快速測試程序（Rapid Testing Procedures,RTP）主要用於檢測病毒性肺炎，它是控制和減少病毒性疾病傳播的有效策略。在快速檢測試劑盒中，通常包括血液注射通道，並配有顏色指示器以顯示陽性或陰性結果，通常使用人眼進行結果判別。此次實驗，我們使用光譜儀（微型光譜儀）來獲取快速篩檢試劑盒的顏色指示器的反射光譜，並通過光譜進行陽性與陰性的結果判別，由於陽性和陰性結果的光譜數據具有很強的相關性，因此很難使用常規統計方法進行分類。 因此在本文工作中配置了各種機器學習分類器來獲得最佳分類結果。
在反射光譜數據上測試了邏輯迴歸演算法，K-近鄰演算法，支持向量機、單純貝氏分類器和決策樹學習等演算法。此外，根據準確率和計算需求進行超參數微調，實驗中考慮了反射率和吸收率兩種性能指標，發現決策樹學習演算法的性能最好，準確率達 98%。
除了對反射光譜進行陽性及陰性的分類，本研究也聚焦在陽性病例的抗體濃度預測，這是評估疾病嚴重程度的關鍵指標。濃度估算是基於統計學方法對陽性案例進行高低臨界值分類。總體而言，發現了人工智慧的方法可以實現性能良好的光譜快速分類。
關鍵字：快速檢測，機器學習，光譜晶片，反射光譜
 

Rapid Testing Procedures (RTP) are majorly used in the diagnosis of viral pneumonia and found to be an effective strategy to control and reduce the spread of the viral diseases. The rapid test kits generally comprise of input channel to feed the human blood channel and provided with either direct indicator to show positive or negative cases. The human eye is usually used to determine the result. In this experiment, we used a spectrometer (micro-spectrometer) to obtain the reflectance spectrum of the color indicator of the rapid screening kit. As the spectral data for the positive and negative cases have strong correlation, it is difficult to classify using the conventional statistical approaches. Hence, in this thesis work, various Machine Learning (ML) classifiers are deployed to obtain the best classification results.
The prominent ML classifiers such as Logisitic regression, K-nearest neighbours, Support vector machines, Naive baiyes classifiers and decision tree classifiers were tested on the spectral data obtained from the spectrochip rapid kit. Further, the hyper parameters are fine tuned based on accuracy and computational demand. Two types of performance indices are considered such as reflectance and absorbance, and the decision tree algorithm is found to be best performer with an accuracy of 98%.
Apart from positive and negative classification, the study also focus on the concentration prediction for the positive cases which is an critical indicator to estimate the seriousness of the disease. The concentration estimation is performed based on the statiscal approach to classify positive cases as high and low critical states. In overall, the artificial intelligence based solution is found to achieve a superior performance for spectral based rapid testing.
Keywords: Rapid test, Machine learning, Spectrochip, Reflectance spectrum

[1] X. Wang, Y. Peng, L. Lu, Z. Lu, M. Bagheri, and R. M. Summers, “ChestX-ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases,” Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 2097–2106.
[2] P. Rajpurkar et al., “CheXNet: Radiologist-level pneumonia detection on chest X-Rays with deep learning,” 2017, pp. 214–216.
[3] H. Wang, H. Jia, L. Lu, and Y. Xia, “Thorax-net: An attention regularized deep neural network for classification of thoracic diseases on chest radiography,” IEEE J. Biomed. Health Informat., vol. 24, no. 2, pp. 475–485, Feb. 2020.
[4] D. S. Kermany et al., “Identifying medical diagnoses and treatable diseases by image-based deep learning,” Cell, vol. 172, no. 5, pp. 1122–1131, 2018.
[5] N. Lavrac, I. Kononenko, E. Keravnou, M. Kukar, and B. Zupan, “Intelligent data analysis for medical diagnosis: using machine learning and temporal abstraction,” AI Commun., vol. 11, no. 3, pp. 191–218, 1998.
[6] I. Use, “Instructions for use content : instructions for use,” Microbiologics, no. October, pp. 1–7, 2017.
[7] R. Zemouri, N. Zerhouni, and D. Racoceanu, “Deep learning in the biomedical applications: recent and future status,” Appl. Sci., vol. 9, no. 8, pp. 1–40, 2019.
[8] B. BenNouma, A. Mitiche, and N. Mezghani, “A sample-encoding generalization of the kohonen associative memory and application to knee kinematic data representation and pathology classification,” Appl. Sci., vol. 9, . no. 9, pp.852-853, 2019.
[9] C. BinJin et al., “DC2 anet: generating lumbar spine MR images from ct scan data based on semi-supervised learning,” Appl. Sci., vol. 9, no. 12, pp, 2019.
[10] A. Czmil, S. Czmil, and D. Mazur, “A method to detect type 1 diabetes based on physical activity measurements using a mobile device,” Appl. Sci., vol. 9, no. 12, pp. 1–16, 2019.
[11] S. B. Kotsiantis, I. D. Zaharakis, and P. E. Pintelas, “Machine learning: a review of classification and combining techniques,” Artif. Intell. Rev., vol. 26, no. 3, pp. 159–190, 2006.
[12] P. Langley, “Crafting papers on machine learning,” Mach. Learn. - Int. Work. 2000, pp 6, 2000.
[13] S. Bhatt, F. Patwa, and R. Sandhu, “An access control framework for cloud-enabled wearable internet of things,” Proc. - 2017 IEEE 3rd Int. Conf. Collab. Internet Comput. CIC 2017, vol. 2017-January, pp. 328–338, 2017.
[14] P. Wlodarczak, Machine learning and its applications. 2019. pp. 78-82.
[15] J. Qiu, Q. Wu, G. Ding, Y. Xu, and S. Feng, “A survey of machine learning for big data processing,” EURASIP J. Adv. Signal Process., vol. 2016, pp, 2016.
[16] S. L. Oh, J. Vicnesh, E. J. Ciaccio, R. Yuvaraj, and U. R. Acharya, “Deep convolutional neural network model for automated diagnosis of schizophrenia using EEG signals,” Appl. Sci., vol. 9, no. 14, p.p 2870, 2019.
[17] M. Kim et al., “Medinoid: computer-aided diagnosis and localization of glaucoma using deep learning,” Appl. Sci., vol. 9, pp. 578-580, 2019.
[18] S. Dankwa and W. Zheng, “Special issue on using machine learning algorithms in the prediction of kyphosis disease: a comparative study,” Appl. Sci., vol. 9, pp. 814–816, 2019.
[19] G. Gonella, E. Binaghi, P. Nocera, and C. Mordacchini, “Investigating the behaviour of machine learning techniques to segment brain metastases in radiation therapy planning,” Appl. Sci., vol. 9, pp. 1122-1125, 2019.
[20] F. Divina and F. Gómez-Vela, “Special issue on machine learning for biomedical data analysis,” Appl. Sci., vol. 9, no. 21, pp. 1–2, 2019.
[21] Y. Zhang et al., “Rapid deployment of a mobile biosafety level-3 laboratory in sierra leone during the 2014 ebola virus epidemic,” PLoS Negl. Trop. Dis., vol. 11, no. 5, pp. 1–15, 2017.
[22] S. Rajaraman, S. Candemir, I. Kim, G. Thoma, and S. Antani, “Visualization and interpretation of convolutional neural network predictions in detecting pneumonia in pediatric chest radiographs,” Appl. Sci., vol. 8, no. 10, pp. 1715, Sep. 2018.
[23] C. Bellinger, S. Sharma, and N. Japkowicz, “One-class versus binary classification in Proc. 11th Int. Conf. Mach. Learn. Appl. (ICMLA), vol. 2, Dec. 2012, pp. 102–106.
[24] C. Zhou and R. C. Paffenroth, “Anomaly detection with robust deep autoencoders,” in Proc. 23rd ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, Aug. 2017, pp. 665–674.
[25] G. Pang, L. Cao, L. Chen, and H. Liu, “Learning representations of ultrahigh-dimensional data for random distance-based outlier detection,” in Proc. 24th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, Jul. 2018, pp. 2041–2050.
[26] G. Pang, C. Shen, and A. van den Hengel, “Deep anomaly detection with deviation networks,” in Proc. 25th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, Jul. 2019, pp. 353–362.
[27] K. Santosh, "AI-driven tools for virus outbreak: need of active learning and cross-population train/test models on multitudinal/multimodal data," journal of medical systems, vol. 44, pp. 1-5, 2020.
[28] J. Gutierrez-Caceres, C. Portugal-Zambrano, and C. Beltrán-Castanon, “Computer aided medical diagnosis tool to detect normal/abnormal studies in digital MR brain images,” Proc. - IEEE Symp. Comput. Med. Syst., pp. 501–502, 2014.
[29] H. Magree et al., “Chest X-ray-confirmed pneumonia in children in Fiji,” Bull. World Health Org., vol. 83, pp. 427–433, Mar. 2005.
[30] J. P. Cohen et al., “Predicting pneumonia severity on chest x-ray with deep learning,” arXiv, vol. 12, no. 7, pp. 24–26, 2020.
[31] M. Yordanova, Y. Evstatieva, G. Chernev, S. Ilieva, R. Denkova, and D. Nikolova, “Enhancement of xylanase production by sol-gel immobilization of aspergillus awamori K-1,” Bulg. J. Agric. Sci., vol. 19, no. SUPPL. 2, pp. 117–119, 2013.
[32] D. Tao, J. Cheng, X. Gao, X. Li, and C. Deng, “Robust sparse coding for mobile image labeling on the cloud,” IEEE Trans. Circuits Syst. Video Technol., vol. 27, no. 1, pp. 62–72, 2017.
[33] C.-H. Ko, C. HONG, and W.-H. Chiu, “MEMS based spectrochip for healthcare, food safety and blockchain applications,” vol. 1098303, no. May 2019, pp. 3, 2019.
[34] “A preliminary research report redmond, R . shamshiri graduate student university of florida 1- spectroscopy,” pp. 1–13, 2007.
[35] https://www.semicontaiwan.org/en/prof-cheng-hao-ko.
[36] http://spectrochips.com/blog/aboutus.html.
[37] C. Y. J. Peng, K. L. Lee, and G. M. Ingersoll, “An introduction to logistic regression analysis and reporting,” J. Educ. Res., vol. 96, no. 1, pp. 3–14, 2002.
[38] E. Y. Boateng and D. A. Abaye, “A review of the logistic regression model with emphasis on medical research,” J. Data Anal. Inf. Process., vol. 07, no. 04, pp. 190–207, 2019.
[39] M. Maalouf, “Logistic regression in data analysis: an overview,” Int. J. Data Anal. Tech. Strategy., vol. 3, no. 3, pp. 281–299, 2011.
[40] O. Ronneberger, P. Fischer, and T. Brox, “U-net: convolutional networks for biomedical image segmentation,” Lect. Notes Comput. Sci. vol. 9351, pp. 234–241, 2015.
[41] A. N. Ramesh, C. Kambhampati, J. R. T. Monson, and P. J. Drew, “Artificial intelligence in medicine,” Ann. R. Coll. Surg. Engl., vol. 86, no. 5, pp. 334–338, 2004.
[42] Y. Qin, S. Zhang, X. Zhu, J. Zhang, and C. Zhang, “Semi-parametric optimization for missing data imputation,” Appl. Intell., vol. 27, no. 1, pp. 79–88, 2007.
[43] D. Peteiro-Barral and B. Guijarro-Berdiñas, “A survey of methods for distributed machine learning,” Prog. Artif. Intell., vol. 2, no. 1, pp. 1–11, 2013.
[44] H. Hormozi, E. Hormozi, and H. R. Nohooji, “The classification of the applicable machine learning methods in robot manipulators,” Int. J. Mach. Learn. Comput., vol. 2, no. 5, pp. 560–563, 2012.
[45] N. Karankar, P. Shukla, and N. Agrawal, “Comparative study of various machine learning classifiers on medical data,” Proc. - 7th Int. Conf. Commun. Syst. Netw. Technol. CSNT 2017, pp. 267–271, 2018.
[46] S. Bozkurt, A. Uyar, and K. H. Gulkesen, “Comparison of bayesian network and binary logistic regression methods for prediction of prostate cancer,” Proc. - 2011 4th Int. Conf. Biomed. Eng. Informatics, BMEI 2011, vol. 3, pp. 1689–1691, 2011.
[47] G. Guo, H. Wang, D. Bell, Y. Bi, and K. Greer, “KNN model-based approach in classification,” Lect. Notes Comput. Sci.vol. 2888, pp. 986–996, 2003.
[48] L. Wang, “Research and implementation of machine learning classifier based on knn,” IOP Conf. Ser. Mater. Sci. Eng., vol. 677, no. 5, pp. 214–216, 2019.
[50] R. McCuen, “Book reviews:,” JAWRA J. Am. Water Resour. Assoc., vol. 47, no. 3, pp. 650–653, 2011.
[51] S. Zhang, X. Li, M. Zong, X. Zhu, and R. Wang, “Efficient knn classification with different numbers of nearest neighbours,” IEEE Trans. Neural Networks Learn. Syst., vol. 29, no. 5, pp. 1774–1785, 2018.
[52] B. A. Thakkar, M. I. Hasan, and M. A. Desai, “Health care decision support system for swine flu prediction using naïve bayes classifier,” Proc. - 2nd Int. Conf. Adv. Recent Technol. Commun. Comput. ARTCom 2010, pp. 101–105, 2010.
[53] Y. Tian, Y. Shi, andX. Liu, “Recent advances on support vector machines research,” Technol. Econ. Dev. Econ., vol. 18, no. 1, pp. 5–33, 2012.
[54] M. A. M. Hasan, M. Nasser, B. Pal, and S. Ahmad, “Support vector machine and random forest modeling for intrusion detection system (IDS),” J. Intell. Learn. Syst. Appl., vol. 06, no. 01, pp. 45–52, 2014.
[55] T. Evgeniou and M. Pontil, “Support vector machines: theory and applications,” Lect. Notes Comput. Sci, vol. 2049 LNAI, no. May, pp. 249–257, 2001.
[56] I. Rish, “An empirical study of the naive bayes classifier an empirical study of the naive bayes classifier,” no. January 2001, pp. 41–46, 2014.
[57] H. T. Zaw, N. Maneerat, and K. Y. Win, “Brain tumor detection based on naive bayes classification,” Proceeding - 5th Int. Conf. Eng. Appl. Sci. Technol. ICEAST 2019, pp. 512–520, 2019.
[58] P. Kaviani and S. Dhotre, “Short survey on naive bayes algorithm,” Int. J. Adv. Eng. Res. Dev., vol. 4, no. 11, pp. 607–611, 2017.
[59] H. Bohra, A. Arora, P. Gaikwad, R. Bhand, and M. R. Patil, “Health prediction and medical diagnosis using naive bayes,” Ijarcce, vol. 6, no. 4, pp. 32–35, 2017.
[60] T. Evgeniou, M. Pontil, and T. Poggio, “Regularization networks and support vector machines,” Adv. Comput. Math., vol. 13, no. 1, pp. 1–50, 2000.
[61] H. Sharma and S. Kumar, “A survey on decision tree algorithms of classification in data mining,” Int. J. Sci. Res., vol. 5, no. 4, pp. 2094–2097, 2016.
[62] H. H. Patel and P. Prajapati, “Study and analysis of decision tree based classification algorithms,” Int. J. Comput. Sci. Eng., vol. 6, no. 10, pp. 74–78, 2018.