在工業4.0時代，隨著資訊科技的蓬勃發展，大數據預測分析是不可或缺的技術。COVID-19的疫情影響全球，人們開始更加的重視醫療照護相關的問題。由於COVID-19的影響，造成人們捐血意願降低。而不同的血液產品有不同的保質期，有些保質期則相當短暫。因此，準確的預測未來的血液需求量，能夠令血液供應鏈上的短缺、浪費相對的減少，進而減少成本，提升效率。
本研究為供應鏈解析研究，其數據是來自血庫的血液相關數據。我們提供了一個分析架構，首先開發了一個ARIMA+XGBoost的混合模型，使用ARIMA時間序列模型分解季節性、趨勢和殘差，然後利用XGBoost模型找到殘差之間的非線性模式。此混合模型可以綜合ARIMA模型和XGBoost模型各自的優點。我們還將此混合模型與Holt-Winters方法、XGBoost模型和長短期記憶模型進行了比較。
本研究使用了RMSE來評估各個模型的優劣指標，結果顯示ARIMA+XGBoost模型在紅血球濃厚液、新鮮冷凍血漿和血小板的預測結果都與深度學習領域知名的長短期記憶模型相近，甚至更好。且在陽性的血液上也比陰性的血液預測結果還要好。本研究所提出的供應鏈解析架構可以提供血液銀行營運做較佳的血液需求預測決策。

In Industry 4.0 era, with the rapid development of information technology, big data
predictive analysis is an indispensable technology. The COVID-19 pandemic has ravaged the world, and people have begun to pay more attention to issues related to medical care. Due to the impact of the pandemic, people’s willingness to donate blood has decreased. Different blood products have different shelf lives, some of which are
quite short. Therefore, accurate predictions of future blood demand can relatively
reduce shortages and waste in the blood supply chain, thereby reducing costs and
improving efficiency.
Supply chain analytics were studied in this thesis by using blood-related datasets
from blood banks. We provide an analytics framework to begin with developing a hybrid model of ARIMA+XGBoost, which can use the ARIMA time series model to disassemble seasonality, trend and residuals, and then use the XGBoost model to find the
nonlinearity between residuals. The model can integrate the respective advantages of the ARIMA model and the XGBoost model. We also compare this hybrid model with Holt-Winters method, the XGBoost model, and the LSTM model.
We use RMSE as the model performance evaluation index. The experimental results show that the prediction results of the ARIMA+XGBoost model in red blood cells, fresh
frozen plasma and platelets are close to or even better than the well-known LSTM
model in the field of deep learning. It is also better on Rh positive blood than Rh negative blood. The proposed supply chain analytics framework can be used to better blood demand forecasting as decision-making for blood bank operations.

Attari, M. Y. N., Pasandideh, S. H. R., Aghaie, A. and Niaki, S. T. A. (2018). “A bi-objective robust optimization model for a blood collection and testing problem: an accelerated stochastic benders decomposition,” Annals of Operations Research. (DOI: 10.1007/s10479-018-3059-9)
Attari, M. Y. N., Laoues, S. and Chabane, S. (2019). “Characterization of an archaeological mortar from the ottoman period in Algeria,” International Journal of Materials, Mechanics and Manufacturing, 7(3), 154 – 157. (DOI: 10.18178/ijmmm.2019.7.3.450)
Anita, K. N., David, J. R. and Asoke, K. N. (2020). “Prediction paradigm involving time series applied to total blood issues data from England,” Transfusion, 60(3), 535 – 543. (DOI: 10.1111/trf.15705)
Andrade-Garda, J. M., Carlosena-Zubieta, A., Soto-Ferreiro, R. M., Teran-Baamonde, J. and Thompson, M. (2013). “Classical linear regression by the least squares method,” Basic Chemometric Techniques in Atomic Spectroscopy (RSC Analytical Spectroscopy Series), Chapter 2, 52 – 122. (DOI: 10.1039/9781849739344-00052)
Badr, H., Abdelkarim, M., Hanane, E and Mohammed, E. (2014). “A comparative study of decision tree ID3 and C4.5,” International Journal of Advanced Computer Science and Applications, 4(2). (DOI: 10.14569/SpecialIssue.2014.040203)
Blackburn, J. and Scudder, G. (2009). “Supply chain strategies for perishable products: the case of fresh produce,” Production and Operations Management, 18(2), 129 – 137. (DOI: 10.1111/j.1937-5956.2009.01016.x)
Breiman, L., Friedman, J. H., Gordon, A.D., Olshen, R. A. and Stone, C. J. (1984). “Classification and regression trees,” Biometrics, 40(3), 874. (DOI: 10.2307/2530946)
Breiman, L. (2001). “Random forests,” Machine Learning, 45(1), 5 – 32. (DOI: 10.1023/A:1010933404324)
Bryson, A. E. (1961). “A gradient method for optimizing multi-stage allocation processes,” Proceedings of the Harvard University Symposium on Digital Computers and Their Applications, 3-6. Cambridge: Harvard University Press. OCLC 498866871.
Bengio, Y., LeCun, Y. and Hinton, G. (2015). “Deep learning,” Nature, 521(7553), 436 – 444. (DOI: 10.1038/nature14539)
Chapman, J. F. Hyam, C. and Hick, R. (2004). “Blood inventory management,” Vox Sanguinis, 87(s2), 143 – 145. (DOI: 10.1111/j.1741-6892.2004.00472.x)
Cover, T. and Hart, P. (1967). “Nearest neighbor pattern classification,” IEEE Transactions on Information Theory, 13(1), 21 – 27. (DOI: 10.1109/TIT.1967.1053964)
Cherif, I. L. and Kortebi, A. (2019). “On using eXtreme gradient boosting (XGBoost) machine learning algorithm for home network traffic classification,” 2019 Wireless Days (WD), 1 – 6. (DOI: 10.1109/WD.2019.8734193)
Chopra, S., Hadsell, R. and LeCun, Y. (2005). “Learning a similarity metric discriminatively, with application to face verification,” 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), 1, 539 – 546. (DOI: 10.1109/CVPR.2005.202)
Chung, C. J. and Wee, H. M. (2007). “Optimizing the economic lot size of a three-stage supply chain with backordering derived without derivatives,” European Journal of Operational Research, 183(2), 933 – 943. (DOI: 10.1016/j.ejor.2006.10.019)
Chen, H., Chiang, R. and Storey, V. (2012). “Business intelligence and analytics: from big data to big impact,” MIS Quarterly, 36(4), 1165. (DOI: 10.2307/41703503)
Chen, T. and Guestrin, C. (2016). “XGBoost: a scalable tree boosting system,” Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785-794. (DOI:10.1145/2939672.2939785)
Domeniconi, C., Gunopulos, D. and Peng, J. (2005). “Large margin nearest neighbor classifiers,” IEEE Transactions on Neural Networks, 16(4), 899 – 909. (DOI: 10.1109/TNN.2005.849821)
Dillon, M., Oliveira, F. and Abbasi, B. (2017). “A two-stage stochastic programming model for inventory management in the blood supply chain,” International Journal of Production Economics, 187, 27 – 41. (DOI: 10.1016/j.ijpe.2017.02.006)
De'ath, G. and Fabricus, K. E. (2000). “Classification and regression trees: a powerful yet simple technique for ecological data analysis,” Ecology, 81(11), 3178 – 3192. (DOI: 10.1890/0012-9658(2000)081[3178:CARTAP]2.0.CO;2)
Elragal, A. (2014). “ERP and big data: the inept couple,” Procedia Technology, 16, 242 – 249. (DOI: 10.1016/j.protcy.2014.10.089)
Fadiya, S. O., Saydam. S. and Zira, V. V. (2014). “Advancing big data for humanitarian needs,” Procedia Engineering, 78, 88 – 95. (DOI: 10.1016/j.proeng.2014.07.043)
Faysal, J. A., Mostafa, S. T., Tamanna, J. S., Mumenin, K. M., Arifin, M. M., Awal, M. M., Shome, A. and Mostafa, S. S. (2022). “XGB-RF: a hybrid machine learning approach for IoT intrusion detection,” Telecom, 3(1), 52 – 69. (DOI: 10.3390/telecom3010003)
Ferguson, M. E. and Toktay, L. B. (2009). “The effect of competition on recovery strategies,” Production and Operations Management, 15(3), 351 – 368. (DOI: 10.1111/j.1937-5956.2006.tb00250.x)
Gantz, J. and Reinsel, D. (2011). “Extracting value from chaos,” IDC’s Digital Universe Study, sponsored by EMC, Issu.1142, 1-12. (Access March 1, 2022 from: http://www.kushima.org/wpcontent/uploads/2013/05/DigitalUniverse2011.pdf)
Gardner, Jr., E. S. (1979). “Box-Jenkins vs multiple regression: some adventures in forecasting the demand for blood tests,” Interfaces, 9(4), 49 – 54. (DOI: 10.1287/inte.9.4.49)
Gallego, G. and Moon, I. (1993). “ The distribution free newsboy problem: review and extensions,” The Journal of the Operational Research Society, 44(8), 825. (DOI: 10.2307/2583894)
Goyal, S. K. and Giri, B. C. (2001). “Recent trends in modeling of deteriorating inventory,” European Journal of Operational Research, 134(1), 1 – 16. (DOI: 10.1016/S0377-2217(00)00248-4)
Gunpinar, S. and Centeno, G. (2015). “Stochastic integer programming models for reducing wastages and shortages of blood products at hospitals,” Computers & Operations Research, 54, 129 – 141. (DOI: 10.1016/j.cor.2014.08.017)
Guan, L., Tian, X., Gombar, S., Zemek, A. J., Krishnan, G., Scott, R., Narasimhan, B., Tibshirani, R. J. and Pham, T. D. (2017). “Big data modeling to predict platelet usage and minimize wastage in a tertiary care system,” Proceedings of the National Academy of Sciences, 114(43), 11368 – 11373. (DOI: 10.1073/pnas.1714097114)
Hashem, I. A. T., Yaqoob, I., Anuar, N. B., Mokhtar, S., Gani, A. and Khan, S. U. (2015). “The rise of “big data” on cloud computing: review and open research issues,” Information Systems, 47, 98-115. (DOI: 10.1016/j.is.2014.07.006)
Harris, F. W. (1913). “How many parts to make at once,” Operations Research, 38(6), 947 – 950. (DOI: 10.1287/opre.38.6.947)
Haijema R., van der Wal, J. and van Dijk, N. M. (2007). “Blood platelet production: Optimization by dynamic programming and simulation,” Computers & Operations Research, 34(3), 760 – 779. (DOI: 10.1016/j.cor.2005.03.023)
Hochreiter, S. (1998). “The vanishing gradient problem during learning recurrent neural nets and problem solutions,” International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 06(02), 107 – 116. (DOI: 10.1142/S0218488598000094)
Hemmelmayr, V., Doerner, K. F., Hartl, R. F. and Savelsbergh, M. W. P. (2010). “Vendor managed inventory for environments with stochastic product usage,” European Journal of Operational Research, 202(3), 686 – 695. (DOI: 10.1016/j.ejor.2009.06.003)
Jiang, S., Xiao, R., Wang, L., Luo, X., Huang, C., Wang, J. H., Chin, K. S. and Nie, X. (2019). “Combining deep neural networks and classical time series regression models for forecasting patient flows in Hong Kong,” IEEE Access, 7, 118965 – 118974. (DOI: 10.1109/ACCESS.2019.2936550)
Kakulapati, V., Nalluri, P. S. and Kokkirala. (2021). “Xgboost analyses of classification of yoga,” SSRN Electronic Journal. (DOI: 10.2139/ssrn.3948127)
Kratzert, F., Klotz, D., Brenner, C., Schulz, K. and Herrnegger, M. (2018). “Rainfall–runoff modelling using long short-term memory (LSTM) networks,” Hydrology and Earth System Sciences, 22(11), 6005 – 6022. (DOI: 10.5194/hess-22-6005-2018)
Khandelwal, M., Kankar, P. and Harsha, S. (2010). “Evaluation and prediction of blast induced ground vibration using support vector machine,” Mining Science and Technology (China), 20(1), 64 – 70. (DOI: 10.1016/S1674-5264(09)60162-9)
Kwon, O., Lee, N. and Shin, B. (2014). “Data quality management, data usage experience and acquisition intention of big data analytics,” International Journal of Information Management, 34(3), 387 – 394. (DOI: 10.1016/j.ijinfomgt.2014.02.002)
Kumari, D. M. S. and Wijayanayake, A. N. (2016). “An efficient inventory model to reduce the wastage of blood in the national blood transfusion service,” 2016 Manufacturing & Industrial Engineering Symposium (MIES), 1 – 4. (DOI: 10.1109/MIES.2016.7779989)
Lindemann, B., Maschler, B., Sahlab, N. and Weyrich, M. (2021). “A survey on anomaly detection for technical systems using LSTM networks,” Computers in Industry, 131, 103498. (DOI: 10.1016/j.compind.2021.103498)
Lestari, F. and Anwar, U. (2017). “Forecasting demand in blood supply chain (case study on blood transfusion unit),” (Access April 10, 2022 from: https://pdfs.semanticscholar.org/d58c/7399dcd56742b3ab6d540109c2cef0ed8137.pdf.)
Li, N., Chiang, F. Down, D. G. and Heddle, N. M. (2021). “A decision integration strategy for short-term demand forecasting and ordering for red blood cell components,” Operations Research for Health Care, 29, 100290. (DOI: 10.1016/j.orhc.2021.100290)
López, V., del Río, S., Benítez, J. M. and Herrera, F. (2015). “Cost-sensitive linguistic fuzzy rule-based classification systems under the MapReduce framework for imbalanced big data,” Fuzzy Sets and Systems, 258, 5 – 38. (DOI: 10.1016/j.fss.2014.01.015)
Lang, J. C., (2010). “Blood bank inventory control with transshipments and substitutions,” Production and Inventory Management with Substitutions (Lecture Notes in Economics and Mathematical Systems), 636, 205 – 226. (DOI: 10.1007/978-3-642-04247-8_8)
Liu, L. and Cheung, K. L. (1997). “Service constrained inventory models with random lifetimes and lead times,” The Journal of the Operational Research Society, 48(10), 1022. (DOI: 10.2307/3010122)
Liu, L. and Lian, Z. (1999). “ (s, S) Continuous review models for products with fixed lifetimes,” Operations Research, 47(1), 150 – 158. (DOI: 10.1287/opre.47.1.150)
Liu, L. and Shi, D. H. (1999). “An (s, S) model for inventory with exponential lifetimes and renewal demands,” Naval Research Logistics, 46(1), 39 – 56. (DOI: 10.1002/(SICI)1520-6750(199902)46:1<39::AID-NAV3>3.0.CO;2-G)
Laney, D. (2001). “3-D data management: controlling data volume, velocity, and variety,” File: 949 Addendum, META Group. (Access March 1, 2022 from: https://blogs.gartner.com/doug-laney/files/2012/01/ad949-3D-Data-Management-Controlling-Data-Volume-Velocity-and-Variety.pdf)
McCulloch, W. S. and Pitts, W. (1943). “A logical calculus of the ideas immanent in nervous activity,” The Bulletin of Mathematical Biophysics, 5(4), 115 – 133. (DOI: 10.1007/BF02478259)
Minsky, M. and Papert, S. A. (1969). Perceptrons, MIT Press. (Access March 3, 2022 from: https://psycnet.apa.org/record/1969-35017-000)
MIT Technology Review, (2013). “Ten breakthrough technologies 2013,” (Access March 20, 2022 from: https://www.technologyreview.com/10-breakthrough- technologies/2013/)
Montgomery, D. C., Peck, E. A. and Vining, G. G. (2012). Introduction to Linear Regression Analysis, 5th edition, John Wiley & Sons, New Your, NY, U.S.A.
Mansur, A., Vanany, I., Arvitrida, N. I., Ma’mun, S., Tamura, H. and Purnomo, M. R. A. (2018). “Challenge and opportunity research in blood supply chain management: a literature review,” The 2nd International Conference on Engineering and Technology for Sustainable Development, 154, 01092. (DOI: 10.1051/matecconf/201815401092)
Maatallah, O. A., Achuthan, A., Janoyan, K. and Marzocca, P. (2015). “Recursive wind speed forecasting based on Hammerstein auto-regressive model,” Applied Energy, 145, 191 – 197. (DOI: 10.1016/j.apenergy.2015.02.032)
Nandakumar, P. and Morton, T. E. (1993). “Near myopic heuristics for the fixed-life perishability problem,” Management Science, 39(12), 1490 – 1498. (DOI: 10.1287/mnsc.39.12.1490)
Nemtajela, N. and Mbohwa, C. (2017). “Relationship between inventory management and uncertain demand for fast moving consumer goods organizations,” Procedia Manufacturing, 8, 699 – 706. (DOI: 10.1016/j.promfg.2017.02.090)
Osorio, A. F., Brailsford, S. C. and Smith, H. K. (2018). “Whole blood or apheresis donations? a multi-objective stochastic optimization approach,” European Journal of Operational Research, 266(1), 193 – 204. (DOI: 10.1016/j.ejor.2017.09.005)
Oscar, S. S. F., Cezarino, W. and Salviano, G. R. (2012). “A decision-making tool for demand forecasting of blood components,” IFAC Proceedings, 45(6), 1499 – 1504. (DOI: 10.3182/20120523-3-RO-2023.00201)
Oscar, S. S. F., Silva, R., Carvalho, M. A., Cezarino, W., Silva, R. and Salviano, G. (2013). “Demand forecasting for blood components distribution of a blood supply chain,” IFAC Proceedings, 46(24), 565 – 571. (DOI: 10.3182/20130911-3-BR- 3021.00092)
Pereira, A. (2004). “Performance of time-series methods in forecasting the demand for red blood cell transfusion,” Transfusion, 44(5), 739 – 746. (DOI: 10.1111/j.1537- 2995.2004.03363.x)
Pandey, K. K. and Shukla, D. (2018). “Challenges of big data to big data mining with their processing framework,” 2018 8th International Conference on Communication Systems and Network Technologies, 89-94. (DOI: 10.1109/CSNT.2018.8820282)
Rahman, M. M., Usman, O. L., Muniyandi, R. C., Sahran, S., Mohamed, S. and Razak, R. A. (2020). “A review of machine learning methods of feature selection and classification for autism spectrum disorder,” Brain Sciences, 10(12), 949. (DOI: 10.3390/brainsci10120949)
Rosenblatt, F. and White, B. W. (1963). “Principles of neurodynamics: perceptrons and the theory of brain mechanisms,” The American Journal of Psychology, 76(4), 705. (DOI: 10.2307/1419730)
Rumelhart, D. E., Hinton, G. E. and Williams, R. J. (1986). “Learning representations by back-propagating errors,” Nature, 323(6088), 533 – 536. (DOI: 10.1038/323533a0)
Sarhangian, V., Abouee-Mehrizi, H., Baron, O. and Berman, O. (2018). “Threshold-based allocation policies for inventory management of red blood cells,” Manufacturing & Service Operations Management, 20(2), 347 – 362. (DOI: 10.1287/msom.2017.0650)
Stevenson, W. J. (2005). Operations Management, 8th international edition, McGraw-Hill/Irwin, Boston.
Sirelson, V. and Brodheim, E. (1991). “A computer planning model for blood platelet production and distribution,” Computer Methods and Programs in Biomedicine, 35(4), 279 – 291. (DOI: 10.1016/0169-2607(91)90006-F)
Sak, H., Senior, A. and Beaufays, F. (2014). “Long short-term memory recurrent neural network architectures for large scale acoustic modeling,” Proceedings Interspeech 2014, 338 – 342. (DOI: 10.21437/Interspeech.2014-80)
Trinh, H. D., Giupponi, L. and Dini, P. (2018). “Mobile traffic prediction from raw data using LSTM networks,” 2018 IEEE 29th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), 1827 – 1832. (DOI: 10.1109/PIMRC.2018.8581000)
Taft, E. W. (1918). “The most economical production lot,” The Iron Age, 101, pp. 1410-1412.
Teng, J. T., Cárdenas-Barrón, L. E. and Lou, K. R. (2011). “The economic lot size of the integrated vendor-buyer inventory system derived without derivatives: a simple derivation,” Applied Mathematics and Computation, 217(12), 5972 – 5977. (DOI: 10.1016/j.amc.2010.12.018)
van Zyl, G. J. J. (1964). “Inventory control for perishable commodities,” unpublished Ph.D. dissertation. University of North Carolina.
Valenzuela, O., Rojas, I., Rojas, F., Pomares, H., Herrera, L. J., Guillen, A., Marquez, L. and Pasadas, M. (2008). “Hybridization of intelligent techniques and ARIMA models for time series prediction,” Fuzzy Sets and Systems, 159(7), 821 – 845. (DOI: 10.1016/j.fss.2007.11.003)
Wang, C., Deng, C. and Wang, S. (2020). “Imbalance-XGBoost: leveraging weighted and focal losses for binary label-imbalanced classification with XGBoost,” Pattern Recognition Letters, 136, 190 – 197. (DOI: 10.1016/j.patrec.2020.05.035)
Weatherford, L. and Pfeifer, P. (1994). “The economic value of using advance booking of orders,” Omega, 22(1), 105 – 111. (DOI: 10.1016/0305-0483(94)90011-6)
Wu, Z. Y., El-Maghraby, M. and Pathak, S. (2015). “Applications of deep learning for smart water networks,” Procedia Engineering, 119, 479 – 485. (DOI: 10.1016/j.proeng.2015.08.870)
Yang, C., Zhang, X., Zhong, C., Liu, C., Pei, J., Ramamohanarao, K. and Chen, J. (2014). “A spatiotemporal compression based approach for efficient big data processing on Cloud,” Journal of Computer and System Sciences, 80(8), 1563 – 1583. (DOI: 10.1016/j.jcss.2014.04.022)
Zhou, D., Leung, L. C. and Pierskalla, W. P. (2011). “Inventory management of platelets in hospitals: optimal inventory policy for perishable products with regular and optional expedited replenishments,” Manufacturing & Service Operations Management, 13(4), 420 – 438. (DOI: 10.1287/msom.1110.0334)
Zahiri, B. and Pishvaee, M. S. (2017). “Blood supply chain network design considering blood group compatibility under uncertainty,” International Journal of Production Research, 55(7), 2013 – 2033. (DOI: 10.1080/00207543.2016.1262563)