隨著量化生活(Quantified Self)這一概念的興起，智慧型穿戴裝置愈發蓬勃發展，使用上簡單、無侵入性，而且具有醫療用途的穿戴型裝置還能持續監測生理訊號。在本篇論文中，將利用能夠即時監測並記錄心率變異(Heart Rate Variability, HRV)的貼片型心電儀和結合機器學習(Machine Learning, ML)演算法進行建模分析。
本次研究中透過受測者的活動行為自我評量和HRV的訊息特徵相互結合，並透過自然語言分析和專家知識將受測者隨興利用字串記錄下的相近活動行為進行分群，並將複雜的使用者活動行為字詞分解成可以被理解的訊息。實驗成果顯示，我們經由心率平均值將資料初步排序和自然語言分析的前處理過程，借由機器學習的隨機森林建模分析以及後處理的Savitzky-Golay低通濾波器，能對使用者一整天的日常動作常模進行評估以及預測。
我們希望本研究的成果未來能對醫療領域有所貢獻，並提供給心理治療師成為個案失眠問題的一項參考指標，或為長期健康照護提出實用的貢獻。

Commercially available smart wearable devices have made constantly monitoring physiological signals simple and non-intrusive. Many new applications can be implemented based on continues recording of signals, such as Electrocardiogram (ECG), Electroencephalogram (EEG), Electroneurogram (ENG), and Electromyogram (EMG), etc., through sensors like patches and smart bracelets. Heart Rate Variability (HRV) is one of such measuring with many aggregated outputs that can be used and provides rich information about wearer’s physiological conditions. In this research, we aim to use wearable HRV patch to gather signals from users and analyze their daily activities through machine learning algorithms. By gathering HRV records with self-report information from subjects, we can propose a preprocessing architecture based on natural language processing to analyze the relationships of the user activities, as well as organize these behaviors into comprehensible information. Using Random Forest algorithm to modeling our features, data and through Savitzky-Golay filter to visualize the data for interpretation by experts.

[1] G. Wolf, “The quantified self,” TED (conference), Mar. 2012.
[2] C.H. Hsieh, R.H. Lu, N.H. Lee, W.T. Chiu, M.H. Hsu, YCJ Li, “Novel solutions for an old disease:Diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks,” Surgery, 149(1), 87-93, Jan. 2011.
[3] W. L. Lin, “The Coming of an Aged Society in Taiwan: Issues and Policies,” Asian Social Work and Policy Review, Volume 4, Issue 3, pp. 148–162, Oct. 2010.
[4] 台灣睡眠醫學學會，「2017 台灣睡眠醫學學會最新調查」，台灣睡眠醫學學會第十五屆學術研討會，2017年。
[5] Sin, Wai-man Celia, “Systematic review on the effectiveness of caffeine abstinence in improving quality of sleep,” Diss. School of Nursing, The Hong Kong Polytechnic University, 2007.
[6] C. E. Carney, J. D. Edinger, B. Meyer, L. Lindman, T. Istre, “Daily activities and sleep quality in college students,” Chronobiol Int. 2006, 23(3), 623–637, Jun. 2016.
[7] 翁根本、何慈育、歐善福、林竹川、謝凱生，「心率變動性分析」，臺灣醫界，Vol.52，No.6，Jun. 2009。
[8] E.H. Hon, S.T. Lee, “Electronic evaluations of the fetal heart rate patterns preceding fetal death, further observations,” Am J Obstet Gynec, 87, 814–26, Nov. 1963.
[9] J. T. Parer, T. King, S. Flanders, M. Fox, S. J. Kilpatrick, “Fetal acidemia and electronic fetal heart rate patterns: Is there evidence of an association?,” J Matern Fetal Neonatal Med, 19(5), 289–294,May 2006.
[10] H. Kudat, V. Akkaya, A. B. Sozen, S. Salman, S. Demirel, M. Ozcan, D. Atilgan, M. T. Yilmaz, O. Guven, “Heart Rate Variability in Diabetes Patients,” J Int Med Res, 34(3), 291–296, May-Jun. 2006.
[11] R. E. Kleiger, J. P. Miller, J. T. Bigger, Jr, A. J. Moss, “Decreased heart rate variability and its association with increased mortality after acute myocardial infarction,” Am J Cardiol, 59(4), 256–262, Feb. 1987.
[12] M. Vaseghi and K. Shivkumar, “The Role of the Autonomic Nervous System in Sudden Cardiac Death,” Progress in Cardiovascular Diseases, vol. 50, no. 6, pp. 404-419, May-Jun. 2008.
[13] F. Rosenblatt, “The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain,” Cornell Aeronautical Laboratory, Psychological Review, v65, No. 6, pp. 386–408, Nov. 1958.
[14] J. R. Quinlan, “Induction of decision trees,” Machine Learning, 1(1):81-106, Mar. 1986.
[15] J. R. Quinlan, “C4.5: Programs for Machine Learning,” Machine Learning, Volume 16, Issue 3, pp 235–240, Sept. 1994.
[16] T. K. Ho, “Random Decision Forest,” Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, pp. 278–282, Aug. 1995.
[17] M. Bates, “Models of natural language understanding,” Proceedings of the National Academy of Sciences of the United States of America,92 (22): 9977–9982, Oct. 1995.
[18] N. Chomsky, “Syntactic Structures,” The Hague/Paris: Mouton. Feb. 1957.
[19] M. Shoaib, S. Bosch, O. D. Incel, H. Scholten, P. J. M. Havinga, “Complex Human Activity Recognition Using Smartphone and Wrist-Worn Motion Sensors,” Sensors (Basel), Apr. 2016.
[20] Z. Feng, L. Mo, M. Li, “A Random Forest-based ensemble method for activity recognition,” Conf Proc IEEE Eng Med Biol Soc, Aug. 2015.
[21] J. Li, Y. Wang, B. Lei, J. Z. Cheng, J. Qin, T. Wang, S. Li, D. Ni, “Automatic Fetal Head Circumference Measurement in Ultrasound using Random Forest and Fast Ellipse Fitting,” IEEE Journal of Biomedical and Health Informatics, May 2017.
[22] Berkay Aydin, Ahmet Alp Kindiroglu, Oya Aran, Lale Akarun, “Automatic personality prediction from audiovisual data using random forest regression,” 2016 23rd International Conference on Pattern Recognition (ICPR), Apr. 2017.
[23] Anna Bosch, Andrew Zisserman, Xavier Munoz, “Image Classification using Random Forests and Ferns,” 2007 IEEE 11th International Conference on Computer Vision, Oct. 2007.