隨著全球逐漸邁向高齡化社會，與高齡相關的神經退化性疾病受到更多重視，其中第二常見的疾病為帕金森氏症(Parkinson's disease, PD)，近年來甚至有年輕化的趨勢。患者會有運動症狀及非運動症狀，隨著時間病情會漸漸惡化，提早診斷有助於減緩病情發展。其中運動症狀主要有顫抖、肌肉僵硬、動作遲緩、姿勢不穩，診斷方式為透過對運動狀態的評估。常見的方法主要集中在穿戴式裝置上，使用加速度計、陀螺儀和表面肌電圖來獲得運動症狀的相關訊息。
本論文提出使用調頻連續波(frequency-modulated continuous-Wave, FMCW)毫米波雷達對「手指輕敲實驗」做非接觸式測量，將雷達測量的相位變化轉換成手指的位置變化來獲得手指運動時位置變化的時間序列資料。
在傳統的手指輕敲實驗中往往由醫生直接用眼睛觀察，判斷上較為主觀以及模糊。有別於傳統方式此實驗方式的優點在於將實驗結果量化後使用大量資料讓模型學習後擁有判斷異常的能力，且不須使用穿戴式裝置。在本論文中所提出的實驗中要求受試者跟隨固定頻率之節拍器輕敲手指。先大量蒐集正常資料與模擬異常的資料，再經由深度學習的方式，使用一維卷積神經網路模型區分出正常資料與模擬異常資料。

As global aging, increasing attention has been paid to neurodegenerative diseases related to advanced age, the second most prevalent disease is Parkinson's disease (PD), the prevalence of Parkinson's disease rising in younger adults. Patients have motor symptoms and non-motor symptoms, and the disease will gradually worsen over time. Early diagnosis may help slow down disease progression. The motor symptoms mainly include Tremor, Rigidity, Bradykinesia (slowness of movement), and Postural instability. The diagnosis method is through the motor assessment. Common approaches focus on wearable devices, using accelerometers, gyroscopes or surface electromyography to obtain information about motor symptoms.
This paper proposes to use frequency-modulated continuous-wave (FMCW) millimeter-wave radar to perform non-contact measurement of Finger Tapping Test (FTT), and convert the phase change measured by the radar into the position change of the finger to obtain the time series data of finger's movement track.
The advantage of method in this paper is that after quantifying the experimental results, a large amount of data is used, so that the model has the ability to judge anomaly after learning. In the experiments presented, subjects were asked to tap their fingers following a fixed-frequency metronome. Normal data and simulated anomaly data are collected first, and then use one dimensional convolutional neural networks (1D-CNN) model, normal data and simulated abnormal data are distinguished.

[1] World Health Organization. "GHE: Life expectancy and healthy life expectancy." Available: https://www.who.int/data/gho/data/themes/mortality-and-global-health-estimates
[2] 內政部我國生命表(2022)。歷次國民生命表。取自https://www.moi.gov.tw/cl.aspx?n=3415
[3] 國家發展委員會(2022)。人口推估查詢系統。取自 https://pop-proj.ndc.gov.tw/index.aspx
[4] L. V. Kalia and A. E. Lang, "Parkinson's disease," Lancet, vol. 386, no. 9996, pp. 896-912, Aug 2015.
[5] National Institute on Aging. (2022,April 14). "Parkinson’s Disease: Causes, Symptoms, and Treatments." Available: https://www.nia.nih.gov/health/parkinsons-disease
[6] Parkinson's Foundation. (n.d.). "Movement Symptoms." Available: https://www.parkinson.org/Understanding-Parkinsons/Movement-Symptoms
[7] A. Jobbagy et al., "Analysis of finger-tapping movement," J. Neurosci. Methods, vol. 141, no. 1, pp. 29–39, Jan. 2005.
[8] M. M. Hoehn and M. D. Yahr , "Parkinsonism: onset, progression and mortality." Neurology, vol. 17, no. 5, pp. 427–442, May. 1967, doi:10.1212/wnl.17.5.427.
[9] Y. Sano et al., "Reliability of Finger Tapping Test Used in Diagnosis of Movement Disorders," 2011 5th International Conference on Bioinformatics and Biomedical Engineering, 2011, pp. 1-4, doi: 10.1109/icbbe.2011.5780409.
[10] R. Okuno, M. Yokoe, K. Akazawa, K. Abe and S. Sakoda, "Finger taps movement acceleration measurement system for quantitative diagnosis of Parkinson's disease," 2006 International Conference of the IEEE Engineering in Medicine and Biology Society, 2006, pp. 6623-6626, doi: 10.1109/IEMBS.2006.260904.
[11] M. Djurić-Jovičić, N. Jovičić, A. Roby-Brami, M. Popović, V. Kostić, and A. Djordjević, "Quantification of Finger-Tapping Angle Based on Wearable Sensors," Sensors, vol. 17, no. 2, p. 203, Jan. 2017, doi: 10.3390/s17020203.
[12] N. Akram et al., "Developing and assessing a new web-based tapping test for measuring distal movement in Parkinson’s disease: a Distal Finger Tapping test," Sci Rep, vol. 12, no. 1, p. 386, Jan. 2022, doi:10.1038/s41598-021-03563-7.
[13] J. A. Grahn and M. Brett, "Impairment of beat-based rhythm discrimination in Parkinson’s disease," Cortex, vol. 45,no. 1, pp. 54-61, Jan. 2009, doi:10.1016/j.cortex.2008.01.005.
[14] D. L. Harrington, K. Y. Haaland, N. Hermanowicz, "Temporal processing in the basal ganglia," Neuropsychology, vol. 12,no. 1, pp. 3-12, Jan.1998, doi:10.1037//0894-4105.12.1.3
[15] M. Bernardinis, S. F. Atashzar, M. Jog and R. V. Patel, "Visual Temporal Perception in Parkinson’s Disease Analyzed Using a Computer-Generated Graphical Tool," 2019 9th International IEEE/EMBS Conference on Neural Engineering (NER), 2019, pp. 65-68, doi: 10.1109/NER.2019.8717099.
[16] F. Milano et al. "Parkinson's Disease Patient Monitoring: A Real-Time Tracking and Tremor Detection System Based on Magnetic Measurements," Sensors, vol. 21, no. 12, p. 4196, Jun. 2021, doi: 10.3390/s21124196.
[17] K. Chang, RF and Microwave Wireless Systems. New York, NY, USA: John Wiley & Sons, Inc., 2000
[18] C. Iovescu and S. Rao, "The fundamentals of millimeter wave sensors," Texas Instrum., Dallas, TX, USA, White Paper SPYY005A, Jul. 2016.
[19] Texas Instruments. 60GHz mmWave Sensor EVMs (Rev.E). (2022). [Online]. Available: https://www.ti.com/lit/ug/swru546e/swru546e.pdf
[20] S. Rao. Introduction to mmWave sensing: FMCW radars. (2017). [Online]. Available: https://training.ti.com/sites/default/files/docs/mmwaveSensing-FMCW-offlineviewing_0.pdf
[21] Texas Instruments. Vital signs 68xx Developer's Guide. (2017). [Online]. Available: https://dev.ti.com/tirex/explore/node?node=AKU0Y-htBc6mwPY1fsOUvw__VLyFKFf__LATEST.
[22] C. Shorten and T. M. Khoshgoftaar, "A survey on Image Data Augmentation for Deep Learning," J.Big Data, vol. 6, no. 1, pp. 60, July. 2019.
[23] J. D. Sui and T. S. Chang, "Deep Gait Tracking With Inertial Measurement Unit," in IEEE Sensors Letters, vol. 3, no. 11, pp. 1-4, Nov. 2019, Art no. 7002404, doi: 10.1109/LSENS.2019.2947625
[24] S.G.K. Patro and K.K. Sahu, " Normalization: A Preprocessing Stage," Int. Adv. Res. J. Sci. Eng. Technol., vol. 2, no. 3, pp. 20-22, Mar. 2015, doi:10.17148/IARJSET.2015.2305
[25] G. Ian, B. Yoshua, and C. Aaron, Deep Learning. Cambridge,MA, USA: MIT Press,
2016.
[26] K. M. Ting, "Confusion Matrix," in Encyclopedia of Machine Learning and Data Mining, C. Sammut and G. I. Webb, Ed. Boston, MA, USA:Springer, 2017.
[27] N. Chinchor, "MUC-4 Evaluation Metrics," in Proceedings of the 4th Conference on Message Understanding (McLean, Virginia) (MUC4 ’92), Association for Computational Linguistics, USA, 1992, pp. 22–29.