跳到主要內容

臺灣博碩士論文加值系統

(35.175.191.36) 您好!臺灣時間:2021/07/31 01:36
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:洪至懿
研究生(外文):Chih-I Hung
論文名稱:腦電波分離及應用
論文名稱(外文):Blind Separation of electroencephalography
指導教授:吳育德
指導教授(外文):Yu-Te Wu
學位類別:博士
校院名稱:國立陽明大學
系所名稱:生物醫學影像暨放射科學系暨研究所
學門:醫藥衛生學門
學類:醫學技術及檢驗學類
論文種類:學術論文
論文出版年:2008
畢業學年度:97
語文別:中文
論文頁數:110
中文關鍵詞:腦電波獨立成份分析法小波分析大腦人機介面庫欣氏症體感覺誘發電位
外文關鍵詞:electroencephalographyindependent component analysiswavelet analysisbrain-computer interfaceCreuzfeldt-Jakob diseasesomantosensory evoked potential
相關次數:
  • 被引用被引用:1
  • 點閱點閱:387
  • 評分評分:
  • 下載下載:123
  • 收藏至我的研究室書目清單書目收藏:2
腦電波訊號(Electroencephalography, EEG)為廣泛地應用於學術研究與臨床診斷之工具。然而,非侵入式的腦電波紀錄方式(surface EEG)所擷取的資料,多半來自各種不同訊號源,包括多種腦電波、不同頻帶的腦波律動、生理雜訊和系統雜訊混合。因此,如何由混合訊號中分離雜訊和感興趣之腦波特徵是相當重要的課題。其中獨立成份分析法(Independent component analysis, ICA)和小波分析法(wavelet analysis)皆為近年來熱門的技術。獨立成份分析法可根據訊號的統計特性,由腦電波拆解出隱含其中之獨立成份,而小波分析則可針對腦電波中不同頻率的律動進行分解。拆解腦電波訊號,可望提供不同以往且深入的觀點來解讀腦電波。
本論文致力於研究與發展以獨立成份分析法和小波分析法為基礎之腦電波分解技術,進而提升腦電波之研究與應用價值。此技術之特點在於利用獨立成份分析法或小波分析法,由腦電波分解出混合其中之各種訊號成分,接著根據研究或應用需求設計成分辨識流程,以區分雜訊並萃取重要特徵。本論文中,將獨立成份分析法與小波分析應用於大腦人機介面系統之設計,輔助庫賈氏症臨床診斷,以及提升體感覺誘發電位之訊雜比。
大腦人機介面系統之研究以辨識想像左、右手手指運動之腦波特徵為基礎分為兩階段,第一階段研究發現透過獨立成分分析法可有效萃取出與想像手指運動相關之腦波特徵,大幅提高了腦波辨識率,進而改善大腦人機介面系統之運作效能。第二階段則以小波分析為基礎之時頻共同訊息法(Time-frequency cross mutual information, TFCMI),萃取出想像左右手運動時之大腦網路聯絡特徵,研究發現網路聯絡特徵提供了更有效之辨識訊號。
在庫賈氏症患者之腦電波分析中,則發現相較於阿茲海默氏患者,獨立成分分析法於庫賈氏症患者之腦電波中分解出較多種與疾病相關之腦波特徵,而此多種疾病相關腦波特徵共存的現象,可用於輔助鑑別與早期診斷庫賈氏症。
於體感覺誘發電位之應用,則是利用獨立成份分析法分解體感覺誘發電位腦電波,輔以小波分析辨識與體感覺相關之成份,相較於傳統平均運算方式,顯著提升了訊雜比。
由上述可知,不論以獨立成份或小波分析拆解過後,異於就混合訊號解讀腦電波,可獲得更豐富的訊息,值得深入多方應用於基礎研究與臨床診斷。
Electroencephalography (EEG) has been applied for the diagnosis of many neurological disorders and the investigation of human brain functions. The noninvasive EEG recordings are overlapping potentials from individual neurons as well as from the artifacts produced outside the brain. Accordingly, extraction of the disease or task-related features is crucial in the field of EEG signal processing. Blind separation of EEG signals based on independent component analysis and wavelet analysis are two effective methods for unraveling the inherent characteristics of EEG signals. The aim of this dissertation is to employ the independent component analysis and wavelet analysis to extract the motor-imagery-related features in the applications of EEG-based brain computer interface, to resolve the disease-related patterns for the assistance to early diagnosis of Creutzfeldt-Jakob disease, and to enhance the signal-to-noise ratio of Peroneal somatosensory evoked potentials.
In the first part of recognition study of motor imagery task for the application of BCI, the ICA-based technique was developed to extract the event-related synchronization features within the primary motor area. Results suggested that ICA-based analysis is effective for artifact removal and extraction reliable neural features, which in turn facilitating the classification of right and left motor imagery. In the second part, the time-frequency cross mutual information (TFCMI) based on Morelet wavelet was elaborated to construct the coupling patterns during the motor imagery task, which has been demonstrated to be informative for the significant improvement of recognition rates.
In the study of assisting early diagnosis of Creutzfeldt-Jakob disease, ICA was employed on the raw EEG signals recorded at first admissions of five patients to segregate the disease-related features from the smearing EEG. Clear CJD-related waveforms, i.e., frontal intermittent rhythmical delta activity (FIRDA), fore PSWCs (triphasic waves) and periodic lateralized epileptiform discharges (PLEDs), have been successfully and simultaneously resolved from all patients. Results show that ICA is an objective and effective means to extract the disease-related patterns for facilitating the early diagnosis of CJD.
In the study of recovering the somatoseneory evoked potential (SEP) induced by the peroneal nerve stimulations from stroke patients, the time-frequency template was first generated from the SEP of three normal subjects by Morlet wavelet. ICA was subsequently employed to decompose the EEG into a set of independent sources from which the SEP-related features were automatically selected by the TF template for reconstruction. Results demonstrated that the proposed method could remarkable suppress the artifacts and effectively reconstruct SEP waveforms in comparison with the conventional averaged method.
致謝 I
摘要 II
Abstract IV
Contents VI
List of Figures VIII
List of Tables X
Introduction 1
1.1 Blind separation of EEG 2
1.1.1 Blind source separation by independent component analysis 2
1.1.2 Time-frequency decomposition by Morlet wavelet 4
1.2 Aims of this dissertation 5
Recognition of Motor Imagery Electroencephalography Using Independent Component Analysis and Machine Classifiers 7
2.1 Abstract 8
2.2 Introduction 8
2.3 Material and Methods 12
2.3.1 Experimental Paradigm for Motor Imagery 12
2.3.2 Construction of Contralateral and Ipsilateral Rebound Maps With and Without ICA 14
2.3.3 Two-Class Supervised Classification 21
2.4 Results and Discussion 27
2.5 Conclusion 36
Recognition of Motor Imagery EEG by Time-Frequency cross Mutual Information 37
3.1 Abstract 38
3.2 Introduction 38
3.3 Methods 40
3.3.1 Motor imagery experiment and EEG recordings 40
3.3.2 Tim- frequency cross mutual information 40
3.3.3 Motor imagery classification by linear discriminat analysis 43
3.3.4 Examination of the difference of coupling patterns between right and left motor imagery 43
3.4 Results 44
3.5 Discussion 46
Blind Source Separation of concurrent disease-related patterns from EEG in Creutzfeldt-Jakob disease for assisting early diagnosis 49
4.1 Abstract 50
4.2 Introduction 50
4.3 Patients and EEG recordings 54
4.4 Method 57
4.4.1 Independent component analysis and extraction of CJD-related components 57
4.4.2 Bayesian information criterion 60
4.5 Results 62
4.5.1 Determination of the number of sources 62
4.5.2 CJD-related feature extraction 62
4.5.3 Feature extraction by PCA 66
4.5 Discussion 66
4.6 Conclusions 70
Enhancement of Signal-to-noise Ratio of Perneal Somatosensory Evoked Potential Using Independent Component Analysis and Time-frequency Template 71
5.1 Abstract 72
5.2 Introduction 72
5.3 Material and Methods 74
5.4 Results 79
5.5 Discussion and Conclusion 81
Conclusion 85
References 89
Appendix (curriculum vitae) 95
1. Au WJ, Gabor AJ, Vijayan N et al (1980) Periodic lateralized epileptiform complexes (PLEDs) in Creutzfeldt-Jakob disease. Neurology 30:611-617
2. Başar E (1998) Brain Function and Oscillations ( Volume I: Brian Oscillations. Principles and Approaches). Springer, Berlin
3. Başar E (1998) Brain Function and Oscillations (Volume II: Integrative Brain Function. Neurophysiology and Cognitive Process). Springer, Berlin
4. Bashashati A, Fatourechi M, Ward RK et al (2007) A survey of signal processing algorithms in brain-computer interfaces based on electrical brain signals. J Neural Eng 4:32-57
5. Calamante F, Mørup M, Hansen LK (2004) Defining a local arterial input function for perfusion MRI using independent component analysis. Magn Reson Med 52:789-797
6. Calautti C, Baron JC, FMedSci FRCP (2003) Functional neuroimaging studies of motor recovery after stroke in adults. Stroke 34:1553-1566
7. Cambier DM, Kantarci K, Worrell GA et al (2003) Lateralized and focal clinical, EEG, and FLAIR MRI abnormalities in Creutzfeldt-Jakob disease. Clin Neurophysiol 114:1724-1728
8. Chen CC, Hsieh JC, Wu YZ et al (2008) Mutual-information-based approach for neural connectivity during self-paced finger lifting task. Hum Brain Mapp 29:265-280
9. Clochon P, Fontbonne JM, Lebrun N et al (1996) A new method for quantifying EEG event-related desynchronization: amplitude envelope analysis. Electroencephalogr Clin NeuroPhysiol 98:126-129
10. Collins SJ, Lawson VA, Masters CL (2004) Transmissible spongiform encephalopathies. Lancent 363:51-61
11. Collins SJ, Sanchez-Juan P, Masters CL et al (2006) Determinants of diagnostic investigation sensitivities across the clinical spectrum of sporadic Creutzfeldt-Jakob disease. Brain 129:2278-2287
12. Cover TM (1965) Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition. IEEE trans Electron Comput EC-14:325-334
13. Cover TM (1968) Pattern Recognition. Thompson Book, Washington DC
14. Cover TM, Thomas JA (1991) Elements of Information Theory. Wiley, New York
15. Cristianini N, Shawe-Taylor J (2000) An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. Cambridge University Press, Cambridge
16. Daubechies I (1992) Ten Lectures on Wavelets. Society for Induced and Applied Mathematics, Philadelphia
17. Delorme A, Makeig S (2003) EEG changes accompanying leraned regulation of 12-Hz EEG activity. IEEE Trans Neural Syst Rehab Eng 11:133-137
18. Fisch BJ (1999) Fisch and Spehlmann's EEG Primer. Elsevier Science B.V., Amsterdam
19. Freye E (2005) Cerebral monitoring in the operating room and the intensive care unit: an introductory for the clinician and a guide for the novice wanting to open a window to the brain. J Clin Monitor Comp 19:77-168
20. Fushimi M, Sato K, Shimizu T et al (2002) PLEDs in Creutzfeldt-Jakob disease following a cadaveric dural graft. Clin Neurophysiol 113:1030-1035
21. Gerloff C, Richard J, Hadley J et al (1998) Functional coupling and regional activation of human cortical motor areas during simple, internally paced and externally paced finger movements. Brain 121:1513-1531
22. Geschwind MD, Martindale J, Miller D et al (2003) Challenging the clinical utility of the 14-3-3 protein for the diagnosis of sporadic Creutzfeldt-Jakob disease. Arch Neurol 60:813-816
23. Hansen HC, Zschocke S, Stürenburg HJ et al (1998) Clinical changes and EEG patterns preceding the onset of periodic sharp wave complexes in Creutzfeldt-Jakob disease. Acta Neurol Scand 97:99-106
24. Hansen LK, Larsen J, Kolenda T (2001) Blind detection of independent dynamic components. IEEE International Conference on Acoustics, Speech, and Signal Processing 5:3197-3200
25. Haykin S, Foundation. NNA (1994) Neural Network:AComprehensive Foundation. . Macmillan, New York
26. Hung CI, Lee PL, Wu YT et al. Single-trial quantification of EEG imagery Beta-band post-movement rebound in finger lifting task using independent component analysis (ICA). In: Proceedings, Proceeding of the 2003 World Congress on Medical Physics and Biomedical Engineering, Sydney, Australia, 2003.
27. Hung CI, Lee PL, Wu YT et al (2005) Recognition of motor imagery electroencephalography using independent component analysis and machine classifiers. Ann Biomed Eng 33:1053-1070
28. Hung CI, Wang PS, Soong BW et al (2007) Blind source separation of concurrent disease-related patterns from EEG in Creutzfeldt-Jakob disease for assisting early diagnosis. Ann Biomed Eng 35:2168-2179
29. Hyvärinen A, Karhunen J, Oja E (2001) Independent Component Analysis. John Wieley & Sons, Inc., New York
30. Joyce CA, Gorodnitsky IF, Kutas M (2004) Automatic removal of eye movement and blink artifacts from EEG data using blind component separation. Psychophysiology 41:313-325
31. Jung KY, Kimb JM, Kimc DW et al (2005) Independent component analysis of generalized spike-and-wave discharges: primary versus secondary bilateral synchrony. Clin Neurohysiol 116:913-919
32. Jung TP, Makeig S, Humphries C et al (2000) Removing electroencephalographic artifacts by blind source separation. Psychophysiology 37:163-178
33. Jung TP, Makeig S, Westerfield M et al (2000) Removal of eye activity artifacts from visual event-related potentials in normal and clinical subjects. Clin Neurohysiol 111:1745-1758
34. Jung TP, Makeig S, Mckeown MJ et al (2001) Imaging Brain Dynamics Using Independent Component Analysis. Proc IEEE 89:1107-1122
35. Jung TP, Makeig S, Westerfield M et al (2001) Analysis and visualization of single trial event-related potentials. . Human Brain Mapping 14:166-185
36. Kao YH, Guo WY, Wu YT et al (2003) Hemodynamic segmentation of MR brain perfusion images using independent component, Bayesian estimation and thresholding. Magn Reson Med 49:885-894
37. Kelly S, Burke D, de Chazal P et al. Parametric models and spectral analysis for classification in brain-computer interfaces. In: Proceedings, Proceedings of the 14th International Conference on Digital Signal Processin, Greece, 2002.
38. Lee PL, Wu YT, Chen LF et al (2003) ICA-based spatiotemporal approach for single-trial analysis of post-movement MEG beta synchronization. . NeuroImage 20:2010-2030
39. Lee PL, Hsieh JC, Wu CH et al (2006) The brain computer interface using flash visual evoked potential and independent component analysis. Ann Biomed Eng 34:1641-1654
40. Leocani L, Toro C, Manganotti P et al (1997) Event-related coherence and event-related desynchronization/synchronization in the 10 Hz and 20 Hz EEG during self-paced movements. Electroencephalogr Clin Neurophysiol 104:199-206
41. Lins OG, Picton TW, Berg P et al (1993) Ocular artifacts in recording EEGs and event-related potentials. II: Source dipoles and source components. Brain Topogr 6:65-78
42. MacKay DJC (1992) Bayesian model comparison and backprop nets. Advances in Neural Information Processing Systems 4: 839-846
43. Makeig S, Bell AJ, Jung TP et al (1996) Independent component analysis of electroencephalographic data. Advances in Neural Information Processing Systems 8:145-151
44. Makeig S, Enghoff S, Jung TP et al (2000) A natural basis for efficient brain-actuated control. IEEE Trans Rehab Eng 8:208-211
45. Misulis KE, Head TC (2002) Essentials of Clinical Neurophysiology. Butterworth-Heinemann, Boston
46. Muller-Gerking J, Pfurtscheller G, Flyvbjerg H (1999) Designing optimal spatial filters for single-trial EEG classification in a movement task. Clin Neurophysiol 110:787-798
47. Müller KR, Krauledat M, Dornhege G et al (2004) Machine learning techniques for brain computer interfaces. Biomed Tech 49:11-22
48. Nagamine T, Kajola M, Salmelin R et al (1996) Movement-related slow cortical magnetic fields and changes of spontaneous MEG- and EEG-brain rhythms. Electroencephalogr Clin Neurophysiol 99:274-286
49. Niedermeyer E, Lopes da Silva FH (1999) Electroencephalography: Basic Principles, Clinical Applications, and Related Fields. Williams & Wilkins, Baltimore, Md
50. Nunez PL, Srinivasan R, Westdorp AF et al (1997) EEG coherency. I: Statistics, reference electrode, volume conduction, Laplacians, cortical imaging, and interpretation at multiple scales. . Electroencephalogr Clin Neurophysiol 103:499-515
51. Obermaier B, Neuper C, Guger C et al (2001) Information Transfer Rate in a Five-Classes Brain-Computer Interface. IEEE Trans Rehab Eng 9:283-288
52. Parra L, Sajda PJ (2003) Blind source separation via generalized eigenvalue decomposition. . Machine Learning Res 4:1261-1269
53. Pfurtscheller G, Aranibar A (1979) Evaluation of event-related desynchronization (ERD) preceding and following voluntary self-paced movements. . Electroencephalogr Clin Neurophysiol 46:138-146
54. Pfurtscheller G, Stancák AJ, Neuper C (1996) Post-movement beta synchronization. A correlate of an idling motor area? Electroencephalogr Clin Neurophysiol:281-293
55. Pfurtscheller G, Neuper C, Schlogl A et al (1998) Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters. IEEE Trans Rehab Eng 63:316-325
56. Pfurtscheller G, Lopes da Silva FH (1999) Event-related EEG/MEG synchronization and desynchronization: basic principles. Clin Neurophysiol 110:1842-1857
57. Pfurtscheller G, Lopes da Silva FH (1999) Event-related desynchronization. Handbook of Electroencephalography and Clinical Neurophysiology,. Elsevier Science, Amsterdam
58. Pfurtscheller G, Guger C, Muller G et al (2000) Brain oscillations control hand orthosis in a tetraplegic. Neurosci Lett 292:211-214
59. Pregenzer M, Pfurtscheller G (1999) Frequency component selection for an EEG-based brain to computer interface. . IEEE Trans Rehab Eng 7:413-419
60. Schröter A, Zerr I, Henkel K et al (2000) Magnetic resonance imaging in the clinical diagnosis of Creutzfeldt-Jakob disease. Arch Neurol 57:1751-1757
61. Stearns SD, David RA (1996) Signal Processing Algorithms in Matlab. Prentice Hall P T R, New Jersey
62. Tang AC, Pearlmutter BA, Zibulevsky M et al (2000) Blind source separation of multichannel neuromagnetic responses. Neurocomput 32-33:1115-1112-
63. Toro R, Fox PT, Paus T (2008) Functional coactivation map ofth ehuman brain. Cerebral Cortex 18:2553-2559
64. Urrestarazu E, LeVan P, Gotman J (2006) Independent component analysis identifies ictal bitemporal activity in intracranial recordings at the time of unilateral discharges. Clin Neurophysiol 117:549-561
65. Vigário R, Särelä J, Jousmäki V et al (2000) Independent component approach to the analysis of EEG and MEG recordings. IEEE Trans Biomed Eng 47:589-593
66. Vorobyov S, Cichocki A (2002) Blind noise reduction for multisensory signals using ICA and subspace filtering, with application to EEG analysis. Biol Cybern 86:293-303
67. Wieser HG, Schwarz U, Blättler T et al (2004) Serial EEG findings in sporadic and iatrogenic Creutzfeldt-Jakob disease. Clin Neurophysiol 115:2467-2478
68. Wieser HG, Schindler K, Zumsteg D (2006) EEG in Creutzfeldt–Jakob disease. Clin Neurophysiol 117:935-951
69. Wolpaw JR, McFarland DJ, Neat GW et al (1991) An EEG-based brain-computer interface for cursor control. Electroenceph Clin Neurophysiol 78:252-259
70. Wolpaw JR, McFarland DJ, Vaughan TM (2000) Brain-computer interface research at the Wadsworth Center. IEEE Trans Rehab Eng 8:222-226
71. Wolpaw JR, Birbaumer N, McFarlanda DJ et al (2002) Brain-computer interfaces for communication and control (Invited Review). . Clin Neurophysiol 113:767-791
72. Wolpaw JR (2007) Brai-computer interfaces as new brain output pathways. J Physiol 579:613-619
73. Wu YT, Chen HY, Lee PL et al. Classifying MEG Data of Left, Right Index Finger Movement and Resting State Using Support Vector Machine (SVM). In: Proceedings, BioMag 13th International Conference on Biomagnetism, 2002, pp. 1042-1044.
74. Wu YT, Lee PL, Chen LF et al. Single-trial quantification of imagery beta-band Murhythm in finger lifting task using independent component analysis (ICA). In: Proceedings, BioMag 13th International Conference on Biomagnetism, 2002, pp. 1045-1047.
75. Wu YT, Lee PL, Chen LF et al. Quantification of movement-related modulation on beta activity of single-trial magnetoencephalography measuring using independent component analysis (ICA). In: Proceedings, 1st International IEEE EMBS Conference on Neural Engineering, 2003, pp. 396-398.
76. Wübbeler G, Ziehe A, Mackert BM et al (2000) Independent component analysis of noninvasively recorded cortical magnetic DC-fields in humans. IEEE Trans Biomed Eng 47:594-599
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊