臺灣博碩士論文加值系統

本篇論文的主要目的是減少血壓量測時因干擾所產生的不準確數據，而干擾有可能是因為血壓機本身的問題或白袍症(White Coat Hypertension, WCH)的發生等。白袍症是當量測者面對醫護人員或是在醫療診所內因為緊張而血壓異常上升的現象，量測者很可能會因為看到不準確的數據而恐慌，甚至造成醫護人員誤判病情。藉由支援向量迴歸(Support Vector Regression, SVR)在非線性資料上能夠預測趨勢的特性，我們能夠預測出合理的血壓資料與容忍一些異常的數據，呈現出當次測量結果是否合理。然而找到適當的參數去建立SVR模型是很複雜，因此，為了提升預測的準確度我們使用基因演算法(Genetic Algorithm, GA)尋找參數。在實驗模擬過程中有十名參與者(四名女性、六名男性)，測量了兩個月的血壓，最後我們取其中的46筆血壓資料，並在其中加入干擾作為我們的實驗。從實驗成果中顯示，SVR並不會因為干擾而影響估測趨勢，因此SVR可以有效的預測血壓數據。本研究實作了血壓預測模型系統，可由量測到的血壓數據訓練模型，進而預測血壓，如果在估測範圍外，則視為異常的血壓。會將血壓資料推播至手機端，更為方便的檢視血壓資料。

The main purpose of this thesis is to reduce the disturbances of blood pressure measurement, where they sometimes arise from the blood pressure manometer, and white coat hypertension, etc. White coat hypertension is a phenomenon of abnormally increasing blood pressure when people fear to face to the medical workers or in clinic setting and it may also cause panic when seeing the inaccuracies of blood pressure. By the superior characteristic of support vector regression (SVR) with forecasting the trend of nonlinear data, we not only can predict the reasonable trend of blood pressure data but also tolerate the abnormal data. By SVR forecasting for improving blood pressure measurement, we can tell that whether the current measurement is reasonable or not. However, it is complicated to determine the appropriate parameters of establishing SVR model, so we used genetic algorithm (GA) to find the parameters for improving the accuracy of the predicted trend. In simulating process, there were 10 participants (four females and six males) who measured blood pressure for 2 months, and finally we took 46 measurements for our experiment. We also add interference to real blood pressure test data. By the proposed SVR method, the experimental result shows that the prediction trend was not influenced by the interference. Thus, we demonstrate that SVR is applicable and efficient for predicting blood pressure data. We implement the blood pressure forecasting system, predicting the blood pressure with trained model. If the prediction value is out of range, the system will judge it to abnormal blood pressure. Also we push the data to Android phone that make user more convenient to view.

目次
圖目錄 IX
表目錄 XI
第一章 緒論 1
第一節 研究背景 1
第二節 研究目的 2
第三節 論文架構 3
第二章 文獻探討 4
第一節 血壓狀態與量測探討 4
第二節 支援向量迴歸與基因演算法 8
第三節 手機血壓量測APP探討 10
第三章 研究方法 11
第一節 血壓預測模型系統 12
第二節 利用真實血壓資料建立SVR模型 16
第三節 利用基因演算法找尋適當SVR參數 20
第四節 收集血壓資料 24
第四章 研究結果 25
第一節 實驗結果與分析 25
第二節 血壓預測模型系統實作成果 33
一、 血壓預測模型系統(電腦端) 33
二、 血壓預測模型系統(手機端) 36
三、 系統實測結果 38
第五章 結論與建議 40
第一節 結論 40
第二節 建議 40
參考文獻 41
一、 網頁參考文獻 41
二、 英文參考文獻 44
附錄 47

網頁參考文獻

[1] 國家發展委員會(2014)。聯合國世界人口高齡化趨勢分析。線上檢索日期：2015年5月1號。網址：http://www.ndc.gov.tw/m1.aspx?sNo=0057397#.VLYjiyuUcnU.
[2] 衛生福利部統計處(2014)。民國102年臺灣死因。線上檢索日期：2015年5月1號。網址：
http://www.mohw.gov.tw/cht/DOS/Statistic.aspx?f_list_no=312&;fod_list_no=5150.
[3] 衛生福利部國民健康屬(2015)。高血壓罹患人數。線上檢索日期：2015年5月1號。網址：
http://www.hpa.gov.tw/BHPNet/Web/News/News.aspx?No=201311070001.
[4] CNA中央通訊社(2014)。白袍症。線上檢索日期：2015年5月1號。網址：
http://www.cna.com.tw/news/firstnews/201403260482-1.aspx.
[5] Mayo Clinic (2012). High blood pressure (hypertension), Get the most out of home blood pressure monitoring. Retrieved May 1, 2015 from the World Wide Web:
http://www.mayoclinic.org/diseases-conditions/high-blood-pressure/in-depth/high-blood-pressure/art-20047889.
[6] 中華民國防高血壓協會(2011)。認識高血壓。線上檢索日期：2015年5月1號。網址：
http://hypertension.org.tw/know.php.
[7] 維基百科(2014)。血壓。線上檢索日期：2015年5月1號。網址：
http://zh.wikipedia.org/wiki/%E8%A1%80%E5%A3%93.
[8] AHA (2014). Understanding Blood Pressure Readings. Retrieved May 1, 2015 from the World Wide Web:
http://www.heart.org/HEARTORG/Conditions/HighBloodPressure/AboutHighBloodPressure/Understanding-Blood-Pressure-Readings_UCM_301764_Article.jsp.
[9] Mayo Clinic (2014). Low blood pressure (hypotension). Retrieved May 1, 2015 from the World Wide Web:
http://www.mayoclinic.org/diseases-conditions/low-blood-pressure/basics/definition/con-20032298.
[10] AHA (2014). Low Blood Pressure. Retrieved May 1, 2015 from the World Wide Web:
http://www.heart.org/HEARTORG/Conditions/HighBloodPressure/AboutHighBloodPressure/Low-Blood-Pressure_UCM_301785_Article.jsp.
[11] AHA (2014). What is High Blood Pressure? Retrieved May 1, 2015 from the World Wide Web:
http://www.heart.org/HEARTORG/Conditions/HighBloodPressure/AboutHighBloodPressure/What-is-High-Blood-Pressure_UCM_301759_Article.jsp.
[12] AHA (2014). Understand Your Risk for High Blood Pressure. Retrieved May 1, 2015 from the World Wide Web:
http://www.heart.org/HEARTORG/Conditions/HighBloodPressure/UnderstandYourRiskforHighBloodPressure/Understand-Your-Risk-for-High-Blood-Pressure_UCM_002052_Article.jsp.
[13] Mayo Clinic (2014). High blood pressure (hypertension). Retrieved May 1, 2015 from the World Wide Web:
http://www.mayoclinic.org/diseases-conditions/high-blood-pressure/basics/risk-factors/con-20019580.
[14] 維基百科(2014)。血壓計。線上檢索日期：2015年5月1號。網址：
http://zh.wikipedia.org/wiki/%E8%A1%80%E5%8E%8B%E8%AE%A1.
[15] Mayo Clinic (2013). High blood pressure (hypertension). Retrieved May 1, 2015 from the World Wide Web:
http://www.mayoclinic.org/diseases-conditions/high-blood-pressure/expert-answers/blood-pressure/faq-20057853.
[16] AHA (2011). Ambulatory monitoring reveals many patients have ‘white coat’ hypertension. Retrieved May 1, 2015 from the World Wide Web:
http://newsroom.heart.org/news/1298.
[17] Chih-Chung Chang &; Chih-Jen Lin (2014). LIBSVM. Retrieved May 1, 2015 from the World Wide Web: http://www.csie.ntu.edu.tw/~cjlin/libsvm.
[18] MathWorks (2015). Genetic Algorithm Options. Retrieved May 1, 2015 from the World Wide Web:
http://www.mathworks.com/help/gads/genetic-algorithm-options.html#f6633.
[19] Google Play (2013)。手部影像血壓計。線上檢索日期：2015年5月1號。網址：
https://play.google.com/store/apps/details?id=nctu.lab615.brian&;hl=zh_TW.
[20] Google Play (2014)。累計。血壓(BP)監測器。線上檢索日期：2015年5月25號。網址：
https://play.google.com/store/apps/details?id=ufone.bloodpressuremonitor.bpcalculator.
[21] Google Play (2015)。臉部影像血壓計。線上檢索日期：2015年5月25號。網址：
https://play.google.com/store/apps/details?id=camera.app.blood_pressure.

英文參考文獻

Stergiou, G. O., Baibas, N. M., Gantzarou, A. P., Skeva, I. I., Kalkana, C. B. Roussias, L. G., &; Mountokalakis, T. D. (2002). Reproducibility of home, ambulatory,and clinic blood pressure: implications for the design of trials for the assessment of antihypertensive drug efficacy. Am. J. Hypertens, vol. 15, pp. 101–104.
Bobrie, G., Gene ́s N., Vaur, L., Clerson, P., Vaisse, B., Mallion, J.-M., &; Chatellier, G. (2001). Is “isolated home” hypertension as opposed to “isolated office” hypertension a sign of greater cardiovascular risk? Arch. Intern. Med, vol. 161, pp. 2205–2211.
Zhang, J., &; Kesteloot, H. (1999). Anthropometric, lifestyle and metabolic determinants of resting heart rate. European Heart Journal, pp. 103–110.
Valentini, M., &; Parati G. (2009). Variables influencing heart rate. Progress in Cardiovascular Diseases, vol. 52, Issue 1, pp. 11-19
Vapnik, V. (1995). The Nature of Statistical Learning Theory. Springer-Verlag New York.
Joachims, T. (1998). Text categorization with Support Vector Machines: Learning with many relevant features. Lecture Notes in Computer Science, vol. 1398, pp. 137-142.
Burges, Christopher J. C. (1998). A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining, &; Knowledge Discovery, vol. 2, Issue 2, pp. 121-167.
Osuna, E., Freund, R. &; Girosi, F. (1997). Training support vector machines: an application to face detection. Computer Vision and Pattern Recognition, pp. 103-136.
Vapnik, V., Golowich, S. E., &; Smola, A. (1997). Support Vector Method for Function Approximation, Regression Estimation, and Signal Processing. Advance in neural information processing system, vol. 9, pp. 281-287.
Smola, A. J. &; Scho ̈lkopf, B. (2004). A tutorial on Support Vector Regression. Statistics and Computing, vol. 14, pp. 199-222.
Wu, C. H., Ho, J. M. &; Lee, D. T. (2004). Travel-Time Prediction with Support Vector Regression. IEEE Trans. Intell.Transport. Syst, vol. 5, no. 4.
Yu, P. S., Chen, S. T. &; Chang, F. I. (2006). Support vector regression for real-time flood stage forecasting. Journal of Hydrology, vol. 328, Issues 3-4, pp. 704-716.
Elattar, E. E. (2010). Electric Load Forecasting Based on Locally Weighted Support Vector Regression. IEEE Systems, Man, and Cybernetics Society, vol. 40, Issue 4, pp. 438-447.
Huang, j. X., Hung, J. C. (2014). Forecasting Stock Market Indices Using RVC-SVR. Advanced Approaches to Intelligent Information and Database Systems, vol. 551, pp. 89-96.
Chen, J. Q., Xue, X. P., Ha, M. g., Yu, D. R. &; Ma, L. T. (2014). Support vector regression method for wind speed prediction incorporating probability prior knowledge. Mathematical Problems in Engineering, vol. 2014 (2014), Article ID 410489, 10 pages.
Jain, R. K., Smith, K. M., Culligan, P. J. &; Taylor, J. E. (2014). Forecasting energy consumption of multi-family residential buildings using support vector regression: Investigating the impact of temporal and spatial monitoring granularity on performance accuracy. Applied Energy, vol. 123, pp. 168-178.
Chen, K. Y. &; Wang, C. H. (2005). Support vector regression with genetic algorithms in forecasting tourism demand. Tourism Management, vol. 28, Issue 1, February 2007, pp. 215-226.
Braga, P. L., Adriano L. I. Oliveira &; Silvio R. L. Metra (2008). A DA-based feature selection and parameters optimization for support vector regression applied to software effort estimation. Proceedings of the 2008 ACM symposium on Applied computing, pp. 1788-1792.
Li, X. M., Ding, L. X., Li, Y., Xu, G. &; Li, J. B. (2010). Hybrid Genetic Algorithm and Support Vector Regression in Cooling Load Prediction. Knowledge Discovery and Data Mining, pp. 527-531.
Zhao, M. Y., Fu, C., Ji, L. P., Tang, K. &; Zhou, M. T. (2011). Feature selection and parameter optimization for support vector machines: A new approach based on genetic algorithm with feature chromosomes. Expert Systems with Applications, vol. 38, Issue 5, pp. 5197–5204.
Yuan, F. C. (2012). Parameters Optimization Using Genetic Algorithms in Support Vector Regression for Sales Volume Forecasting. Applied Mathematics, Vol. 3, No. 10A, pp. 1480-1486.
Guo, M. L., Li, D. J., Du, C. B., Jia, Z. H., Qin, X. Z., Chen, L., Sheng, L., &; Li, H. (2012). Prediction of the Busy Traffic in Holidays Based on GA-SVR. Advances in Computer Science and Information Engineering, vol. 2, pp. 557-582.
Kalteh, A. M. (2014). Wavelet Genetic Algorithm-Support Vector Regression (Wavelet GA-SVR) for Monthly Flow Forecasting. Water Resources Management, vol. 29, Issue 4, pp. 1283-1293.
Vaseghi, S. V. (2000). Advanced Digital Signal Processing and Noise Reduction, Impulsive noise (pp. 355-377). New York: Wiley.