Characterizing Regularization Techniques for Spatial Filter Optimization in Oscillatory EEG Regression Problems : Guidelines Derived from Simulation and Real-World Data.
Saved in:
| Title: | Characterizing Regularization Techniques for Spatial Filter Optimization in Oscillatory EEG Regression Problems : Guidelines Derived from Simulation and Real-World Data. |
|---|---|
| Authors: | Meinel A; Brain State Decoding Lab, Cluster of Excellence BrainLinks-BrainTools, Department of Computer Science, Albert-Ludwigs-University, Freiburg, Germany. andreas.meinel@blbt.uni-freiburg.de., Castaño-Candamil S; Brain State Decoding Lab, Cluster of Excellence BrainLinks-BrainTools, Department of Computer Science, Albert-Ludwigs-University, Freiburg, Germany., Blankertz B; Neurotechnology Dept., Technical University of Berlin, Berlin, Germany., Lotte F; Potioc project team, Inria, Talence, France.; LaBRI (University of Bordeaux, CNRS, INP), Talence, France., Tangermann M; Brain State Decoding Lab, Cluster of Excellence BrainLinks-BrainTools, Department of Computer Science, Albert-Ludwigs-University, Freiburg, Germany. michael.tangermann@blbt.uni-freiburg.de. |
| Source: | Neuroinformatics [Neuroinformatics] 2019 Apr; Vol. 17 (2), pp. 235-251. |
| Publication Type: | Journal Article; Research Support, Non-U.S. Gov't |
| Language: | English |
| Journal Info: | Publisher: Humana Press, Inc Country of Publication: United States NLM ID: 101142069 Publication Model: Print Cited Medium: Internet ISSN: 1559-0089 (Electronic) Linking ISSN: 15392791 NLM ISO Abbreviation: Neuroinformatics |
| Imprint Name(s): | Original Publication: Totowa, NJ : Humana Press, Inc., c2003- |
| MeSH Terms: | Algorithms* , Signal Processing, Computer-Assisted*, Brain/*physiology , Brain Mapping/*methods , Electroencephalography/*methods, Humans ; Magnetoencephalography ; Reproducibility of Results |
| Abstract: | We report on novel supervised algorithms for single-trial brain state decoding. Their reliability and robustness are essential to efficiently perform neurotechnological applications in closed-loop. When brain activity is assessed by multichannel recordings, spatial filters computed by the source power comodulation (SPoC) algorithm allow identifying oscillatory subspaces. They regress to a known continuous trial-wise variable reflecting, e.g. stimulus characteristics, cognitive processing or behavior. In small dataset scenarios, this supervised method tends to overfit to its training data as the involved recordings via electroencephalogram (EEG), magnetoencephalogram or local field potentials generally provide a low signal-to-noise ratio. To improve upon this, we propose and characterize three types of regularization techniques for SPoC: approaches using Tikhonov regularization (which requires model selection via cross-validation), combinations of Tikhonov regularization and covariance matrix normalization as well as strategies exploiting analytical covariance matrix shrinkage. All proposed techniques were evaluated both in a novel simulation framework and on real-world data. Based on the simulation findings, we saw our expectations fulfilled, that SPoC regularization generally reveals the largest benefit for small training sets and under severe label noise conditions. Relevant for practitioners, we derived operating ranges of regularization hyperparameters for cross-validation based approaches and offer open source code. Evaluating all methods additionally on real-world data, we observed an improved regression performance mainly for datasets from subjects with initially poor performance. With this proof-of-concept paper, we provided a generalizable regularization framework for SPoC which may serve as a starting point for implementing advanced techniques in the future. |
| References: | Arvaneh, M., Guan, C., Ang, K.K., Quek, C. (2011). Optimizing the channel selection and classification accuracy in EEG-based BCI. IEEE Transactions on Biomedical Engineering, 58(6), 1865–1873. https://doi.org/10.1109/TBME.2011.2131142 . (PMID: 10.1109/TBME.2011.213114221427014) Arvaneh, M., Guan, C., Ang, K.K., Quek, C. (2013). Optimizing spatial filters by minimizing within-class dissimilarities in electroencephalogram-based brain-computer interface. IEEE Transactions on Neural Networks and Learning Systems, 24(4), 610–619. https://doi.org/10.1109/TNNLS.2013.2239310 . (PMID: 10.1109/TNNLS.2013.223931024808381) Bai, Z, & Silverstein, JW. (2009). Spectral analysis of large dimensional random matrices. Springer Science & Business Media. Bartz, D., & Müller, K.-R. (2014). Covariance shrinkage for autocorrelated data. In Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (Eds.) Advances in neural information processing systems, (Vol. 27 pp. 1592–1600): Curran Associates Inc. Blankertz, B., Tomioka, R., Lemm, S., Kawanabe, M., Müller, K.-R. (2008). Optimizing spatial filters for robust EEG single-trial analysis. Signal Processing Magazine, IEEE, 25(1), 41–56. (PMID: 10.1109/MSP.2008.4408441) Blankertz, B., Sannelli, C., Halder, S., Hammer, E.M., Kübler, A., Müller, K.-R., Curio, G., Dickhaus, T. (2010). Neurophysiological predictor of SMR-based BCI performance. NeuroImage, 51(4), 1303–1309. https://doi.org/10.1016/j.neuroimage.2010.03.022 . (PMID: 10.1016/j.neuroimage.2010.03.02220303409) Blankertz, B., Acqualagna, L., Dähne, S, Haufe, S., Schultze-Kraft, M., Sturm, I., Ušćumlic, M., Wenzel, M.A., Curio, G., Müller, K.-R. (2016). The berlin brain-computer interface: progress beyond communication and control. Frontiers in Neuroscience, 10, 530. https://doi.org/10.3389/fnins.2016.00530 . (PMID: 10.3389/fnins.2016.00530279171075116473) Castaño-Candamil, J.S., Meinel, A., Dähne, S., Tangermann, M. (2015). Probing meaningfulness of oscillatory EEG components with bootstrapping, label noise and reduced training sets. In 2015 37th Annual international conference of the IEEE engineering in medicine and biology society (EMBC) (pp. 5159–5162). IEEE. Castaño-Candamil, S., Meinel, A., Tangermann, M. (2017). Post-hoc labeling of arbitrary EEG recordings for data-efficient evaluation of neural decoding methods. arXiv: 171108208 . Chen, Y., Wiesel, A., Hero, A.O. (2011). Robust shrinkage estimation of high-dimensional covariance matrices. IEEE Transactions on Signal Processing, 59(9), 4097–4107. https://doi.org/10.1109/TSP.2011.2138698 . (PMID: 10.1109/TSP.2011.2138698) Cheng, M., Lu, Z., Wang, H. (2017). Regularized common spatial patterns with subject-to-subject transfer of EEG signals. Cognitive Neurodynamics, 11(2), 173–181. https://doi.org/10.1007/s11571-016-9417-x . (PMID: 10.1007/s11571-016-9417-x28348648) Cho, H., Ahn, M., Kim, K., Jun, S.C. (2015). Increasing session-to-session transfer in a brain–computer interface with on-site background noise acquisition. Journal of Neural Engineering, 12(6), 066,009. https://doi.org/10.1088/1741-2560/12/6/066009 . (PMID: 10.1088/1741-2560/12/6/066009) Clerc, M., Bougrain, L., Lotte, F. (2016). Brain-computer interfaces 2: technology and applications. Wiley. Dähne, S., Meinecke, F.C., Haufe, S., Höhne, J, Tangermann, M., Müller, K.-R., Nikulin, V.V. (2014). SPoC: a novel framework for relating the amplitude of neuronal oscillations to behaviorally relevant parameters. NeuroImage, 86(0), 111–122. https://doi.org/10.1016/j.neuroimage.2013.07.079 . (PMID: 10.1016/j.neuroimage.2013.07.07923954727) de Cheveigné, A., & Parra, L.C. (2014). Joint decorrelation, a versatile tool for multichannel data analysis. NeuroImage, 98(Supplement C), 487–505. https://doi.org/10.1016/j.neuroimage.2014.05.068 . (PMID: 10.1016/j.neuroimage.2014.05.06824990357) De Bie, T., Cristianini, N., Rosipal, R. (2005). Eigenproblems in pattern recognition. In Handbook of geometric computing (pp. 129–167). Springer. De Vos, M., Riès, S., Vanderperren, K., Vanrumste, B., Alario, F.X., Huffel, V.S., Burle, B. (2010). Removal of muscle artifacts from EEG recordings of spoken language production. Neuroinformatics, 8(2), 135–150. https://doi.org/10.1007/s12021-010-9071-0 . (PMID: 10.1007/s12021-010-9071-020480401) Devlaminck, D., Wyns, B., Grosse-Wentrup, M., Otte, G., Santens, P. (2011). Multisubject learning for common spatial patterns in motor-imagery BCI. Intelligence Neuroscience, 2011, 8:8–8:8. https://doi.org/10.1155/2011/217987 . (PMID: 10.1155/2011/217987) Engemann, D.A., & Gramfort, A. (2015). Automated model selection in covariance estimation and spatial whitening of MEG and EEG signals. NeuroImage, 108, 328–342. https://doi.org/10.1016/j.neuroimage.2014.12.040 . (PMID: 10.1016/j.neuroimage.2014.12.04025541187) Farina, D., Jiang, N., Rehbaum, H., Holobar, A., Graimann, B., Dietl, H., Aszmann, O.C. (2014). The extraction of neural information from the surface EMG for the control of upper-limb prostheses: emerging avenues and challenges. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 22(4), 797–809. https://doi.org/10.1109/TNSRE.2014.2305111 . (PMID: 10.1109/TNSRE.2014.230511124760934) Farquhar, J., & Hill, N.J. (2013). Interactions between pre-processing and classification methods for event-related-potential classification. Neuroinformatics, 11(2), 175–192. https://doi.org/10.1007/s12021-012-9171-0 . (PMID: 10.1007/s12021-012-9171-023250668) Farquhar, J., Hill, N., Lal, T.N., Schölkopf, B. (2006). Regularised CSP for sensor selection in BCI. In Proceedings of the 3rd international BCI workshop. Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861–874. (PMID: 10.1016/j.patrec.2005.10.010) Frey, J., Daniel, M., Hachet, M., Castet. J., Lotte, F. (2016). Framework for electroencephalography-based evaluation of user experience. InProcedings of CHI (pp. 2283–2294). Grosse-Wentrup, M., Liefhold, C., Gramann, K., Buss, M. (2009). Beamforming in non invasive brain-computer interfaces. IEEE Transactions on Biomedical Engineering, 56(4), 1209–1219. (PMID: 10.1109/TBME.2008.200976819423426) Hyvarinen, A. (1999). Fast and robust fixed-point algorithms for independent component analysis. IEEE Transactions on Neural Networks, 10(3), 626–634. https://doi.org/10.1109/72.761722 . (PMID: 10.1109/72.761722) Kang, H., Nam, Y., Choi, S. (2009). Composite common spatial pattern for subject-to-subject transfer. IEEE Signal Processing Letters, 16(8), 683–686. https://doi.org/10.1109/LSP.2009.2022557 . (PMID: 10.1109/LSP.2009.2022557) Kenney, J.F. (2013). Mathematics of statistics. Toronto: D. Van Nostrand Company Inc. Princeton; New Jersey; London; New York,; Affiliated East-West Press Pvt-Ltd; New Delhi. Koles, Z.J. (1991). The quantitative extraction and topographic mapping of the abnormal components in the clinical EEG. Electroencephalography and clinical Neurophysiology, 79(6), 440–447. (PMID: 10.1016/0013-4694(91)90163-X1721571) Krusienski, D., Grosse-Wentrup, M., Galán, F., Coyle, D., Miller, K., Forney, E., Anderson, C. (2011). Critical issues in state-of-the-art brain-computer interface signal processing. Journal of Neural Engineering, 8(2), 025,002. (PMID: 10.1088/1741-2560/8/2/025002) Ledoit, O., & Wolf, M. (2004). A well-conditioned estimator for large-dimensional covariance matrices. Journal of Multivariate Analysis, 88(2), 365–411. https://doi.org/10.1016/S0047-259X(03)00096-4 . (PMID: 10.1016/S0047-259X(03)00096-4) Lotte, F. (2015). Signal processing approaches to minimize or suppress calibration time in oscillatory activity-based brain-computer interfaces. Proceedings of the IEEE, 103(6), 871–890. https://doi.org/10.1109/JPROC.2015.2404941 . (PMID: 10.1109/JPROC.2015.2404941) Lotte, F., & Guan, C. (2010). Learning from other subjects helps reducing brain-computer interface calibration time. In 2010 IEEE International conference on acoustics, speech and signal processing (pp. 614–617). https://doi.org/10.1109/ICASSP.2010.5495183 . Lotte, F., & Guan, C. (2011). Regularizing common spatial patterns to improve BCI designs: unified theory and new algorithms. IEEE Transactions on Biomedical Engineering, 58(2), 355–362. https://doi.org/10.1109/TBME.2010.2082539 . (PMID: 10.1109/TBME.2010.208253920889426) Lu, H., Eng, H.L., Guan, C., Plataniotis, K.N., Venetsanopoulos, A.N. (2010). Regularized common spatial pattern with aggregation for EEG classification in small-sample setting. IEEE Transactions on Biomedical Engineering, 57(12), 2936–2946. https://doi.org/10.1109/TBME.2010.2082540 . (PMID: 10.1109/TBME.2010.208254020889425) Mahmud, M., Kaiser, M.S., Hussain, A., Vassanelli, S. (2018). Applications of deep learning and reinforcement learning to biological data. IEEE Transactions on Neural Networks and Learning Systems, 29(6), 2063–2079. https://doi.org/10.1109/TNNLS.2018.2790388 . (PMID: 10.1109/TNNLS.2018.279038829771663) Makeig, S., Debener, S., Onton, J., Delorme, A. (2004). Mining event-related brain dynamics. Trends in Cognitive Sciences, 8(5), 204–210. https://doi.org/10.1016/j.tics.2004.03.008 . (PMID: 10.1016/j.tics.2004.03.00815120678) Makeig, S., Kothe, C., Mullen, T., Bigdely-Shamlo, N., Zhang, Z., Kreutz-Delgado, K. (2012). Evolving signal processing for brain-computer interfaces. Proceedings of the IEEE, 100(Special Centennial Issue), 1567–1584. https://doi.org/10.1109/JPROC.2012.2185009 . (PMID: 10.1109/JPROC.2012.2185009) Mattout, J., Phillips, C., Penny, W.D., Rugg, M.D., Friston, K.J. (2006). MEG source localization under multiple constraints: an extended Bayesian framework. NeuroImage, 30(3), 753–767. https://doi.org/10.1016/j.neuroimage.2005.10.037 . (PMID: 10.1016/j.neuroimage.2005.10.03716368248) Meinel, A., Castaño-Candamil, S, Reis, J., Tangermann, M. (2016). Pre-trial EEG-based single-trial motor performance prediction to enhance neuroergonomics for a hand force task. Frontiers in Human Neuroscience, 10, 170. https://doi.org/10.3389/fnhum.2016.00170 . (PMID: 10.3389/fnhum.2016.00170271997014843706) Meinel, A., Lotte, F., Tangermann, M. (2017). Tikhonov regularization enhances EEG-based spatial filtering for single-trial regression. In Proceedings of the 7th Graz brain-computer interface conference 2017 (pp. 308-313). https://doi.org/10.3217/978-3-85125-533-1-57 . Millán, J.d.R., Rupp, R., Mueller-Putz, G., Murray-Smith, R., Giugliemma, C., Tangermann, M., Vidaurre, C., Cincotti, F., Kübler, A, Leeb, R., Neuper, C., Müller, K.-R, Mattia, D. (2010). Combining brain–computer interfaces and assistive technologies: state-of-the-art and challenges. Frontiers in Neuroscience, 4, 161. (PMID: 208774342944670) Nicolae, I.E., Acqualagna, L., Blankertz, B. (2017). Assessing the depth of cognitive processing as the basis for potential user-state adaptation. Frontiers in Neuroscience, 11. https://doi.org/10.3389/fnins.2017.00548 . Park, S.H., Lee, D., Lee, S.G. (2017). Filter bank regularized common spatial pattern ensemble for small sample motor imagery classification. IEEE Transactions on Neural Systems and Rehabilitation Engineering, PP(99), 1–1. https://doi.org/10.1109/TNSRE.2017.2757519 . (PMID: 10.1109/TNSRE.2017.2757519 https://doi.org/10.1109/TNSRE.2017.2757519) Parra, L.C., Spence, C.D., Gerson, A.D., Sajda, P. (2005). Recipes for the linear analysis of EEG. NeuroImage, 28(2), 326–341. (PMID: 10.1016/j.neuroimage.2005.05.03216084117) Ramanathan, C., Ghanem, R.N., Jia, P., Ryu, K., Rudy, Y. (2004). Noninvasive electrocardiographic imaging for cardiac electrophysiology and arrhythmia. Nature Medicine, 10(4), nm1011. https://doi.org/10.1038/nm1011 . (PMID: 10.1038/nm1011) Ramoser, H., Muller-Gerking, J., Pfurtscheller, G. (2000). Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE Transactions on Rehabilitation Engineering, 8(4), 441–446. (PMID: 10.1109/86.89594611204034) Reuderink, B., & Poel, M. (2008). Robustness of the common spatial patterns algorithm in the BCI-pipeline. Tech rep. HMI, University of Twente. Samek, W., Vidaurre, C., Müller, K.-R., Kawanabe, M. (2012). Stationary common spatial patterns for brain-computer interfacing. Journal of Neural Engineering, 9(2), 026,013. https://doi.org/10.1088/1741-2560/9/2/026013 . (PMID: 10.1088/1741-2560/9/2/026013) Samek, W., Meinecke, F.C., Müller, K.-R. (2013). Transferring subspaces between subjects in brain-computer interfacing. IEEE Transactions on Biomedical Engineering, 60(8), 2289–2298. https://doi.org/10.1109/TBME.2013.2253608 . (PMID: 10.1109/TBME.2013.225360823529075) Samek, W., Kawanabe, M., Müller, K.-R. (2014). Divergence-based framework for common spatial patterns algorithms. IEEE Reviews in Biomedical Engineering, 7, 50–72. https://doi.org/10.1109/RBME.2013.2290621 . (PMID: 10.1109/RBME.2013.229062124240027) Schäfer, J., & Strimmer, K. (2005). A shrinkage approach to large-scale covariance matrix estimation and implications for functional genomics. Statistical Applications in Genetics and Molecular Biology, 4, 1. (PMID: 10.2202/1544-6115.1175) Schultze-Kraft, M., Dähne, S, Gugler, M., Curio, G., Blankertz, B. (2016). Unsupervised classification of operator workload from brain signals. Journal of Neural Engineering, 13(3), 036,008. https://doi.org/10.1088/1741-2560/13/3/036008 . (PMID: 10.1088/1741-2560/13/3/036008) Tian, T.S., Huang, J.Z., Shen, H., Li, Z. (2013). EEG/MEG source reconstruction with spatial-temporal two-way regularized regression. Neuroinformatics, 11(4), 477–493. https://doi.org/10.1007/s12021-013-9193-2 . (PMID: 10.1007/s12021-013-9193-223842791) Tikhonov, A.N. (1963). Regularization of incorrectly posed problems. Soviet Mathematics Doklady, 4, 1624–1627. Úbeda, A., Azorín, J.M., Chavarriaga, R., Millán, J.d.R. (2017). Classification of upper limb center-out reaching tasks by means of EEG-based continuous decoding techniques. Journal of NeuroEngineering and Rehabilitation, 14, 9. https://doi.org/10.1186/s12984-017-0219-0 . (PMID: 10.1186/s12984-017-0219-0281436035286813) Wang, H., & Li, X. (2016). Regularized filters for L1-norm-based common spatial patterns. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 24(2), 201–211. https://doi.org/10.1109/TNSRE.2015.2474141 . (PMID: 10.1109/TNSRE.2015.247414126336136) Winkler, I., Brandl, S., Horn, F., Waldburger, E., Allefeld, C., Tangermann, M. (2014). Robust artifactual independent component classification for bci practitioners. Journal of Neural Engineering, 11(3), 035,013. (PMID: 10.1088/1741-2560/11/3/035013) Wu, D., King, J.T., Chuang, C.H., Lin, C.T., Jung, T.P. (2017). Spatial filtering for EEG-based regression problems in brain-computer interface (BCI). IEEE Transactions on Fuzzy Systems, PP(99), 1–1. https://doi.org/10.1109/TFUZZ.2017.2688423 . (PMID: 10.1109/TFUZZ.2017.2688423) |
| Grant Information: | bwHPC International Ministerium für Wissenschaft, Forschung und Kunst Baden-Württemberg; EXC 1086 International Deutsche Forschungsgemeinschaft; INST 39/963-1 FUGG International Deutsche Forschungsgemeinschaft; ANR-15-CE23-0013-01 International Agence Nationale de la Recherche; ERC-2016-STG-714567 International H2020 European Research Council |
| Contributed Indexing: | Keywords: Brain state decoding algorithm; Brain-computer interface; EEG bandpower; Single trial analysis; Source power comodulation; Subspace decomposition |
| Entry Date(s): | Date Created: 20180822 Date Completed: 20190821 Latest Revision: 20210216 |
| Update Code: | 20250114 |
| DOI: | 10.1007/s12021-018-9396-7 |
| PMID: | 30128674 |
| Database: | MEDLINE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstract: | We report on novel supervised algorithms for single-trial brain state decoding. Their reliability and robustness are essential to efficiently perform neurotechnological applications in closed-loop. When brain activity is assessed by multichannel recordings, spatial filters computed by the source power comodulation (SPoC) algorithm allow identifying oscillatory subspaces. They regress to a known continuous trial-wise variable reflecting, e.g. stimulus characteristics, cognitive processing or behavior. In small dataset scenarios, this supervised method tends to overfit to its training data as the involved recordings via electroencephalogram (EEG), magnetoencephalogram or local field potentials generally provide a low signal-to-noise ratio. To improve upon this, we propose and characterize three types of regularization techniques for SPoC: approaches using Tikhonov regularization (which requires model selection via cross-validation), combinations of Tikhonov regularization and covariance matrix normalization as well as strategies exploiting analytical covariance matrix shrinkage. All proposed techniques were evaluated both in a novel simulation framework and on real-world data. Based on the simulation findings, we saw our expectations fulfilled, that SPoC regularization generally reveals the largest benefit for small training sets and under severe label noise conditions. Relevant for practitioners, we derived operating ranges of regularization hyperparameters for cross-validation based approaches and offer open source code. Evaluating all methods additionally on real-world data, we observed an improved regression performance mainly for datasets from subjects with initially poor performance. With this proof-of-concept paper, we provided a generalizable regularization framework for SPoC which may serve as a starting point for implementing advanced techniques in the future. |
|---|---|
| ISSN: | 1559-0089 |
| DOI: | 10.1007/s12021-018-9396-7 |