在骨科的臨床上，發現當膝關節發生病變時，其活動時會產生異常的聲音，即膝關節在擺動下所產生的振動訊號，vibration arthrometry（VAM）即是藉由分析此一振動訊號來診斷膝關節的病變。而本研究即是針對退化性關節炎的振動訊號來分析。由於VAM是一種非侵襲性的檢查工具，因此極具發展潛力。因此本研究利用時域(time domain)及頻域(frequency domain) 數學理論為獨立成份分析及經驗模態建立訊號的特徵，對照後找出退化性關節炎的特徵。我們發現膝關節於站立及蹲下所產生的振動訊號可以用來區分正常者與退化性關節炎患者。本研究首次嘗試將獨立成份分析及經驗模態分析引入退化性關節炎振動訊號的診斷，並針對所提供之ICA及HHT 及受測姿勢-位置的選擇上加以驗證，來區別退化性關節炎患者與正常者具有最大的差異性。關節振動測量術是一種非侵襲性且簡單方便低成本的膝關節病變診斷工具。本項技術的持續發展，將可成為醫生診斷時另一種重要的工具，藉由選用適當的治療方式，不僅解除了病患的痛苦，也可以避免醫療資源的浪費。本研第二部分究使用希伯特黃轉換技術診斷膝蓋關節振動號，在實驗過程中結合希伯特黃轉換方法作驗證。且所提出的方法確實可以有效運用於膝蓋關節退化之非侵入性診斷。

A phenomenon can be found which abnormal joint sound arises from knee joint disorder during knee motion in the clinical diagnosis. The knee joint could produce vibration signals from a standing position to a squatting position, and the vibration arthrometry（VAM）could diagnose the disorders of the knee joint by analyzing these vibration signals. In this study we will apply VAM to the patients of the normal and degenerative arthritis. Because VAM is a noninvasive diagnostic tool, it has great potential. The main methods in the thesis we apply VAM to the vibration signals of the normal and degenerative arthritis, utilizing Independent Component Analysis (ICA) and Empirical Mode Decomposition (EMD) to establish the mathematical model after adaptive decomposition, and try to find out the characteristic parameters of the vibration signals in these diseases. Vibration arthrometry (VAM) provided a noninvasive, simple, and cheap clinic tool for diagnosing knee joints. Appropriate therapy can be given to the patients with correct diagnosis. The performance of the combined ICA/HHT technique is verified experimentally. The experimental results show that proposed ICA/HHT approach has better recognition performance than that obtained using other traditional methods.

REFERENCES
[1]C. B. Frank, R. M. Rangayyan and G. D. Bell, Analysis of knee joint sound signals for non-invasive diagnosis of cartilage pathology, IEEE Eng. In Medicine and Biology Magazine, pp. 65-68, 1990.
[2]C.-J. Lu, T.-S. Lee, C.-C. Chiu “Financial time series forecasting using independent component analysis and support vector regression,” Decision Support Systems, Vol. 47, pp. 115-125, 2009.
[3]J. Karhunen. “Neural approaches to independent component analysis and source separation,” In Proc. 4th European Symp. Artificial Neural Networks, ESANN’96, Bruges, Belgium, pp.249-266, Apr. 1996.
[4]H. Sahlin, H. Broman, “Separation of real-world signals,” Signal Processing, Vol.64, No.2, pp.103-113, 1998.
[5]G. J. Erickson, J. T. Rychert and C. R. Smith. “Difficults applying recent blind source separation techniques to EEG and MEG,” Proceedings of the 17th International Workshop on Maxiumum Entropy and Bayesian Methods of Statistical Analysis, Boise, Idaho, pp.209-222, 1997.
[6]J. Karhumen, A. Hyvarinen, “Application of neural blind separation to signal and image processing,” In Proc ICASSP. Germany, Munich, pp.131-134, 1997.
[7]S. Makeig, T. P. Jung, A. J. Bell, “Blind separation of auditory event-related brain reponses into independent components,” In Proc Natl Acad Sci, Vol.94, pp.10979-10984, 1997.
[8]A. Benveniste, “Goursat M. Blind Equalizers,” IEEE Trans on Commun, Vol.32, No.8, pp.871-883, 1984.
[9]S. Makeig, M., Westerfield T-P. Jung, S. Enghoff, J. Townsend, E. Courchesne & T. J. Sejnowski “Dynamic brain sources of visual evoked responses,” Science Vol.295, pp.690-694, 2002.
[10]J. Herault & C. Jutten “Space or time adaptive signal processing by neural network models,” Neural Networks for Computing, AIP Conference Proceedings Vol.151, pp.207-211, 1986.
[11]P. Comon, “Independent component analysis-a new concept?” Signal Process., Vol.36, pp.287-314, 1994.
[12]A.J. Bell and T.J. Sejnowski, “An information maximisation approach to blind separation and blind deconvolution,” Neural Comput., Vol.7, No.6, pp.1129-1159, 1995.
[13]J.-F. Cardoso, B.H. Laheld, “Equivariant adaptive source separation,” IEEE Transactions on Signal Processing, Vol.44, No.12 pp.3017-3030, Dec 1996
[14]D. T. Pham and P. Garat, “Blind separation of mixture of independent sources through aquasi-maximum likelihood approach,” IEEE Transactions on Signal Processing, Vol.45, No.7, pp.1712-1725, Jul 1997.
[15]T.W. Lee, Independent Component Analysis: Theory and Applications, Kluwer Academic Publishers, Boston, 1998.
[16]A. Hyvärinen, “Sparse code shrinkage: Denoising of non-Gaussian data by maximum likelihood estimation,” Neurocomputing Vol.11, No.7, pp. 1739-1768, 1999.
[17]A. Hyvärinen and E. Oja, “Independent Component Analysis: Algorithms and Applications,” Neural Netw. Vol.13, No.4-5, pp.411-430, 2000.
[18]A. Hyvärinen, “Fast and robust fixed-point algorithms for independent component analysis,” IEEE Trans. Neural Netw. Vol.10, No.3, pp. 626-634, 1999b.
[19]A. Hyvärinen and E. Oja, “A fast fixed-point algorithm for independent component analysis,” Neural Comput. Vol.9, No.7, pp. 1483-1492, 1997.
[20]A. Hyvärinen, J. Karhunen and E. Oja, Independent Component Analysis Wiley, New York, 2001.
[21]N. E. Huang, Z. Shen, S. R. Long, M. C. Wu, E. H. Shih, Q. Zheng, C. C. Tung, & H. H. Liu, “The empirical mode decomposition method and the Hilbert spectrum for non-stationary time series analysis,” Proc. Roy. Soc. Lond. A Vol. 454, pp. 903-995, 1998.
[22]Z. Wu, N. E Huang, Ensemble Empirical Mode Decomposition: a noise-assisted data analysis method. Advances in Adaptive Data Analysis. 1(1) 1-41 (2009)
[23]N. E. Huang, Z. Wu, “A review on Hilbert-Huang transform: method and its applications to geophysical studies,” Reviews of Geophysics, Vol.46, No. RG2006, 2008.

[24]Z. Wu, N. E Huang, S. R. Long, C.-K. Peng, “On the trend, detrending, and the variability of nonlinear and non-stationary time series,” Proc. Natl. Acad. Sci. USA. Vol. 104, pp. 14889-14894, 2007.
[25]N. E. Huang, , M. L. Wu, S. R. Long, S. S. Shen, W. D. Qu, P. Gloersen, & K. L. Fan, “A confidence limit for the Empirical Mode Decomposition and Hilbert Spectral Analysis,” Proc. Roy. Soc. Lond. A Vol. 459, pp.2317-2345, 2003.
[26]W. Huang, Z. Shen, N. E. Huang, & Y. C. Fung, “Engineering analysis of biological variables: An example of blood pressure over 1 day,” Proc. Natl. Acad. Sci. USA. Vol. 95, pp. 4816-4821, 1998.
[27]D. A.T. Cummings, R. A. Irizarry, N. E. Huang, T. P. Endy, A. Nisalak, K. Ungchusak & D. S. Burke, “Travelling waves in the occurrence of dengue haemorrhagic fever in Thailand,” Nature Vol. 427, pp. 344-347, 2004.
[28]Z. Wu, N. E. Huang, S. R. Long, & C.-K. Peng, “On the trend, detrending, and the variability of nonlinear and non-stationary time series,” Proc. Natl. Acad. Sci. USA. Vol. 104, pp. 14889-14894, 2007.
[29]S. Krishnan, R. M. Rangayyan, G. D. Bell, and C. B. Frank, Adaptive time-frequency analysis of knee joint vibroarthrographic signals for noninvasive screening of articular cartilage pathology, IEEE Trans. Biomed. Eng., vol. 47, no. 6, pp. 773-783, 2000.
[30]R.M. Rangayyan, S. Krishnan, G.D. Bell, C.B. Frank, K.O. Ladly, Parametric representation and screening of knee joint vibroarthrographic signals, IEEE Trans. Biomed. Eng. Vol. 44, pp.1068-1074, 1997.
[31]S. Krishnan, R.M. Rangayyan, G.D. Bell, C.B. Frank, K.O. Ladly, Adaptive filtering, modelling, and classification of knee joint vibroarthrographic signals for non-invasive diagnosis of articular cartilage pathology, Med. Biol. Eng. Comput. Vol. 35, pp. 677684, 1997.
[32]K. Umapathy, S. Krishnan, Modified local discriminant bases algorithm and its application in analysis of human knee joint vibration signals, IEEE Trans. Biomed. Eng. Vol. 53, pp. 517-523, 2006.
[33]C. Jiang, J. Lee and T. Yuan, Vibration arthrometry in patients with failed total knee replacement, IEEE Trans. Biomed. Eng,vol.47,no.2,pp.219-227,2000.
[34]M.L. Chu, I.A. Gradisar, M.R. Railey and G.F. Bowling, An electroacoustical technique for the detection of. knee joint noise, Medical Research Engineering, vol.12,no.1,pp.18-20,1976.
[35]R.A.B. Mollan, G.C. McCullagh and R.I. Wilson, A critical appraisal of auscultation of human joints, Clinical Orthopaedics And Related Research, vol.170,pp.231-237,1982.
[36]Y.T. Zhang, C.B. Frank, R.M. Rangayyan and G.D. Bell Mathematical modeling and spectral analysis of the patella-femoral pulse train produced during slow knee movement, IEEE Trans. Biomed. Eng, vol.39,no.9,pp.971-979,1992.
[37]Y.T. Zhang, K.O. Ladly, R.M. Rangayyan, C.B. Frank, G.D. Bell and Z.Q. Liu, Muscle contraction interference in acceleration vibroarthrography, Proc. The IEEE/EMBS 12th Annual International Conference,pp.2150-2151,1990.
[38]Y.T. Zhang, R.M. Rangayyan, C.B. Frank, G.D. Bell, Adaptive cancellation of muscle contraction interference from knee joint vibration signals, IEEE Trans. Biomed. Eng, vol.41,no.2,pp.181-191,1994.
[39]S. Krishnan, R.M. Rangayyan, G.D. Bell and C.B. Frank, Sonification of knee-joint vibration signals, in Proc. 22nd IEEE Annu. Int. Conf. IEEE Engineering in Medicine and Biology Society, pp.1995-1998,2000.
[40]Y. Shen, R.M. Rangayyan, G.D. Bell, C. B. Frank, Y.T. Zhang and K.O. Ladly, Localization of knee joint cartilage pathology by multichannel vibroarthrography, Med Eng Phys,vol.17,pp.583-594,1995.
[41]S.C. Huang, I.P. Wei, H.L. Chien, T.M. Wang, Y.H. Liu, H.L. Chen, T.W. Lu, J.G. Lin, Effects of severity of degeneration on gait patterns in patients with medial knee osteoarthritis, Med Eng Phys,vol.30,pp.997-1003,2008.
[42]G. Spahn, H. Plettenberg, H. Nagel, E. Kahl, H.M. Klinger, T. Mückley, M. Günther, G.O. Hofmann and J.A. Mollenhauer, Evaluation of cartilage defects with near-infrared spectroscopy (NIR): An ex vivo study, Med Eng Phys,vol.30,pp.285-292,2008.
[43]P. Julkunen, R.K. Korhonen, W. Herzog and J.S. Jurvelin, Uncertainties in indentation testing of articular cartilage: A fibril-reinforced poroviscoelastic study,Med Eng Phys, vol.30,pp.506-515,2008.
[44]C. Provatidis, C. Vossou, E. Petropoulou, A. Balanika and G. Lyritis, A finite element analysis of a T12 vertebra in two consecutive examinations to evaluate the progress of osteoporosis, Med Eng Phys, In Press, Corrected Proof, Available online 30 January,2009.
[45]J.R. Steele, A. Basu and A. Job, A three-dimensional representation of an athletic female knee joint using magnetic resonance imaging, Med Eng Phys,vol.16,pp.363-369,1994.
[46]R.A.B. Mollan, W.G. Kemohan and P.H. Watters, Artefact encountered by the vibration detection system, J. Biomechanics,vol.16,no.3,pp.193-199,1983.
[47]C. Orizio, R. Perini, B. Diemont, M.M. Figini and A. Veicsteinas, Spectral analysis of muscular sound during isometric contraction of biceps, J Appl Physiol,vol.68,no.2,pp.508-512,1990.
[48]J. Maddox, “Cocktail party effect made tolerable,” Nature, Vol. 369, pp. 517, 1994.
[49]L. Molgedey, & H. G. Schuster, “Separation of a mixture of independent signals using time delayed correlations,” Phys. Rev. Lett. Vol. 72, pp. 3634-3637, 1994.
[50]E. Seifritz, F. Esposito, F. Hennel, H. Mustovic, J. G. Neuhoff, et al., “Spatiotemporal pattern of neural processing in the human auditory cortex,” Science, Vol. 297, pp. 1706-1708, 2002.
[51]M. Alrubaiee, M. Xu, S. K. Gayen, M. Brito, & R. R. Alfano, “Three-dimensional optical tomographic imaging of scattering objects in tissue-simulating turbid media using independent component analysis,” Appl. Phys. Lett. Vol. 87, No. 191112, 2005.
[52]M. Alrubaiee, M. Xu, S. K. Gayen, & R. R.Alfano, “Localization and cross section reconstruction of fluorescent targets in ex vivo breast tissue using independent component analysis,” Appl. Phys. Lett. Vol. 89, No.133902, 2006.
[53]J. B. Tenenbaum, V.de Silva, & J. C. Langfoed, “A globl geometric framework for nonlinear dimensionality reduction,” Science Vol. 290, pp. 2319-2323, 2000.
[54]E. Mjolsness, & D. DeCoste, “Machine learning for science: state of the art and future prospects,” Science Vol. 293, pp. 2051-2055, 2001.
[55]M. S. Lewicki, “Efficient coding of natural sounds,” Nature Neuroscience Vol. 5, pp. 356-362, 2002.
[56]F. C. Meinecke, A. Ziehe, J. Kurths, & K.-R. , “Measuring phase synchronization of superimposed signals,” Phys. Rev. Lett. Vol. 94, No. 084102, 2005.
[57]Lauro, E. De, Martino, S. De & Falanga, M. Complexity of time series associated to dynamical systems inferred from independent component analysis. Phys. Rev. E 72, No. 046712 (2005).
[58]X. Huang, S. Y. Lee, E. Prebys, & R. Tomlin, “Application of independent component analysis to fermilab booster,” Physical Review Special Topics-Accelerators & Beams, Vol. 8, No.. 064001, 2005.
[59]M. Laubach, J. Wessberg, & M. A. L. Nicolelis, “Cortical ensemble activity increasingly predicts behaviour outcomes during learning of a motor task,” Nature, Vol. 405, pp. 567-571, 2000.
[60]H. Stögbauer, A. Kraskov, S. A. Astakhov, & P. Grassberger, “Least dependent component analysis based on mutual information,” Phys. Rev. E Vol. 70, No. 066123, 2004.
[61]N. M. Abramson, Information Theory and Coding. McGraw-Hill, New York, 1963.
[62]A. Feinstein, Foundations of Information Theory. McGraw-Hill, New York, 1958.
[63]A. Hyvärinen, Complexity pursuit: separating interesting components from time-series, Neural Computation,vol.13,no.4,pp.883-898,2001.
[64]N.E. Huang, Z. Shen, S.R. Long, M. Wu, H. Shih, N. Zheng, C. Yen, C.C. Tung, H.H. Liu, The empirical mode decomposition and the Hilbert spectrum for non-linear and non-stationary time series analysis, Proceedings of the Royal Society of London Series A-Mathematical Physical and Engineering Sciences, vol.454,pp.903-995,1998.

[65]M. L. Chu, l. A. Gradisar, M. R. Railey and G. F. Bowling, An electroacoustical technique for the detection of knee joint noise, Medical Research Engineering, vol. 12, no. 1, pp. 18-20, 1976.

[66]T. Mu, A.K. Nandi and R.M. Rangayyan, Screening of knee-joint vibroarthrographic signals using the strict 2-surface proximal classifier and genetic algorithm, Computers in Biology and Medicine, vol. 38, pp.1103-1111,2008