在台灣腎臟病是一個常見且嚴重的疾病，針對腎臟病的處理，腹膜透析是一個僅次於血液透析的洗腎方式，這個方法比起血液透析可以更節省醫療成本，但是很容易發生感染產生腹膜炎，因此我們設計了一套腹膜透析的居家照護系統去監督病患的透析液情形並且記錄下來提供醫生做參考
不同於傳統的利用生化分析的結果去做預測需要耗費較多的時間，我們的系統主要是利用色度和濁度去篩檢病患做完腹膜透析之後的透析液來判斷是否有腹膜炎的現象發生，我們的方法可以有效的省去生化篩檢的時間。在資料的蒐集上面，我們會先把透析液倒入我們特製的容器中，利用手機照相功能還有我們自製的手機程式去獲得透析液的色度，再利用一個LED的發射器發射光源到透析液內部藉由測量光線的衰減來判斷透析液的混濁程度。
在篩檢的流程上面，我們用了一個簡單的三步驟去執行，第一步是用高斯混和模型(Gaussian Mixture Model)去檢測該透析液顏色是否異常，第二步是針對我們目前所蒐集到的實驗資料做假設檢定(Hypothesis Testing)的一個透光度和發炎與否的標準來判斷是否有發炎的情形，針對在模糊地區的資料，我們會再根據同一個人過去的測量結果利用指數移動平均法(Exponential Moving Average)做一個趨勢分析判斷他的透析液情形是正在好轉或是惡化。
總共我們蒐集到的75筆資料裡面，根據這些資料下去做篩檢可以得到94.5%的準確率，總而言之，我們的這套系統的篩檢方法不但承襲了原先可以快速篩檢的優勢在準確率上更有顯著的提升。

In Taiwan, kidney disease is an usual disease and common issue. Peritoneal dialysis (PD) is common way to treat kidney disease patient. We have develop a portable homecare system to supervise the patients' dialysate condition and record for the doctors to diagnosis. However, our expectation on this system is to help the users can grasp their health condition immediately, and give them a suggestion about visiting the doctors or not. Therefore, my research focused on the develop of the algorithm which can preliminary screen out the inflammation samples and normal samples for doctors and users to refer.
Different from the traditional biomedical testing, our system use colorimetric information and absorbance to screen out the peritonitis from patients with PD treatment. To collect the colorimetric of the PD effluent, we should pour the PD effluent into the transparent container, then take a picture for the color checker and the container with effluent. To get the absorbance of the PD effluent, we use arduino micro controller to drive the light emitter to incident the light pass through the PD effluent and calculate the light intensity to get the absorbance of the PD effluent. After these steps, the data will be sent to the cloud data base and we can analysis the patients' condition with our screening method base on the data we collected.

In our screening method, we establish a three steps flow for the screening. First, using gaussian mixture model (GMM) cluster the samples of PD effluent into undetectable and detectable two groups. This step we take the colorimetric information from the dialysate for the features. Thus, the undetectable samples will be exclude. and the detectable samples will be sent to the next screening stage. Second, according to the hypothesis test, we calculate a standard threshold according to the turbidity data collected by National Taiwan University Hospital (NTUH) and we. Operating with this standard, according to the the region where the samples are distributed to, once their region are located on the fuzzy region, then the third step will be operated to solve it. In the last stage, we use the exponential moving average (EMA) to calculate the same users' historical data and compare with it to see whether the newest sample getting better or not. In brief, these three stages screening can give a simple and fast determination after the users finish the whole screening.
So far, we have 75 samples, based on this database, this algorithm can reach 94.5\% accuracy. In summary we design an screening algorithm on our homecare system, and it not only improve the accuracy from the original system but also adopts the characteristic of the fast screening and easy to operate. We believe this system can bring the users a better life.

Abstract i
1 Introduction 1
1.1 Background . . . . . . . . . . . . . . . . . 1
1.1 End-stage Renal Disease and Dialysis . . . . 1
1.1.2 Peritoneal Dialysis Homecare System. . . . 2
1.2 Motivation . . . . . . . . . . . . . . . . . 3
1.3 Main Contributions . . . . . . . . . . . . . 3
1.4 Organization . . . . . . . . . . . . . . . . 4
2 Overview of Peritonitis Diagnosis 5
2.1 Hemodialysis and Peritoneal Dialysis . . . . 5
2.1.1 Principle of Hemodialysis . . . . . .. . . 5
2.1.2 Comparison with Peritoneal Dialysis and Hemodialysis . . . . . . . . 6
2.2 Introductioin of Peritonitis and Clinical Test . . . . . . . . . . . . . . . . . . 7
2.2.1 Introduciton of Peritonitis . . . . . . . . . . . . . . . . . . . . . . . 7
2.3 Literature Overview of Screening Technique for Peritonitis . . . . . . . . . . 9
2.3.1 Prevention of Peritonitis . . . . . . . . . . . . . . . . . . . . . . . . 9
2.3.2 Screening Technique for Peritoneal Dialysis . . . . . . . . . . . . . . 10
2.4 Comparison of Screening Technique for Peritonitis . . . . . . . . . . . . . . 16
2.5 Proposed Screening Architecture . . . . . . . . . . . . . . . . . . . . . . . 16
3 Proposed Peritonitis Diagnosis Algorithm 21
3.1 System Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
3.1.1 Overview of Sensing Model . . . . . . . . . . . . . . . . . . . . . . 22
3.1.2 Overview of Sensing Method . . . . . . . . . . . . . . . . . . . . . 23
3.1.3 Overview of screening method . . . . . . . . . . . . . . . . . . . . . 25
3.2 Screening Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
3.2.1 Color Detection Method . . . . . . . . . . . . . . . . . . . . . . . . 29
3.2.2 Turbidity Detection Method . . . . . . . . . . . . . . . . . . . . . . 33
3.2.3 Individual Long-term Tracking Algorithm . . . . . . . . . . . . . . . 39
3.3 Expected Results of Screening Algorithm . . . . . . . . . . . . . . . . . . . 42
3.3.1 Color Detection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42
3.3.2 Turbidity Detection . . . . . . . . . . . . . . . . . . . . . . . . . . . 43
3.3.3 Individual Long-term Tracking . . . . . . . . . . . . . . . . . . . . 44
4 Implementation Results 47
4.1 Color Detection by Gaussian Mixture Model Clustering . . . . . . . . . . . . 47
4.1.1 Parameter Setting . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47
4.1.2 Result of Gaussian Mixture Model Color Detection . . . . . . . . . . 49
4.1.3 Verification of Positive Correlation about Absorbance and Inflammation 50
4.1.4 Absorbance Threshold Determination . . . . . . . . . . . . . . . . . 52
4.2 Experimental Result of Individual Long-term Tracking Technique . . . . . . 54
4.3 Comparison between Other Methods on Peritonitis Screening . . . . . . . . 60
5 Conclusions and Future Works 63
5.1 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 63
5.2 Future Works . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 64

[1] Y.-C. Tyan, S.-B. Su, S.-S. Ting, H.-Y.Wang, and P.-C. Liao, “A comparative proteomics analysis of peritoneal dialysate before and after the occurrence of peritonitis episode by mass spectrometry,” Clinica Chimica Acta, vol. 420, pp. 34–44, 2013.
[2] N. Tangri, D. Ansell, and D. Naimark, “Predicting technique survival in peritoneal dialysis patients: comparing artificial neural networks and logistic regression,” Nephrology Dialysis Transplantation, vol. 23, no. 9, pp. 2972–2981, 2008.
[3] L. Li, M. Chen, H. Wang, W. Chen, and Z. Guo, “A cost sensitive ensemble method for medical prediction,” in 2009 First International Workshop on Database Technology and Applications, April 2009, pp. 221–224.
[4] S. S. Fenton, D. E. Schaubel, M. Desmeules, H. I. Morrison, Y. Mao, P. Copleston, J. R.
Jeffery, and C. M. Kjellstrand, “Hemodialysis versus Peritoneal dialysis: a comparison of adjusted mortality rates,” American Journal of Kidney Diseases, vol. 30, no. 3, pp.334–342, 1997.
[5] A. Sayin, R. Mutluay, and S. Sindel, “Quality of life in hemodialysis, peritoneal dialysis, and transplantation patients,” in Transplantation proceedings, vol. 39, no. 10. Elsevier, 2007, pp. 3047–3053.
[6] K. Griva, A. W. Kang, Z. L. Yu, V. Y. Lee, S.Zarogianis, M. C. Chan, and M. Foo, “Predicting technique and patient survival over 12 months in Peritoneal dialysis: the role of anxiety and depression,” International urology and nephrology, vol. 48, no. 5, pp.
791–796, 2016.
[7] W. M. Association et al., “World medical association declaration of helsinki: ethical principles for medical research involving human subjects.” Journal of postgraduate medicine, vol. 48, no. 3, p. 206, 2002.
[8] M. H. M. Baygi, P. A. Payne, and M. J. Henery, “Measurement of turbidity with polarized light,” Measurement Science and Technology, vol. 5, no. 6, p.685, 1994.[Online]. Available: http://stacks.iop.org/0957-0233/5/i=6/a=008
[9] M. L. Green, P. and M. H. Brill, “Colour engineering: Achieving device-independent colour,” Journal of the Society for Information Display, 2004.
[10] M. Shaw and M. Fairchild, “Evaluating the 1931 cie color-matching functions,” Color Research & Application, vol. 27, no. 5, pp. 316–329, 2002.
[11] G. Hong, M. R. Luo, and P. A. Rhodes, “A study of digital camera colorimetric characterisation based on polynomial modelling,” 2001.
[12] S. Westland and C. Ripamonti, Computational colour science using MATLAB. Chichester, West Sussex, England, Hoboken, NJ: J. Wiley, 2004, prsentation de l’ouvrage http://www.loc.gov/catdir/description/wiley041/2003021483.html. [Online].Available: http://opac.inria.fr/record=b1122104
[13] M. M. Baygi, P. Payne, and M. Henery, “Measurement of turbidity with polarized light,” Measurement Science and Technology, vol. 5, no. 6, p. 685, 1994.
[14] J. Refonaa, M. Lakshmi, and V. Vivek, “Analysis and prediction of natural disaster using
spatial data mining technique,” in Circuit, Power and Computing Technologies (ICCPCT),
2015 International Conference on, March 2015, pp. 1–6.
[15] S. Haykin and B. Kosko, Deterministic Annealing for Clustering, Compression, Classification, Regression, and Speech Recognition. Wiley-IEEE Press, 2001, pp. 163–229. [Online]. Available: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5265779
[16] R. Xu and D. Wunsch, Cluster Analysis. Wiley-IEEE Press, 2009, pp. 1–13. [Online].Available: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5237487
[17] X. Zhuang, Y. Huang, K. Palaniappan, and Y. Zhao, “Gaussian mixture density modeling, decomposition, and applications,” IEEE Transactions on Image Processing, vol. 5, no. 9, pp. 1293–1302, Sep 1996.
[18] D. Reynolds, “Gaussian mixture models,” Encyclopedia of biometrics, pp. 827–832,2015.
[19] M. Abramowitz and I. A. Stegun, Handbook of mathematical functions: with formulas, graphs, and mathematical tables. Courier Corporation, 1964, vol. 55.
[20] S.-C. Cheng, C.-S. Hu et al., “Dynamic image model established based on gaussian mixture model and shadow filter,” Ph.D. dissertation, 2004.
[21] G. McLachlan and D. Peel, Finite mixture models. John Wiley & Sons, 2004.
[22] D. Reynolds, “Gaussian mixture models.”
[23] A. P. Dempster, N. M. Laird, and D. B. Rubin, “Maximum likelihood from incomplete data via the em algorithm,” Journal of the royal statistical society. Series B (methodological),pp. 1–38, 1977.
[24] A. P. H. Association, A. W.W. Association et al., Standard methods for the examination of water and wastewater: selected analytical methods approved and cited by the United States Environmental Protection Agency. American Public Health Association, 1981.
[25] T. Lumley, “Kendall’s advanced theory of statistics. volume 2a: classical inference and the linear model. alan stuart, keith ord and steven arnold, arnold, london, 1998, no. of pages: xiv+ 885. price:£ 85.00. isbn 0-340-66230-1,” Statistics in Medicine, vol. 19, no. 22, pp. 3139–3140, 2000.
[26] D. J. Hand, H. Mannila, and P. Smyth, Data Analysis and Uncertainty. MIT Press, 2001, pp. 93–139. [Online]. Available: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?
arnumber=6282069
[27] H. H. Permuter, Y. H. Kim, and T. Weissman, “Interpretations of directed information
in portfolio theory, data compression, and hypothesis testing,” IEEE Transactions on
Information Theory, vol. 57, no. 6, pp. 3248–3259, June 2011.
[28] G. Keller and N. Gaciu, Managerial statistics. South-Western Cengage Learning, 2012.
[29] D. R. Anderson, K. P. Burnham, and W. L. Thompson, “Null hypothesis testing: problems, prevalence, and an alternative,” The journal of wildlife management, pp. 912–923, 2000.
[30] D. C. Montgomery, G. C. Runger, and N. F. Hubele, Engineering statistics. JohnWiley& Sons, 2009.
[31] R. Paternoster, R. Brame, P. Mazerolle, and A. Piquero, “Using the correct statistical test for the equality of regression coefficients,” Criminology, vol. 36, no. 4, pp. 859–866,1998.
[32] R. C. Sprinthall, Basic statistical analysis, 2011.
[33] D. L. Wilson, “Asymptotic properties of nearest neighbor rules using edited data,” IEEE Transactions on Systems, Man, and Cybernetics, no. 3, pp. 408–421, 1972.
[34] D. A. Freedman, Statistical models: theory and practice. cambridge university press,2009.
[35] R. Peck and J. L. Devore, Statistics: The exploration & analysis of data. Cengage Learning, 2011.
[36] D. J. Sheskin, Handbook of parametric and nonparametric statistical procedures. crc Press, 2003.
[37] N. F. Schneidewind, Forecasting Models. Wiley-IEEE Standards Association, 2009,pp. 405–414. [Online]. Available: http://ieeexplore.ieee.org/xpl/articleDetails.jsp?
arnumber=5769993
[38] D. Haynes, S. Corns, and G. K. Venayagamoorthy, “An exponential moving average algorithm,” in 2012 IEEE Congress on Evolutionary Computation, June 2012, pp. 1–8.
[39] M. H. Dunham, Data mining: Introductory and advanced topics. Pearson Education India, 2006.
[40] D. R. Helsel and T. A. Cohn, “Estimation of descriptive statistics for multiply censored water quality data,” Water Resources Research, vol. 24, no. 12, pp. 1997–2004, 1988.
[41] H. S. Chen, “A portable homecare system for Peritoneal dialysis patients,” Master’s thesis, National Tsing Hua University, 2015