پایان نامه بهبود روش فیلترینگ الگوی مکانی مشترک جهت ارتقاء راندمان سیستم های واسط کامپیوتری مغزی

فهرست:

فصل اول. مقدمه.......................................................................................................... 1

1-1- مغز انسان و فعالیت­های آن ....................................................................................................................................2

1-2- سیستم­های واسط کامپیوتری-مغزی .................................................................................................................3

1-3- هدف اصلی این تحقیق ..........................................................................................................................................6

1-3-1 شخصی­سازی کرنل CSP .......................................................................................................................... 7

      1-3-1-1 روش پیشنهادی FFT kernel CSP .....................................................................................7

      1-3-1-1روش پیشنهادی Nonlinear Synchronous kernel CSP ........................................7

1-3-2 Adaptive Kernel CSP .................................................................................................................... 7

فصل دوم. مروری بر تحقیقات گذشته..................................................................................................... 9

2-1 مروری بر کارها و تحقیقات صورت گرفته پیشین ..............................................................................................10

فصل سوم. روش تحقیق ...........................................................................................................................  14

3-1 اصول نظری اولیه ...................................................................................................................................... 15

    3-1-1 CSP ............................................................................................................................................................ 15

    3-1-2 تبدیل فوریه ................................................................................................................................................ 19

    3-1-3 همزمانی ....................................................................................................................................................... 21

           3-1-3-1 همزمانی خطی ............................................................................................................................ 23

3-2 ارایه برخی آنالیزها در مورد روش CSP ......................................................................................................... 24

    3-2-1 روش Kernel CSP ............................................................................................................................... 24

    3-2-2 روش پیشنهادی FFT Kernel CSP .............................................................................................  27

    3-2-3 روش پیشنهادی Nonlinear Synchronous Kernel CSP. .............................................. 27

           3-2-3-1 راهکار اول تزریق هم­فعالیتی بین کانال­ها ............................................................................ 27

           3-2-3-2 معرفی هم­فعالیتی تعمیم یافته و تزریق آن به فرمولاسیون CSP و kernel CSP ............. 28

    3-2-3 روش پیشنهادی Adaptive kernel CSP .................................................................................... 29

           3-2-3-1 فرمولاسیون KPC به صورت بازگشتی.................................................................................. 30

فصل چهارم.  پیاده­سازی و ارزیابی نتایج ............................................................................................  36

4-1 مجموعه داده­های مورد پردازش........................................................................................................... 37

4-2 پیاده سازی الگوریتم­ها .......................................................................................................................  39

   4-2-1 الگوریتم دسته­بندی .................................................................................................................................... 40

   4-2-2 تابع کرنل ....................................................................................................................................................... 40

   4-2-3 انتخاب ویژگی و کلاس­بندی .................................................................................................................... 41

4-3  ارزیابی نتایج ...................................................................................................................................... 42

    4-3-1 نتایج روش پیشنهادی FFT Kernel CSP ................................................................................... 43

    4-3-2 نتایج روش پیشنهادی Nonlinear Synchronous Kernel CSP .................................... 46

    4-3-3 نتایج روش پیشنهادی Adaptive Kernel CSP ........................................................................ 58

فصل پنجم . جمع بندی و پیشنهادات آتی........................................................................................... 60

فصل ششم . فهرست منابع .....................................................................................................................  64

منبع:

[1] G. J. Tortora and B. Derrickson, “Principles of Anatomy and Physiology”, USA: John Wiley & Sons.Inc, 2009.

[2] B. Graimann, B. Allison and G. Pfurtscheller, “Brain Computer Interfaces, Revolutionary Human-Computer Interaction”, Springer, pp. 331-355, 2010.

[3] J. Lehtonen, “EEG-based Brain Computer Interfaces”, In Partial Fulfillment of Requirement for the Degree of Master of Science. Helsinki University of Technology: Department of Electrical and Communications Engineering, 2002.

[4] M. J. Aminoff, D. A. Greenberg and R. P. Simon, “Clinical Neurology”, Lang Medical Books/McGraw-Hill, New York, sixth edition, pp. 174, 2005.

[5] M. Jeannerod, “Mental Imagery in the Motor Context”, Neuropsy and Chologia, J. Britain, vol.33, no. 11, pp. 1419-1432, 1995.

[6] D. Fattahi, “Presenting a novel Method to Determine Spatial Distribution of the Brain Sources during different Imagery Movements”, Master’s thesis, 2012.

[7] T. Al-Ani and D. Trad, “Signal Processing and classification approaches for Brain-Computer Interface”, Intelligent and Biosensors, book edited by Vernon S. Somerset, January 2010.

[8] B. Scholkopf, A. J. Smola, “Learning with Kernels”, MIT Press, 2002.

[9] B. Nasihatkon, “Design of a Classifier for Separation of Imagery Tasked in ALS Patients”, Master’s thesis, 2008.

[10] B. Graimann, B. Allison and G Pfurtscheller, “Brain Computer Interface: A Gentle Introduction”, Springer Berlin Heidelberg, pp. 1-27, 2010.

[11] N. Birbaumer, N. Ghanayim, T. Hinterberger, I. Iversoen, B. Kotchoubey, A. Kubler, J. Perelmouter, E. Taub and H. Flor, “A Spelling Device for the Paralysed”, Nature, 1999.

[12] B. Blankert, G. Curio and K. Muller, “Classifying Single Trial EEG: Towards Brain Computer Interfacing”, In T. G. Diettrich, S. Becker and Z. Ghahrameni, editors, Advances in Neural Information Processing Systems 14. MIT Press, 2002.

[13] K. Fukunaga and W. L. G. Koontz, “Application of the karhunen-love expansion to feature selection and ordering”, vol. C-19, no. 4, pp. 311-318, 1970.

[14] J. Muller-Gerking, and G. Pfurtscheller, “Designing Optimal Spatial Filters for Single-Trial EEG Classification in a Movement Task”, IEEE”, Clinical Neurophysiology, vol. 110, no. 4, pp. 787-798, 1999.

[15] B. Nasihatkon, R. Boostani and M. Zolghadri, “An Efficient Hybrid linear and Kernel CSP Approach for EEG Feature Extraction”, Neurocomputing, vol. 73, pp. 432-437, 2009.

[16] S. Lemm, B. Blankertz, G. Curio, and K. R. Muller, “Spatio-Spectral Filters for Improved Classification of Single Trial EEG”, IEEE Trans. Biomed.Eng, vol. 52, pp. 1541-1548, 2005.

[17] B. Nasihatkon, D. Fattahi and R. Boostani, “A General Framework to Estimate Spatial and Spatio-Spectral Filters for EEG Signal Classification”, Neurocomputing, vol. 119, pp. 165-174, 2013.

[18] S. Sun and C. Zhang, “An Optimal Kernel Feature Extractor and its Application to EEG Signal Classification”, Neurocomputing, no. 69, pp. 1743-1748, 2006.

[19] J. Zhang, J. Tang and L. Yao, “Optimizing Spatial Filters with Kernel Methods for BCI Application”, in: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications, Presented at the Society of Photo-Optical Instrumentation Engineers (SPIE) Conference, vol. 67903V, pp. 1-8, 2007.

[20] B. Scholkopf, A. J. Smola, “Learning with Kernels”, MIT Press, 2002.

[21] Y. Liu, Z. Zhao and D. Hu, “Large Scale Kernel CSP Algorithm for EEG Feature Extraction”, In Graz BCI Workshop, 2008.

[22] B. Nasihatkon, R. Boostani and M. Zolghadri, “An Efficient Hybrid linear and Kernel CSP Approach for EEG Feature Extraction”, Neurocomputing, vol. 73, pp. 432-437, 2009.

[23] Q. Zhao, T. M. Rutkoski, L. Zhang and A. Cichocki, “Generalized Optimal Spatial Filtering Using a Kernel Approach with Application to EEG Classification”, Cogn. Neurodyn, vol. 4, pp. 355-358, 2010.

[24] H. Albalawi and X. Song, “ A Study of Kernel CSP-based Motor Imagery Brain Computer Interface Classification”, Signal Processing in Medicine and Biology Symposium (SPMB), 2012.

[25] B. Nasihatkon, R. Boostani and M. Zolghadri, “An Efficient Hybrid linear and Kernel CSP Approach for EEG Feature Extraction”, Neurocomputing, vol. 73, pp. 432-437, 2009.

[26] J. Lachaux, E. Rodriguez, J, Martinerie and F. Varela, “Measuring phase synchrony in brain signal”, Hum Brain Mapp, vol. 8, pp. 194-208,1999.

[27] A. Y. Mutlu and S. Aviyente, “Multivariate Empirical Mode Decomposition for Quantifying Multivariate Phase Synchronization”, EURASIP Journal on Advances in Signal Processing, special issue on Recemt Advances in Theory and Methods for Nonstationary Signal Analysis, 2011.

[28] C. M. Sweeney-Reed and S. J. Nasuto, “A novel approach to the detection of synchronization in EEG based on empirical mode decomposition”, J Comput Neurosci, vol, 23, pp. 79-111, 2007.

[29] M. Rosenblum, A. Pikovsky, J. Kurths, C. Schafer and PA Tass, “Phase synchronization: from theory to data analysis”, Hand Book of Biological Physics, pp. 279-321, 2001.

[30] V. Sakkalis, P. Xanthopoulos, E. Zervakis, V. Tsiaras, Y. Yang, K Karakonstantaki and S. Micheloyannis, “Assessmentt of linear and nonlinear synchronization measures for analysisng EEG in a mild spileptic paradigm”, IEEE Transactions on Information Technology in Biomedical, vol. 13, pp. 433-441, 2009.

[31] T. Netoff and S. Schiff, “Decreased neuronal synchronization during experimental seizures”, J Neuroscience, vol. 22, pp. 7297-7307, 2002.

[32] R Quain Quiroga, A Kraskov, T Kreuz and P Grassberger, “Performance of different synchronization measures in real data; a case study on electroencephalographic signals”, Physical Review E, vol. 65, 2002.

[33] C. Carmeli, M.Knyazev, G. Innocenti and O. Feo, “Assessment of EEG synchronization based on state-space analysis”, Elsevier Inc NeuroImage, vol. 25, pp. 339-354, 2005.

[34] F. Mormann, “Synchronization phenomena in human epileptic brain”, PhD thesis; Dissertation in Physics, University of Bonn, Germany, 2003.

[35] F. Mormann, K. Lehnertz, P. David, C. Elger, “Mean phase coherence as a measure for phase synchronization and its application to the EEG of epilepsy patients”, Physica D, vol. 144, pp. 358-369, 2000.

[36] R Quain Quiroga, A Kraskov, T Kreuz and P Grassberger, “Performance of different synchronization measures in real data; a case study on electroencephalographic signals”, Physical Review E, vol. 65, 2002.

[37] B. Nasihatkon, “Design of a Classifier for Separation of Imagery Tasked in ALS Patients”, Master’s thesis, 2008.

[38] M. Ding, Z. Tian and Haixia Xu, “Adaptive kernel principle component analysis”, Signal Processing, Elsivier, 2010.

[39] M. Girolami, “Mercer kernel-based clustering in feature space”, IEEE Transactions, Neural Networks, vol. 13, pp. 780-784, 2002.

[40] B. Obermaier, C. Neupar, C. Guger and G. Pfurtscheller, “Information Transfer Rate in a Five-Classes Brain-Computer Interface”, IEEE Trans. On Neural Systems and Rehabilitation Eng, vol. 9, no. 3, 2001.

[41] http://www.bbci.de/competition/iii/desc_IIIa.html , 2015.

[42] J. B. MacQueen, “Some methods for classification and Analysis of Multivariate Observations”, Proceedings of 5th Berekeley Symposium on Mathematical Statistics and Probability. University of California Press. pp. 281-297, 1967.

[43] R. O. Duda, P. E. Hart and D. G. Stork, “Pattern classification”, Wiley-Interscience, 2001.

[44] C. M. Jarque and A. K. Bera, “Efficient tests for Normality, homoscedasticity and serial independence of regression residuals”, Economics Letters, pp. 255-259, 1980.

[45] http://en.wikipedia.org/wiki/Receiver_operating_characteristic, 2015.