filtered and epoched signal was spatially filtered using common spatial patterns [38].”
MethodSelf-citationAveraging covariance matrices for EEG signal classification based on the CSP: An empirical study
Yger, F., Lotte, F., & Sugiyama, M. (2015) · 2015 23rd European Signal Processing Conference (EUSIPCO) · doi:10.1109/eusipco.2015.7362879 · Cited by 47
“The feature extracted from every trial consists of the log-variance EEG signal projected on the 6 selected CSP filters (as recommended in [11]).”
BackgroundMethodFacilitating motor imagery-based brain–computer interface for stroke patients using passive movement
Arvaneh, M., Guan, C., Ang, K. K., Ward, T. E., Chua, K. S. G., Kuah, C. W. K., Joseph, G. J. E., Phua, K. S., & Wang, C. (2016) · Neural Computing and Applications · doi:10.1007/s00521-016-2234-7 · Cited by 53
“Recently, the FBCSP algorithm [28] was proposed that combined a filter bank framework with the common spatial patterns (CSP) algorithm [29] to select the most discriminative features using a mutual information-based criterion [30].”
MethodExtracting the nonlinear features of motor imagery EEG using parametric t-SNE
Li, M., Luo, X., & Yang, J. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.08.083 · Cited by 58
Hugle, M., Heller, S., Watter, M., Blum, M., Manzouri, F., Dumpelmann, M., Schulze‐Bonhage, A., Woias, P., & Boedecker, J. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489493 · Cited by 54
Novel hybrid brain–computer interface system based on motor imagery and P300
Zuo, C., Jin, J., Yin, E., Saab, R., Miao, Y., Wang, X., Hu, D., & Cichocki, A. S. (2019) · Cognitive Neurodynamics · doi:10.1007/s11571-019-09560-x · Cited by 51
Miao, M., Hu, W., Yin, H., & Zhang, K. (2020) · Computational and Mathematical Methods in Medicine · doi:10.1155/2020/1981728 · Cited by 61
“To evaluate the classification performance of our method objectively, three other algorithms including CSP [9], FBCSP [12], and SFBCSP [13] were adopted for performance comparison.”
MethodOptical brain imaging and its application to neurofeedback
Soekadar, S. R., Kohl, S. H., Mihara, M., & von Lühmann, A. (2021) · NeuroImage Clinical · doi:10.1016/j.nicl.2021.102577 · Cited by 52
“…(LIS) could select single letters on a screen by self-regulating slow cortical potentials (SCP) recorded by EEG. Applicability and versatility of such BCI systems for restoration of communication were later substantially improved (Blankertz et al., 2011; Blankertz, 2008; Kubler & Kotchoubey, 2007).”
BackgroundImproving EEG Decoding via Clustering-Based Multitask Feature Learning
Zhang, Y., Zhou, T., Wu, W., Xie, H., Zhu, H., Zhou, G., & Cichocki, A. S. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3053576 · Cited by 58
How Many People Can Use a BCI System?
Edlinger, G., Allison, B. Z., & Guger, C. (2014) · Springer eBooks · doi:10.1007/978-4-431-55037-2_3 · Cited by 57
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.