本論文主要目的為開發結合時頻轉換及深度學習網路的步態分析演算法、並以神經退化性疾病步態的自動辨識來驗證演算法的功效。神經退行性疾病如肌萎縮性脊髓側索硬化症(Amyotrophic Lateral Sclerosis, ALS)、亨廷頓舞蹈症(Huntington’s Disease, HD)、帕金森氏症(Parkinson’s Disease, PD)是一種大腦及脊髓細胞神經元逐漸退化及死亡的慢性疾病，在細胞神經元逐漸退化的過程中，患者的動作控制能力會逐漸的退化，其中步態異常為神經退化性疾病中明顯的動作退化現象。若比較健康受測者與神經退化性疾病的患者的步態，可發現健康受測者(Healthy Control, HC)的足底壓力時域訊號可顯示出規律的步態、而神經退化性疾病患者的足底壓力時域訊號則顯示出較不規律的步態。過去已有相關研究開發機械學習辨識演算法用於辨識健康受測者及不同類別的神經退化性疾病的步態訊號，本研究希望進一步以深度學習理論來開發健康人及神經退化性疾病的步態辨識演算法。深度學習與機械學習主要的不同之處在於特徵萃取的原理，深度學習網路以自動化演算法為基礎，自動萃取足以區辨出不同類別的特徵；而機械學習則是透過人為先行定義特徵的類別、然後寫成自動演算程式，達到特徵萃取的目的。某些足以區辨不同類別的良好特徵，可能在人為篩選定義特徵的類別時被忽略。現今深度學習網路如卷積式類神經網路，在影像辨識問題上有非常良好的表現，本論文的研發重點為將時域的足底壓力訊號轉為類似影像的特徵，再搭配卷積式類神經網路進行神經退化性疾病步態的自動辨識。本論文開發的演算法包括以下程序：1) 視窗化程序：首先將連續時間的足底壓力訊號切分成以10、30、60秒為單位的訊號。2) 特徵產生程序：本論文使用兩種特徵產生程序，第一種是透過連續小波轉換、將左腳或右腳的足底壓力訊號轉為時頻圖(Time-frequency spectrogram)，第二種則是透過小波同調性演算法，將左腳及右腳的訊號共同產生小波同調性頻譜圖(wavelet coherence spectrogram)，藉以表示雙腳行走時的同調性。3) 接著透過主成分分析，強化不同類別資料的特徵。4) 最後透過卷積式類神經網路，來進行自動辨識。驗證本論文演算法的測試資料為麻省理工學院的生理訊號開源資料庫Physionet中的Gait Dynamics in Neuro-Degenerative Disease Data Base資料庫。此資料庫包括16名健康受測者、13名肌萎縮性脊髓側索硬化症受測者、20名亨廷頓舞蹈症受測者、15名帕金森氏症受測者，以上共有64名受測者，每一名受測者的步態訊號都是5分鐘長度的足底壓力訊號（包含左腳以及右腳）。本論文採用Leave-One-Out交叉驗證(LOOCV)和k-fold交叉驗證(kfoldCV)兩種不同的訓練-測試方法進行演算法功效的評估。在LOOCV交叉驗證中、辨別HC受測者與ALS受測者的辨識率達到100%、辨別HC受測者與PD的辨識率達到100%、辨別HC受測者與PD受測者的辨識率為97.42%、辨別ALS受測者與HD受測者的辨識率為98.38%、辨別ALS受測者與PD受測者的辨識率達到100%、辨別HD受測者與PD受測者的辨識率為98.19%、辨別HC受測者與神經退化性疾病受測者(ALS+HD+PD)為的辨識率98.59%。若與過去使用同一個資料庫的文獻進行比較，如Zheng與Wang等人於2015年發表的論文[1]、Ren等人於2017發表的論文[2]、Zhao等人於2018發表的論文[3]、Pham等人於2018發表的論文[4]，本論文提出的方法有優於所有既有文獻的辨識率。最後，本論文成功的開發基於時頻轉換及深度學習網路的步態分析演算法並驗證於神經退化性疾病步態自動辨識的表現。

Neuro-degenerative diseases (NDDs), such as Amyotrophic Lateral Sclerosis (ALS), Huntington’s Disease (HD), and Parkinson’s Disease (PD), may cause serious gait abnormalities. A comparison of gait abnormalities among healthy controls and NDD subjects will indicate different force pattern variations since the gait force signals are irregular in NDDs. A detection algorithm using a convolutional neural network (CNN) has been developed in this research to classify NDDs based on the gait force signal. The main purpose of this research is to help a physician with screening for NDDs for early diagnosis, efficient treatment planning, and monitoring of disease progression. The database used in this study consisted 64 recordings (five-minutes in each recording) of gait force signals acquired from 16 healthy controls, 13 ALS, 20 HD, and 15 PD subjects. The proposed detection algorithm consists of a windowing process, a feature transformation process, and a classification process. In the windowing process, the five-minute gait force signal was divided into 10, 30, and 60 seconds of successive time windows. There are two feature transformation process compared in this study. In the first one, time domain gait force signal of right or left foot is transformed into a time-frequency spectrogram using a continuous wavelet transform (CWT) spectrogram, specifically a Morlet or Gabor wavelet. In the second apporach, time domain gait force signals from right and left feet are used to compute the wavelet coherence spectrogram. Then, the feature extraction of the time-frequency spectrogram is utilized using a principal component analysis (PCA). The difference force pattern variations among healthy controls, ALS, HD, and PD patients can be distinctly observed from the feature extracted spectrogram images. Finally, CNN is employed in the classification process of the proposed detection algorithm and evaluated using the leave-one-out cross-validation (LOOCV) and the k-fold cross-validation (kfoldCV). As the result, using LOOCV, the highest performance accuracy in the ALS vs. healthy controls classification is 100%, in the HD vs.s healthy controls is 100%, in the PD vs.s healthy controls is 97.42%, in ALS vs. HD is 98.38%, in ALS vs. PD is 100%, in HD vs. PD is 97.90%, and in NDD (ALS+HD+PD) vs. healthy controls is 98.44%. We compared our highest performance accuracy in terms of three classification tasks (ALS vs. healthy control, HD vs. healthy controls, and PD vs. healthy controls) with several existing studies using the same database: Zeng and Wang (2015) [1], Ren et al. (2016) [2], Zhao et al. (2018) [3], and Pham (2017) [4], and find that the proposed method outperforms the performance results in the existing literature. In conclusion, the proposed detection algorithm can effectively differentiate the gait patterns based on a time-frequency spectrogram of a gait force signal between healthy control subjects and patients with neuro-degenerative diseases.

[1] W. Zeng, and C. Wang, “Classification of neurodegenerative diseases using gait dynamics via deterministic learning,” Information Sciences, vol. 317, pp. 246-258, Oct 1, 2015.
[2] P. Ren, S. Tang, F. Fang, L. Luo, L. Xu, M. L. Bringas-Vega, D. Yao, K. M. Kendrick, and P. A. Valdes-Sosa, “Gait rhythm fluctuation analysis for neurodegenerative diseases by empirical mode decomposition,” IEEE Transactions on Biomedical Engineering, vol. 64, no. 1, pp. 52-60, 2016.
[3] A. Zhao, L. Qi, J. Dong, and H. Yu, “Dual channel LSTM based multi-feature extraction in gait for diagnosis of Neurodegenerative diseases,” Knowledge-Based Systems, vol. 145, pp. 91-97, 2018.
[4] T. D. Pham, “Texture classification and visualization of time series of gait dynamics in patients with neuro-degenerative diseases,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 26, no. 1, pp. 188-196, 2017.
[5] JPND Research, “What is Neurodegenerative Disease?,” JPND Research, February 7, 2015. [Online]. Available: https://bit.ly/2Hkzs9w. [Accessed: July 12, 2019].
[6] A. Lee, and R. M. Gilbert, “Epidemiology of Parkinson disease,” Neurologic clinics, vol. 34, no. 4, pp. 955-965, 2016.
[7] Parkinson's Disease Foundation, “Statistics on Parkinson's,” Parkinson's Disease Foundation, EIN: 13-1866796, 2018. [Online]. Available: https://bit.ly/2RCeh9H. [Accessed: July 12, 2019].
[8] A. Chiò, G. Logroscino, B. Traynor, J. Collins, J. Simeone, L. Goldstein, and L. White, “Global epidemiology of amyotrophic lateral sclerosis: a systematic review of the published literature,” Neuroepidemiology, vol. 41, no. 2, pp. 118-130, 2013.
[9] A. E. Renton, A. Chiò, and B. J. Traynor, “State of play in amyotrophic lateral sclerosis genetics,” Nature neuroscience, vol. 17, no. 1, pp. 17, 2014.
[10] M. Agrawal, and A. Biswas, “Molecular diagnostics of neurodegenerative disorders,” Frontiers in molecular biosciences, vol. 2, pp. 54, 2015.
[11] Harvard NeuroDiscovery Center, “The Challenge of Neurodegenerative Diseases,” Harvard NeuroDiscovery Center. [Online]. Available: https://bit.ly/2soDGmD. [Accessed: July 12, 2019].
[12] J. M. Hausdorff, M. E. Cudkowicz, R. Firtion, J. Y. Wei, and A. L. Goldberger, “Gait variability and basal ganglia disorders: stride-to-stride variations of gait cycle timing in Parkinson's disease and Huntington's disease,” Mov Disord, vol. 13, no. 3, pp. 428-37, May, 1998.
[13] F. Arafsha, C. Hanna, A. Aboualmagd, S. Fraser, and A. El Saddik, “Instrumented wireless smartinsole system for mobile gait analysis: A validation pilot study with tekscan strideway,” Journal of Sensor and Actuator Networks, vol. 7, no. 3, pp. 36, 2018.
[14] A. Razak, A. Hadi, A. Zayegh, R. K. Begg, and Y. Wahab, “Foot plantar pressure measurement system: A review,” Sensors, vol. 12, no. 7, pp. 9884-9912, 2012.
[15] R. H. Brown, Jr., and A. Al-Chalabi, “Amyotrophic Lateral Sclerosis,” N Engl J Med, vol. 377, no. 16, pp. 162-172, Oct 19, 2017.
[16] J. M. Hausdorff, A. Lertratanakul, M. E. Cudkowicz, A. L. Peterson, D. Kaliton, and A. L. Goldberger, “Dynamic markers of altered gait rhythm in amyotrophic lateral sclerosis,” Journal of applied physiology, vol. 88, no. 6, pp. 2045-2053, 2000.
[17] S. Zarei, K. Carr, L. Reiley, K. Diaz, O. Guerra, P. F. Altamirano, W. Pagani, D. Lodin, G. Orozco, and A. Chinea, “A comprehensive review of amyotrophic lateral sclerosis,” Surgical neurology international, vol. 6, pp. 171, 2015.
[18] M. Banaie, Y. Sarbaz, S. Gharibzadeh, and F. Towhidkhah, “Huntington's disease: Modeling the gait disorder and proposing novel treatments,” Journal of theoretical biology, vol. 254, no. 2, pp. 361-367, 2008.
[19] P. Dayalu, and R. L. Albin, “Huntington disease: pathogenesis and treatment,” Neurologic clinics, vol. 33, no. 1, pp. 101-114, 2015.
[20] S. J. Pyo, H. Kim, I. S. Kim, Y.-M. Park, M.-J. Kim, H. M. Lee, and S.-B. Koh, “Quantitative gait analysis in patients with Huntington’s disease,” Journal of movement disorders, vol. 10, no. 3, pp. 140-144, 2017.
[21] National Institute of Neurological Disorders and Stroke, “Parkinson's Disease Information Page,” National Institute of Neurological Disorders and Stroke, 2016. [Online]. Available: https://bit.ly/2xTA6rL. [Accessed: July 12, 2019].
[22] J. Hoff, A. v/d Plas, E. Wagemans, and J. Van Hilten, “Accelerometric assessment of levodopa‐induced dyskinesias in Parkinson's disease,” Movement disorders: official journal of the Movement Disorder Society, vol. 16, no. 1, pp. 58-61, 2001.
[23] M. Pistacchi, M. Gioulis, F. Sanson, E. De Giovannini, G. Filippi, F. Rossetto, and S. Z. Marsala, “Gait analysis and clinical correlations in early Parkinson’s disease,” Functional neurology, vol. 32, no. 1, pp. 28-34, 2017.
[24] G. Legname, “Novel approaches to diagnosis and therapy in neurodegenerative diseases,” 5th International Conference on Biomedical Engineering in Vietnam, pp. 155-158, 2015.
[25] M. Gómez-Río, M. M. Caballero, J. M. Gorriz Saez, and A. Mínguez-Castellanos, “Diagnosis of neurodegenerative diseases: the clinical approach,” Current Alzheimer Research, vol. 13, no. 5, pp. 469-474, 2016.
[26] A. Muro-De-La-Herran, B. Garcia-Zapirain, and A. Mendez-Zorrilla, “Gait analysis methods: An overview of wearable and non-wearable systems, highlighting clinical applications,” Sensors, vol. 14, no. 2, pp. 3362-3394, 2014.
[27] A. Salarian, H. Russmann, F. J. Vingerhoets, C. Dehollain, Y. Blanc, P. R. Burkhard, and K. Aminian, “Gait assessment in Parkinson's disease: toward an ambulatory system for long-term monitoring,” IEEE transactions on biomedical engineering, vol. 51, no. 8, pp. 1434-1443, 2004.
[28] O. Sofuwa, A. Nieuwboer, K. Desloovere, A.-M. Willems, F. Chavret, and I. Jonkers, “Quantitative gait analysis in Parkinson’s disease: comparison with a healthy control group,” Archives of physical medicine and rehabilitation, vol. 86, no. 5, pp. 1007-1013, 2005.
[29] Y. A. Grimbergen, M. J. Knol, B. R. Bloem, B. P. Kremer, R. A. Roos, and M. Munneke, “Falls and gait disturbances in Huntington's disease,” Movement disorders: official journal of the Movement Disorder Society, vol. 23, no. 7, pp. 970-976, 2008.
[30] S.-B. Koh, K.-W. Park, D.-H. Lee, S. J. Kim, and J.-S. Yoon, “Gait analysis in patients with Parkinson’s Disease: relationship to clinical features and freezing,” Journal of Movement Disorders, vol. 1, no. 2, pp. 59-64, 2008.
[31] T. Karakostas, S. Hsiang, H. Boger, L. Middaugh, and A.-C. Granholm, “Three-dimensional rodent motion analysis and neurodegenerative disorders,” Journal of neuroscience methods, vol. 231, pp. 31-37, 2014.
[32] M. H. Pham, M. Elshehabi, L. Haertner, S. Del Din, K. Srulijes, T. Heger, M. Synofzik, M. A. Hobert, G. S. Faber, and C. Hansen, “Validation of a step detection algorithm during straight walking and turning in patients with Parkinson’s disease and older adults using an inertial measurement unit at the lower back,” Frontiers in neurology, vol. 8, pp. 457, 2017.
[33] W.-C. Hsu, T. Sugiarto, Y.-J. Lin, F.-C. Yang, Z.-Y. Lin, C.-T. Sun, C.-L. Hsu, and K.-N. Chou, “Multiple-Wearable-Sensor-Based Gait Classification and Analysis in Patients with Neurological Disorders,” Sensors, vol. 18, no. 10, pp. 3397-3413, 2018.
[34] Y. Wu, P. Chen, X. Luo, M. Wu, L. Liao, S. Yang, and R. M. Rangayyan, “Measuring signal fluctuations in gait rhythm time series of patients with Parkinson's disease using entropy parameters,” Biomedical Signal Processing and Control, vol. 31, pp. 265-271, 2017.
[35] C. Kamath, “Influence of Neurodegenerative Disorders on Gait Dynamics Using Poincaré Symbolic Measures,” MOJ Gerontol Ger, vol. 1, no. 6, pp. 164-173, 2017.
[36] P. Ren, W. Zhao, Z. Zhao, M. L. Bringas-Vega, P. A. Valdes-Sosa, and K. M. Kendrick, “Analysis of gait rhythm fluctuations for neurodegenerative diseases by phase synchronization and conditional entropy,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 24, no. 2, pp. 291-299, 2015.
[37] Y. Xia, Q. Gao, and Q. Ye, “Classification of gait rhythm signals between patients with neuro-degenerative diseases and normal subjects: Experiments with statistical features and different classification models,” Biomedical Signal Processing and Control, vol. 18, pp. 254-262, 2015.
[38] S. Bilgin, “The impact of feature extraction for the classification of amyotrophic lateral sclerosis among neurodegenerative diseases and healthy subjects,” Biomedical Signal Processing and Control, vol. 31, pp. 288-294, 2017.
[39] E. Baratin, L. Sugavaneswaran, K. Umapathy, C. Ioana, and S. Krishnan, “Wavelet-based characterization of gait signal for neurological abnormalities,” Gait & posture, vol. 41, no. 2, pp. 634-639, 2015.
[40] M. R. Daliri, “Chi-square distance kernel of the gaits for the diagnosis of Parkinson's disease,” Biomedical Signal Processing and Control, vol. 8, no. 1, pp. 66-70, 2013.
[41] S.-H. Lee, and J. S. Lim, “Parkinson’s disease classification using gait characteristics and wavelet-based feature extraction,” Expert Systems with Applications, vol. 39, no. 8, pp. 7338-7344, 2012.
[42] N. Khoury, F. Attal, Y. Amirat, L. Oukhellou, and S. Mohammed, “Data-driven based approach to aid parkinson’s disease diagnosis,” Sensors, vol. 19, no. 2, pp. 242, 2019.
[43] Ö. F. Ertuğrul, Y. Kaya, R. Tekin, and M. N. Almalı, “Detection of Parkinson's disease by shifted one dimensional local binary patterns from gait,” Expert Systems with Applications, vol. 56, pp. 156-163, 2016.
[44] A. Khorasani, and M. R. Daliri, “HMM for classification of Parkinson’s disease based on the raw gait data,” Journal of medical systems, vol. 38, no. 12, pp. 147, 2014.
[45] M. R. Daliri, “Automatic diagnosis of neuro-degenerative diseases using gait dynamics,” Measurement, vol. 45, no. 7, pp. 1729-1734, 2012.
[46] Y. Wu, and S. Krishnan, “Statistical analysis of gait rhythm in patients with Parkinson's disease,” IEEE transactions on neural systems and rehabilitation engineering, vol. 18, no. 2, pp. 150-158, 2009.
[47] J. C. Vasquez-Correa, T. Arias-Vergara, J. Orozco-Arroyave, B. M. Eskofier, J. Klucken, and E. Noth, “Multimodal assessment of Parkinson's disease: a deep learning approach,” IEEE journal of biomedical and health informatics, pp. 1-12, 2018.
[48] G. Paragliola, and A. Coronato, “Gait Anomaly Detection of Subjects With Parkinson’s Disease Using a Deep Time Series-Based Approach,” IEEE Access, vol. 6, pp. 73280-73292, 2018.
[49] P. Prabhu, A. Karunakar, H. Anitha, and N. Pradhan, “Classification of gait signals into different neurodegenerative diseases using statistical analysis and recurrence quantification analysis,” Pattern Recognition Letters, pp. 1-7, 2018.
[50] Q. Ye, Y. Xia, and Z. Yao, “Classification of gait patterns in patients with neurodegenerative disease using adaptive neuro-fuzzy inference system,” Computational and mathematical methods in medicine, vol. 2018, pp. 1-8, 2018.
[51] Y. N. Jane, H. K. Nehemiah, and K. Arputharaj, “A Q-backpropagated time delay neural network for diagnosing severity of gait disturbances in Parkinson’s disease,” Journal of biomedical informatics, vol. 60, pp. 169-176, 2016.
[52] J. M. Hausdorff, Z. Ladin, and J. Y. Wei, “Footswitch system for measurement of the temporal parameters of gait,” Journal of biomechanics, vol. 28, no. 3, pp. 347-351, 1995.
[53] J. Nilsson, and A. Thorstensson, “Adaptability in frequency and amplitude of leg movements during human locomotion at different speeds,” Acta Physiologica Scandinavica, vol. 129, no. 1, pp. 107-114, 1987.
[54] J. Sadowsky, “The continuous wavelet transform: a tool for signal investigation and understanding,” Johns Hopkins APL Technical Digest, vol. 15, pp. 306-306, 1994.
[55] J. Ashmead, “Morlet wavelets in quantum mechanics,” arXiv preprint arXiv:1001.0250, 2010.
[56] C. Torrence, and G. P. Compo, “A practical guide to wavelet analysis,” Bulletin of the American Meteorological society, vol. 79, no. 1, pp. 61-78, 1998.
[57] P. C. Liu, “Wavelet spectrum analysis and ocean wind waves, ” Wavelet Analysis and Its Applications, pp. 151-166: Elsevier, 1994.
[58] C. Torrence, and P. J. Webster, “Interdecadal changes in the ENSO–monsoon system,” Journal of climate, vol. 12, no. 8, pp. 2679-2690, 1999.
[59] A. Grinsted, J. C. Moore, and S. Jevrejeva, “Application of the cross wavelet transform and wavelet coherence to geophysical time series,” Nonlinear processes in geophysics, vol. 11, no. 5/6, pp. 561-566, 2004.
[60] I. T. Jolliffe, “Introduction”, in Principal Component Analysis, 2nd ed. United States, New York: Springer, 2002, ch. 1, pp. 1.
[61] K. O'Shea, and R. Nash, “An introduction to convolutional neural networks,” arXiv preprint arXiv:1511.08458, 2015.
[62] P. Refaeilzadeh, L. Tang, and H. Liu, “Cross-validation,” Encyclopedia of database systems, pp. 532-538, 2009.
[63] W. J. Youden, “Index for rating diagnostic tests,” Cancer, vol. 3, no. 1, pp. 32-35, 1950.
[64] T. Fawcett, “An introduction to ROC analysis,” Pattern recognition letters, vol. 27, no. 8, pp. 861-874, 2006.
[65] J. Hintze, “NCSS statistical software. 1998,” NCSS Kaysville, UT.
[66] M. Yang, H. Zheng, H. Wang, and S. McClean, “Feature selection and construction for the discrimination of neurodegenerative diseases based on gait analysis,” 3rd International Conference on Pervasive Computing Technologies for Healthcare, pp. 1-7:IEEE, 2009.