Divergence-based framework for common spatial patterns algorithms

IEEE Reviews in Biomedical Engineering

Volumn 7, Issue , 2014, Pages 50-72

  Samek, Wojciech ^a   Kawanabe, Motoaki ^b   Muller, Klaus Robert ^a,c  

^a TECHNISCHE UNIVERSITÄT BERLIN   (Germany)

^b ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

^c Korea University   (South Korea)

Author keywords

Brain computer interfaces; information geometry; spatial filters

Indexed keywords

BRAIN COMPUTER INTERFACE; FEATURE EXTRACTION; INTERFACES (COMPUTER); OPTIMIZATION;

COMMON SPATIAL PATTERNS; DIVERGENCE PROBLEMS; HIGH-DIMENSIONAL; INFORMATION GEOMETRY; MAXIMIZATION PROBLEM; REGULARIZATION SCHEMES; SPATIAL FILTERINGS; SPATIAL FILTERS;

ALGORITHMS;

ARTICLE; BRAIN COMPUTER INTERFACE; COMMON SPATIAL PATTERN ALGORITM; ELECTRIC ACTIVITY; ELECTRODE; ELECTROENCEPHALOGRAM; ELECTROENCEPHALOGRAPHY; EYE MOVEMENT; EYELID REFLEX; FILTRATION; HUMAN; IMAGERY; INFORMATION SCIENCE; LEARNING ALGORITHM; MENTAL HEALTH; MOTOR CORTEX; NEUROPHYSIOLOGY; PROBABILITY; SPATIAL ANALYSIS; ALGORITHM; SIGNAL PROCESSING;

ALGORITHMS; BRAIN-COMPUTER INTERFACES; ELECTROENCEPHALOGRAPHY; HUMANS; SIGNAL PROCESSING, COMPUTER-ASSISTED;

EID: 84899454044     PISSN: 19373333     EISSN: 19411189     Source Type: Journal    
DOI: 10.1109/RBME.2013.2290621     Document Type: Article

References (99)

1. G. Dornhege, J. del R. Milĺan, T. Hinterberger, D. McFarland, andK.-R. M̈uller, Eds., Toward Brain-Computer Interfacing. Cambridge,MA, USA: MIT Press, 2007.
2. J. Wolpaw and E. W. Wolpaw, Eds., Brain-Computer Interfaces: Principlesand Practice. Oxford, U.K.: Oxford Univ. Press, 2012.
3. B. Blankertz, R. Tomioka, S. Lemm, M. Kawanabe, and K.-R. M̈uller,"Optimizing spatial filters for robust EEG single-trial analysis," IEEESignal Proc. Mag., vol. 25, no. 1, pp. 41-56, Jan. 2008.
4. H. Ramoser, J. M̈uller-Gerking, and G. Pfurtscheller, "Optimal spatialfiltering of single trial EEG during imagined hand movement," IEEETrans. Rehabil. Eng., vol. 8, no. 4, pp. 441-446, Dec. 2000. (Pubitemid 32178931)
5. L. C. Parra, C. D. Spence, A. D. Gerson, and P. Sajda, "Recipesfor the linear analysis of EEG," NeuroImage, vol. 28, pp. 326-341,2005.
6. S. Lemm, B. Blankertz, T. Dickhaus, and K.-R. M̈uller, "Introduction tomachine learning for brain imaging," NeuroImage, vol. 56, no. 2, pp. 387-399, 2011.
7. F. Lotte and C. Guan, "Regularizing common spatial patterns to improveBCI designs: Unified theory and new algorithms," IEEE Trans. Biomed.Eng., vol. 58, no. 2, pp. 355-362, Feb. 2011.
8. P. Sajda, A. Gerson, K.-R. M̈uller, B. Blankertz, and L. Parra, "A dataanalysis competition to evaluate machine learning algorithms for usein brain-computer interfaces," IEEE Trans. Neural Syst. Rehabil. Eng.,vol. 11, no. 2, pp. 184-185, Jun. 2003. (Pubitemid 36935054)
9. B. Blankertz, K.-R. M̈uller, G. Curio, T. Vaughan, G. Schalk, J. Wolpaw,A. Schl̈ogl, C. Neuper, G. Pfurtscheller, T. Hinterberger,M. Schr̈oder, andN. Birbaumer, "The BCI competition 2003: Progress and perspectives indetection and discrimination of EEG single trials," IEEE Trans. Biomed.Eng., vol. 51, no. 6, pp. 1044-1051, Jun. 2004. (Pubitemid 38661460)
10. B. Blankertz, K.-R. M̈uller, D. Krusienski, G. Schalk, J. Wolpaw,A. Schl̈ogl, G. Pfurtscheller, J. del R. Milĺan, M. Schr̈oder, andN. Birbaumer, "The BCI competition III: Validating alternative approachesto actual BCI problems," IEEE Trans. Neural Syst. Rehabil.Eng., vol. 14, no. 2, pp. 153-159, Jun. 2006. (Pubitemid 44150230)
11. M. Tangermann, K.-R. M̈uller, A. Aertsen, N. Birbaumer, C. Braun, C.Brunner, R. Leeb, C. Mehring, K. J. Miller, G. M̈uller-Putz, G. Nolte, G.Pfurtscheller, H. Preissl, G. Schalk, A. Schl̈ogl, C. Vidaurre, S. Waldert,and B. Blankertz, "Review of the BCI competition IV," Front. Neurosci.,vol. 6, no. 55, 2012.
12. D. J. McFarland, L. M. McCane, S. V. David, and J. R. Wolpaw, "Spatialfilter selection for EEG-based communication," Electroencephalogr. Clin.Neurophysiol., vol. 103, no. 3, pp. 386-394, 1997.
13. B. Blankertz, C. Sannelli, S. Halder, E. M. Hammer, A. K̈ubler,K.-R. M̈uller, G. Curio, and T. Dickhaus, "Neurophysiological predictorof SMR-based BCI performance," NeuroImage, vol. 51, no. 4pp. 1303-1309, 2010.
14. T. P. Jung, S. Makeig,C.Humphries, T. W. Lee, M. J.McKeown,V. Iragui,and T. J. Sejnowski, "Removing electroencephalographic artifacts byblind source separation," Psychophysiology, vol. 37, no. 2, pp. 163-178,2000. (Pubitemid 30140282)
15. N. Ille, P. Berg, and M. Scherg, "Artifact correction of the ongoing EEGusing spatial filters based on artifact and brain signal topographies,"J. Clin. Neurophysiol., vol. 19, no. 2, pp. 113-124, 2002. (Pubitemid 34538845)
16. C. Sannelli, M. Braun, and K.-R. M̈uller, "Improving BCI performanceby task-related trial pruning," Neural Netw., vol. 22, no. 9, pp. 1295-1304,2009.
17. P. Shenoy, M. Krauledat, B. Blankertz, R. P. Rao, and K.-R. M̈uller, "Towardsadaptive classification for BCI," J. Neural Eng., vol. 3, no. 1,pp. R13-R23, 2006.
18. W. Samek, C. Vidaurre, K.-R. M̈uller, and M. Kawanabe, "Stationarycommon spatial patterns for brain-computer interfacing," J. Neural Eng.,vol. 9, no. 2, p. 026013, 2012.
19. M. Arvaneh, C. Guan, K. K. Ang, and C. Quek, "Optimizing spatial filtersby minimizing within-class dissimilarities in electroencephalogram- basedbrain-computer interface," IEEE Trans. Neural Netw. Learn. Syst., vol. 24,no. 4, pp. 610-619, Apr. 2013.
20. S. Amari and A. Cichocki, "Information geometry of divergence functions,"Bull. Polish Acad. Sci.: Tech. Sci., vol. 58, no. 1, pp. 183-195,2010.
21. H. Berger, "Ü ber das Elektrenkephalogramm des Menschen II," J. fürPsychologie und Neurologie, vol. 40, pp. 160-179, 1930.
22. G. Pfurtscheller and F. L. da Silva, "Event-related EEG/MEG synchronizationand desynchronization: Basic principles.," Clin. Neurophysiol.,vol. 110, no. 11, pp. 1842-1857, 1999. (Pubitemid 29454610)
23. E. Niedermeyer and F. L. da Silva, Electroencephalography: Basic Principles,Clinical Applications, and Related Fields, 5th ed. Philadelphia,PA, USA: Lippincott Williams & Wilkins, 2004.
24. B. Blankertz, S. Lemm, M. S. Treder, S.Haufe, and K.-R.M̈uller, "Singletrialanalysis and classification of ERP components-A tutorial," NeuroImage,vol. 56, no. 2, pp. 814-825, 2011.
25. C. M. Michel, M. M. Murray, G. Lantz, S. Gonzalez, L. Spinelli, andR. G. de Peralta, "EEG source imaging," Clin. Neurophysiol., vol. 115,no. 10, pp. 2195-2222, 2004. (Pubitemid 39200787)
26. H. Lu, K. Plataniotis, and A. Venetsanopoulos, "Regularized commonspatial patterns with generic learning for EEG signal classification, " inProc. IEEE Int. Conf. Eng. Med. Biol. Soc., 2009, pp. 6599-6602.
27. M. Kawanabe and C. Vidaurre, "Improving BCI performance by modifiedcommon spatial patterns with robustly averaged covariance matrices," inProc. Int. Work-Conf. Artif. Neural Netw., 2009, pp. 279-282.
28. M. Kawanabe, W. Samek, K.-R. M̈uller, and C. Vidaurre, "Robust commonspatial filters with a maxmin approach," Neural Comput., vol. 26,no. 2, pp. 1-28, 2014.
29. M. Krauledat, "Analysis of nonstationarities in EEG signals for improvingbrain-computer interface performance," Ph.D. dissertation, Dept. Softw.Eng. Theoretical Comput. Sci., Technische Universiẗat Berlin, Berlin,Germany, 2008.
30. A. Bamdadian, C. Guan, K. K. Ang, and J. Xu, "Online semi-supervisedlearning with KL distance weighting for motor imagery-based BCI," inProc. IEEE Int. Conf. Eng. Med. Biol. Soc., 2012, pp. 2732-2735.
31. W. Samek, F. C. Meinecke, and K.-R. M̈uller, "Transferring subspacesbetween subjects in brain-computer interfacing," IEEE Trans. Biomed.Eng., vol. 60, no. 8, pp. 2289-2298, Aug. 2013.
32. M. Krauledat, M. Tangermann, B. Blankertz, and K.-R. M̈uller, "Towardszero training for brain-computer interfacing," PloS one, vol. 3, no. 8,p. e2967, 2008.
33. F. Lotte and C. Guan, "Learning from other subjects helps reducing Brain-Computer interface calibration time," in Proc. IEEE Int. Conf. Acoust.,Speech, Signal Process., 2010, pp. 614-617.
34. D. Devlaminck, B. Wyns, M. Grosse-Wentrup, G. Otte, and P. Santens,"Multi-subject learning for common spatial patterns in motor-imageryBCI," Comput. Intell. Neurosci., vol. 2011, no. 217987, pp. 1-9,2011.
35. H. Kang, Y. Nam, and S. Choi, "Composite common spatial pattern forsubject-to-subject transfer," Signal Process. Lett., vol. 16, no. 8, pp. 683-686, 2009.
36. S. Lemm, B. Blankertz, G. Curio, and K.-R.M̈uller, "Spatio-spectral filtersfor improving the classification of single trial EEG," IEEE Trans. Biomed.Eng., vol. 52, pp. 1541-1548, Sep. 2005. (Pubitemid 41462184)
37. C. Vidaurre, C. Sannelli, K.-R. M̈uller, and B. Blankertz, "Machinelearning-based coadaptive calibration for brain-computer interfaces," NeuralComput., vol. 23, no. 3, pp. 791-816, 2011.
38. X. Yong, R. Ward, and G. Birch, "Robust common spatial patterns forEEG signal preprocessing," in Proc. IEEE Int. Conf. Eng.Med. Biol. Soc.,2008, pp. 2087-2090.
39. H. Lu, H.-L. Eng, C. Guan, K. Plataniotis, and A. Venetsanopoulos, "Regularizedcommon spatial pattern with aggregation for EEG classificationin small-sample setting," IEEE Trans. Biomed. Eng., vol. 57, no. 12,pp. 2936-2946, Dec. 2010.
40. T. Lal, M. Schr̈oder, T. Hinterberger, J.Weston, M. Bogdan, N. Birbaumer,and B. Scḧolkopf, "Support vector channel selection in BCI," IEEE Trans.Biomed. Eng., vol. 51, no. 6, pp. 1003-1010, Jun. 2004. (Pubitemid 38661455)
41. M. Arvaneh, C. Guan, K. K. Ang, and H.-C. Quek, "Spatially sparsedcommon spatial pattern to improve BCI performance," in Proc. IEEE Int.Conf. Acoust., Speech, Signal Process., 2011, pp. 2412-2415.
42. F. Goksu, N. Ince, and A. Tewfik, "Sparse common spatial patterns inbrain computer interface applications," in Proc. IEEE Int. Conf. Acoust.,Speech Signal Process., 2011, pp. 533-536.
43. M. Grosse-Wentrup, K. Gramann, and M. Buss, "Adaptive spatial filterswith predefined region of interest for EEG based brain-computerinterface, "in Advances in Neural Information Processing Systems 19.Cambridge, MA, USA: MIT Press, 2007, pp. 537-544.
44. M. Grosse-Wentrup, C. Liefhold, K. Gramann, andM. Buss, "Beamformingin noninvasive brain computer interfaces," IEEE Trans. Biomed. Eng.,vol. 56, no. 4, pp. 1209-1219, Apr. 2009.
45. C. Sannelli, C. Vidaurre, K.-R. M̈uller, and B. Blankertz, "CSP patches:An ensemble of optimized spatial filters. an evaluation study," J. NeuralEng., vol. 8, no. 2, p. 025012, 2011.
46. M. Kawanabe, C. Vidaurre, B. Blankertz, and K.-R. M̈uller, "A maxminapproach to optimize spatial filters for EEG single-trial classification," inBio-Inspired Systems: Computational and Ambient Intelligence, vol. 5515,(LNCS Series). New York, NY, USA: Springer, 2009, pp. 674-682.
47. F. Lotte and C. Guan, "Spatially regularized common spatial patterns forEEG classification," in Proc. Int. Conf. Pattern Recognit., 2010, pp. 3712-3715.
48. B. Blankertz, M. Kawanabe, R. Tomioka, F. U. Hohlefeld, V. Nikulin,and K.-R. M̈uller, "Invariant common spatial patterns: Alleviatingnonstationarities in brain-computer interfacing," in Advances in NeuralInformation Processing Systems 20. Cambridge, MA, USA: MIT Press,2008, pp. 113-120.
49. J. Park and W. Chung, "Common spatial patterns based on generalizednorms," in Proc. Int. Winter Workshop Brain-Comput. Interf., 2013,pp. 39-42.
50. H. Wang, Q. Tang, and W. Zheng, "L1-norm-based common spatial patterns,"IEEE Trans. Biomed. Eng., vol. 59, no. 3, pp. 653-662, Mar.2012.
51. W.Wu, Z. Chen, S. Gao, and E. N. Brown, "A probabilistic framework forlearning robust common spatial patterns," in Proc. IEEE Int. Conf. Eng.Med. Biol. Soc., 2009, pp. 4658-4561.
52. W. Samek, D. Blythe, K.-R. M̈uller, and M. Kawanabe, "Robust spatialfiltering with beta divergence," in Proc. Adv. Neural Inf. Process. Syst. 26(NIPS), 2013, pp. 1007-1015.
53. J. Quionero-Candela, M. Sugiyama, A. Schwaighofer, andN. D. Lawrence, Eds., Dataset Shift in Machine Learning. Cambridge,MA, USA: MIT Press, 2009.
54. M. Sugiyama and M. Kawanabe, Machine Learning in Non- StationaryEnvironments: Introduction to Covariate Shift Adaptation. Cambridge,MA, USA: MIT Press, 2011.
55. P. von B̈unau, F. Meinecke, S. Scholler, and K.-R. M̈uller, "Finding stationarybrain sources in EEG data," in Proc. IEEE Int. Conf. Eng. Med.Biol. Soc., 2010, pp. 2810-2813.
56. W. Samek, K.-R.M̈uller,M.Kawanabe, andC.Vidaurre, "Brain-computerinterfacing in discriminative and stationary subspaces," in Proc. IEEE Int.Conf. Eng. Med. Biol. Soc., 2012, pp. 2873-2876.
57. W. Samek, M. Kawanabe, and C. Vidaurre, "Group-wise stationary subspaceanalysis-A novel method for studying non-stationarities," in Proc.Int. Brain-Comput. Interf. Conf., 2011, pp. 16-20.
58. B. Reuderink, "Robust brain-computer interfaces," Ph.D. dissertation,Dept. Comput. Sci., University of Twente, Enschede, The Netherlands,2011.
59. M. Arvaneh, C. Guan, K. K. Ang, and C. Quek, "EEG data space adaptationto reduce intersession nonstationarity in brain-computer interface,"Neural Comput., vol. 25, no. 8, pp. 2146-2171, 2013.
60. S. Fazli, F. Popescu, M. Dańoczy, B. Blankertz, K.-R. M̈uller, andC. Grozea, "Subject-independent mental state classification in single trials,"Neural Netw., vol. 22, no. 9, pp. 1305-1312, 2009.
61. R. Tomioka, J. Hill, B. Blankertz, and K. Aihara, "Adapting spatial filtermethods for nonstationary BCIs," in Proc. Workshop Inf.-Based Induct.Sci., 2006, pp. 65-70.
62. H. Kang and S. Choi, "Bayesian multi-task learning for common spatialpatterns," in Proc. Int. Workshop Pattern Recognit. NeuroImag., 2011,pp. 61-64.
63. W. Samek, A. Binder, and K.-R. M̈uller, "Multiple kernel learning forbrain-computer interfacing," in Proc. IEEE Int. Conf. Eng. Med. Biol.Soc., 2013, pp. 7048-7051.
64. H. Wang and W. Zheng, "Local temporal common spatial patterns forrobust single-trial EEG classification," IEEE Trans. Neural Syst. Rehabil.Eng., vol. 16, no. 2, pp. 131-139, Apr. 2008. (Pubitemid 351519528)
65. H. Wang, "Discriminant and adaptive extensions to local temporal commonspatial patterns," Pattern Recognit. Lett., vol. 34, no. 10, pp. 1125-1129, 2013.
66. H. Wang and D. Xu, "Comprehensive common spatial patterns with temporalstructure information of EEG data: Minimizing nontask related EEGcomponent," IEEE Trans. Biomed. Eng., vol. 59, no. 9, pp. 2496-2505,Sep. 2012.
67. M. Grosse-Wentrup and M. Buss, "Multiclass common spatial patternsand information theoretic feature extraction," IEEE Trans. Biomed. Eng.,vol. 55, no. 8, pp. 1991-2000, Aug. 2008. (Pubitemid 352013536)
68. C. Gouy-Pailler,M. Congedo, C. Brunner, C. Jutten, and G. Pfurtscheller,"Nonstationary brain source separation for multiclass motor imagery,"IEEE Trans. Biomed. Eng., vol. 57, no. 2, pp. 469-478, Feb. 2010.
69. T.-H. Nguyen, S.-M. Park, K.-E. Ko, and K.-B. Sim, "Multi-class stationaryCSP for optimal feature separation of brain source in BCI system," inProc. Int. Conf. Control, Autom. Syst., 2012, pp. 1035-1039.
70. H. Wang, "Harmonic mean of Kullback-Leibler divergences for optimizingmulti-class EEG spatio-temporal filters," Neural Process. Lett.,vol. 36, no. 2, pp. 161-171, 2012.
71. H. Zhang, H. Yang, and C. Guan, "Bayesian learning for spatial filteringin an EEG-based brain-computer interface," IEEE Trans. Neural Netw.Learn. Syst., vol. 24, no. 7, pp. 1049-1060, Jul. 2013.
72. E. A. Mousavi, J. J. Maller, P. B. Fitzgerald, and B. J. Lithgow, "Waveletcommon spatial pattern in asynchronous offline brain computer interfaces,"Biomed. Signal Process. Control, vol. 6, no. 2, pp. 121-128,2011.
73. O. Falzon, K. P. Camilleri, and J. Muscat, "The analytic common spatialpatterns method for EEG-based BCI data," J. Neural Eng., vol. 9, no. 4,p. 045009, 2012.
74. D. Fattahi, B. Nasihatkon, and R. Boostani, "A general framework toestimate spatial and spatio-spectral filters for EEG signal classification,"Neurocomputing, vol. 119, pp. 165-174, 2013.
75. X. Li, H. Zhang, C. Guan, S. H. Ong, K. K. Ang, and Y. Pan, "Discriminativelearning of propagation and spatial pattern for motor imagery EEGanalysis," Neural Comput., vol. 25, no. 10, pp. 2709-2733, 2013.
76. M. Alamgir, M. Grosse-Wentrup, and Y. Altun, "Multitask learning forbrain-computer interfaces," in Proc. 13th Int. Conf. Artif. Intell. Statist.,2010, pp. 17-24.
77. M. Sugiyama,M.Krauledat, and K.-R.M̈uller, "Covariate shift adaptationby importance weighted cross validation," J. Mach. Learn. Res., vol. 8,pp. 985-1005, 2007. (Pubitemid 46798411)
78. C. Vidaurre,M. Kawanabe, P. von B̈unau, B. Blankertz, and K.-R.M̈uller,"Toward unsupervised adaptation of LDA for brain-computer interfaces,"IEEE Trans. Biomed. Eng., vol. 58, no. 3, pp. 587-597, Mar. 2011.
79. Y. Li and C. Guan, "An extended EMalgorithm for joint feature extractionand classification in brain-computer interfaces," Neural Comput., vol. 18,no. 11, pp. 2730-2761, 2006. (Pubitemid 44684605)
80. R. Tomioka and K.-R. M̈uller, "A regularized discriminative frameworkfor EEG analysis with application to brain-computer interface,"NeuroImage, vol. 49, no. 1, pp. 415-432, 2009.
81. A. Barachant, S. Bonnet, M. Congedo, and C. Jutten, "Common spatialpattern revisited by Riemannian geometry," in Proc. IEEE Int. WorkshopMultimedia Signal Process., 2010, pp. 472-476.
82. A. Barachant, S. Bonnet, M. Congedo, and C. Jutten, "Multiclass braincomputerinterface classification by Riemannian geometry," IEEE Trans.Biomed. Eng., vol. 59, no. 4, pp. 920-928, Apr. 2012.
83. A. Hyv̈arinen, "Survey on independent component analysis," Neural Comput.Surv., vol. 2, pp. 94-128, 1999.
84. M. Kawanabe, W. Samek, P. von B̈unau, and F. Meinecke, "An informationgeometrical view of stationary subspace analysis," in ArtificialNeural Networks and Machine Learning-ICANN 2011, ser. LNCS, 2011,pp. 397-404.
85. S. Amari, H. Nagaoka, and D. Harada, Methods of Information Geometry.Providence, RI, USA: American Mathematical Society, 2000.
86. P. von B̈unau, F. C. Meinecke, F. C. Kiŕaly, and K.-R. M̈uller, "Findingstationary subspaces in multivariate time series," Phys. Rev. Lett., vol. 103,no. 21, p. 214101, 2009.
87. P. von B̈unau, "Stationary subspace analysis-Towards understandingnon-stationary data," Ph.D. dissertation, Dept. Softw. Eng. TheoreticalComput. Sci., Technische Universiẗat Berlin, Berlin, Germany, 2012.
88. M. D. Plumbley, "Geometrical methods for non-negative ICA: Manifolds,lie groups and Toral subalgebras," Neurocomputing, vol. 67, pp. 161-197,2005. (Pubitemid 40945717)
89. A. Hyv̈arinen, "Fast and robust fixed-point algorithms for independentcomponent analysis," IEEE Trans. Neural Netw., vol. 10, no. 3, pp. 626-634, May 1999.
90. S. Eguchi and Y. Kano, "Robustifying maximum likelihood estimation,"Tokyo Institute of Statistical Mathematics, Tokyo, Japan, Tech. Rep. Res.Memo. 802, 2001.
91. A. Basu, I. R. Harris, N. L. Hjort, and M. C. Jones, "Robust and efficientestimation by minimising a density power divergence," Biometrika,vol. 85, no. 3, pp. 549-559, 1998.
92. N. Murata, T. Takenouchi, and T. Kanamori, "Information geometry of uboostand Bregman divergence," Neural Comput., vol. 16, pp. 1437-1481,2004. (Pubitemid 38740017)
93. A. Cichocki and S. Amari, "Families of alpha-beta-and gamma-divergences:Flexible and robust measures of similarities," Entropy, vol. 12,no. 6, pp. 1532-1568, 2010.
94. I. Guyon and A. Elisseeff, "An introduction to variable and feature selection,"J. Mach. Learn. Res., vol. 3, pp. 1157-1182, 2003.
95. G. Montavon, M. Braun, T. Kr̈uger, and K.-R. M̈uller, "Analyzing localstructure in kernel-based learning: Explanation, complexity, and reliabilityassessment," IEEE Signal Process. Mag., vol. 30, no. 4, pp. 62-74, Jul.2013.
96. F. Bießmann, S. M. Plis, F. C. Meinecke, T. Eichele, and K.-R. M̈uller,"Analysis of multimodal neuroimaging data," IEEE Rev. Biomed. Eng.,vol. 4, pp. 26-58, Oct. 2011.
97. D. J. C. MacKay, Information Theory, Inference & Learning Algorithms.New York, NY, USA: Cambridge Univ. Press, 2002.
98. K. B. Petersen and M. S. Pedersen. (2008). "The Matrix Cookbook," [Online]. Available: http://matrixcookbook.com/
99. R. Bhatia, Matrix Analysis, vol. 169, (Graduate Texts in Mathematicsseries). New York, NY, USA: Springer, 1997.