Hybrid ANFIS-Taguchi Method Based on PCA for Blood Bank Demand Forecasting

Yıl 2020, , 225 - 233, 31.07.2020

Seda Hatice Gökler , Semra Boran

https://doi.org/10.17671/gazibtd.580530

Cited By: 2

Öz

Blood is a vital product that is needed by thousands of people every day due to diseases, surgeries or injuries. For this reason, it is necessary that the blood banks have enough blood quantity to meet the blood needs of hospitals . The provision of small amounts of blood in hospitals creates significant problems such as loss of life and can’t meet the demand. On the other hand, the stocking of large amounts of blood leads to the wastage of blood and the stockless of blood different hospitals.
The aim of this study is to determine the criteria affecting blood demand and to forecast the blood demand by the machine learning algorithm Adaptive Network Based Fuzzy Inference System (ANFIS) method. However, since the number of impact criteria is high, principal component analysis (PCA) method has been used in order to decrease criteria and eliminate the dependencies between the criteria. In addition, the performance of ANFIS depend on determining ANFIS parameters that affect its structure and learning. So to provide the highest learning ANFIS parameters were determined by the Taguchi experimental design method. The developed hybrid method was applied in a regional blood center and evaluated with correlation coefficient (𝑅). At the end of the application, it is seen that the estimated red blood cells demand is similar to the demand amount realized at the rate of 88.1%.

Anahtar Kelimeler

ANFIS, PCA, taguchi method, demand forecasting

PCA Esaslı Hibrit ANFIS-Taguchi Yöntemi ile Kan Bankası için Talep Tahmini

Öz

Kan; hastalıklar, ameliyatlar veya yaralanmalar nedeniyle her gün binlerce insan tarafından ihtiyaç duyulan hayati bir üründür. Bu nedenle hastanelerin kan ihtiyacını karşılayan kan bankalarının stoklarında yeterli miktarda kan bulundurması gereklidir. Gereğinden az miktarda kan elde bulundurulması ihtiyacın karşılanamaması ve can kaybı gibi önemli sorunlar oluştururken, fazla miktarda kanın stoklanması ise kanın bozulmasına ve kan ihtiyacı olan farklı hastanelerin stoksuz kalmasına neden olmaktadır.
Bu çalışmada öncelikle kan bileşenlerinden biri olan eritrosit süspansiyonu talebine etki eden kriterler belirlenerek; bu kriterlere göre makine öğrenme algoritmalarından uyarlamalı ağ tabanlı bulanık çıkarım sistemi (ANFIS) yöntemi ile talebin tahmin edilmesi amaçlanmaktadır. Ancak talebe etki eden çok sayıda kriter olduğu için gruplandırarak azaltmak ve kriterler arasındaki bağımlılıkları ortadan kaldırmak amacıyla temel bileşen analizi (PCA) yönteminden yararlanılmıştır. Ayrıca ANFIS’in performansı; modelin yapısı ve öğrenmesini etkileyen parametre değerlerinin doğru belirlenmesi ile ilişkili olduğundan en yüksek doğrulukla tahmini sağlayacak değerler Taguchi deney tasarımı yöntemiyle belirlenmiştir. Geliştirilen PCA esaslı hibrit ANFIS-Taguchi yöntemi bir bölge kan merkezinde uygulanmıştır. Korelasyon katsayısı (𝑅) performans ölçütü ile yöntemin tahmin yeteneği değerlendirilmiştir. Uygulama sonunda tahmin edilen eritrosit süspansiyon talep miktarının %88.1 oranla gerçekleşen talep miktarı ile benzer sonuç verdiği görülmüştür. 

Anahtar Kelimeler

ANFIS, PCA, Taguchi metodu, talep tahmini

Kaynakça

• T. Akita, J. Tanaka, M. Ohisa, A. Sugiyama, K. Nishida, S. Inoue, T. Shirasaka, “Predicting future blood supply and demand in Japan with a Markov model: application to the sex- and age-specific probability of blood donation”, Transfusion, 56(11), 2750-2759, 2016.
• E.H.Y. Lau, X.Q. He, C.K. Lee, J T. Wu, “Predicting future blood demand from thalassemia major patients in Hong Kong”, PLoS ONE, 8(12), e81846, 2013.
• C.J. Currie , T.C. Patel , P. McEwan , S. Dixon, “Evaluation of the future supply and demand for blood products in the United Kingdom National Health Service”, Transfus Med, 14(1), 19-24, 2004.
• D.M.S. Kumari, A. N. Wijayanayake, “An efficient inventory model to reduce the wastage of blood in the national blood transfusion service” 2016 Manufacturing & Industrial Engineering Symposium (MIES), Colombo, 1-4, 2016.
• A. Wijayanayake, M. Dandunna, “An efficient model to improve the performance of platelet inventory of the blood banks”, Adv Sci Technol Eng Syst J, 2(3), 839-844, 2017.
• A. Drackley , K.B. Newbold , A. Paez , N. Heddle, “Forecasting Ontario's blood supply and demand”, Transfusion, 52(2), 366-374, 2012.
• A. Pereira, “Performance of time-series methods in forecasting the demand for red blood cell transfusion”, Transfusion, 44(5), 739-746, 2004.
• F,Firouzi Jahantigh, B. Fanoodi, S. Khosravi, “A demand forcasting model for the blood platelet supply chain with Artificial Neural Network approach and ARIMA models”, Sci J Iran Blood Transfus Organ, 14(4), 335-345, 2018.
• S. Walczak, J.E. Scharf, “Reducing surgical patient costs through use of an artificial neural network to predict transfusion requirements”, Decis Support Syst, 30(2), 125–138, 2000.
• W.H. Ho, C.S. Chang, “Genetic-algorithm-based artificial neural network modeling for platelet transfusion requirements on acute myeloblastic leukemia patients”, Expert Syst Appl, 38(5), 6319-6323, 2011.
• S. Haghani, Sedehi M, Kheiri S, “Artificial neural network to modeling zero-inflated count data: application to predicting number of return to blood donation”, J Res Health Sci, 17(3), e00392, 2017.
• H. Shih, S. Rajendran, “Comparison of Time Series Methods and Machine Learning Algorithms for Forecasting Taiwan Blood Services Foundation’s Blood Supply”, J Healthc Eng, 2019, Article ID 6123745, 2019.
• S. Barak, J.H. Dahooie, T. Tichý, “Wrapper ANFIS-ICA method to do stock market timing and feature selection on the basis of Japanese Candlestick”, Expert Syst Appl, 42(23), 9221–9235, 2015.
• A. Dariane, S. Azimi, “Forecasting streamflow by combination of genetic input selection algorithm and wavelet transforms using ANFIS model”, Hydrol Sci J, 61(3), 585–600, 2016.
• A. K. Sangaiah, A. K. Thangavelu, X. Z. Gao, N. Anbazhagan, M. S. Durai, “An ANFIS approach for evaluation of team-level service climate in GSD projects using Taguchi-genetic learning algorithm”, Appl Soft Comput, 30, 628–635, 2015.
• A. Sarkheyli, A. MohdZain, S. Sharif, “Robust optimization of ANFIS based on a new modified GA”, Neurocomputing, 166, 357-366, 2015.
• R. Bro, A.K. Smilde, “Principal component analysis”, Anal Methods, 6(9), 2812–2831, 2014.
• J.A.M. Bispo, E. E. de Sousa Vieira, L. Silveira, A.B. Fernandes, “Correlating the amount of urea, creatinine, and glucose in urine from patients with diabetes mellitus and hypertension with the risk of developing renal lesions by means of Raman spectroscopy and principal component analysis”, J Biomed Opt, 18(8), 2013.
• T. Ş. Yapraklı, H. Erdal, “Firma Başarısızlığı Tahminlemesi: Makine Öğrenmesine Dayalı Bir Uygulama”, Bilişim Teknolojileri Dergisi, 9(1), 21-31, 2016.
• O.A. Oral, Ö.Ö. Tanrıöver, M. Soubra, “Modeling and Predicting Scientific Thinking Skills of University Students Using a Data Mining Tool”, Bilişim Teknolojileri Dergisi, 10(1), 89-95, 2017.
• D.H. Vu, K.M. Muttaqi, A.P. Agalgaonkar, “A variance inflation factor and backward elimination based robust regression model for forecasting monthly electricity demand using climatic variables”, Appl Energy, 140, 385–394, 2015.
• A. C. Hadjichambis, D. Paraskeva-Hadjichambi, “Environmental Citizenship Questionnaire (ECQ): The Development and Validation of an Evaluation Instrument for Secondary School Students”, Sustainability, 12(3), 821-833, 2020.
• D. Wang, L. Shi, “Source identification of mine water inrush: a discussion on the application of hydrochemical method”, Arab J Geosci, 12(58), 2019.
• J. Jang, “ANFIS: adaptive-network-based fuzzy inference system”, Ieee Trans Syst Man Cybern Syst, 23(3), 665-685, 1993.
• M. Şahin, R. Erol, “A comparative study of neural networks and ANFIS for forecasting attendance rate of soccer games”, Math Comput Appl, 22(43), 12, 2017.
• P.J.Ross, Taguchi for Quality Engineering, Mc Graw Hill, second Edution, Newyork, ABD 1996.
• M. Milovančević, V. Nikolić, B. Anđelković, “Analyses of the most influential factors for vibration monitoring of planetary power transmissions in pellet mills by adaptive neuro-fuzzy technique”, Mech Syst Signal Pr, 82, 356-375, 2017.
• F. Mekanik, M. A. Imteaz, A. Talei, “Seasonal rainfall forecasting by adaptive network based fuzzy inference system (ANFIS) using large scale climate signals”, Clim Dyn, 46, 3097–3111, 2016.
• Ö. Çokluk, G. Şekercioğlu, Ş. Büyüköztürk, Sosyal Bilimler İçin Çok Değişkenli İstatistik: SPSS ve Lisrel Uygulamaları, Pegem Akademi Yayıncılık, 2012.
• S. Boran, S.H. Gökler, “A Novel FMEA Model Using Hybrid ANFIS–Taguchi Method”, Arab J Sci Eng, 45, 2131–2144, 2020.
• Riahi-Madvar, H., Seifi, A. “Uncertainty analysis in bed load transport prediction of gravel bed rivers by ANN and ANFIS”. Arab J Geosci, 11, 688, 2018.
• H. Baseri, M. Belali-Owsia, “A novel hybrid ICA-ANFIS model for prediction of manufacturing processes performance”, P I Mech Eng E-J Pro, 231(2), 181-190, 2017.
• M. Ganjeh, S. M. Jafari, M. Amanjani, I. Katouzian, “Modeling corrosion trends in tin-free steel and tinplate cans containing tomato paste via adaptive-network-based fuzzy inference system”, J Food Process Eng., 40, e12580, 2017.
• M. H. Jokar, A. Khosravi, A. Heidaripanah, F. Soltani, “Unsaturated soils permeability estimation by adaptive neuro-fuzzy inference system”, Soft Comput, 23 (16), 6871-6881, 2019.
• H. Rahnema, M. Hashemi, H. Khabbaz, “Predicting the Effective Stress Parameter of Unsaturated Soils Using Adaptive Neuro-Fuzzy Inference System”, SCI IRA Transactions A: Civil Engineering, 26, 3140-3158, 2019.
• F. H. Ismail, M. A. Aziz, A. E. Hassanien, “Optimizing the parameters of Sugeno based adaptive neuro fuzzy using artificial bee colony: A Case study on predicting the wind speed”, Proceedings of the Federated Conference on Computer Science and Information Systems, 8, 645–651, 2015.
• V. Moosavi, M. Vafakhah, B. Shirmohammadi , M. Ranjbar, “Optimization of Wavelet-ANFIS and Wavelet-YSA hybrid models by Taguchi method for groundwater level”, Arab J Sci Eng, 39(3), 1785–1796, 2014.
• N. G. Fragiadakis, V. D. Tsoukalas, V. J. Papazoglou, “An adaptive neuro-fuzzy inference system (ANFIS) model for assessing occupational risk in the shipbuilding industry”, Saf Sci, 63, 226–235, 2014.
• M. Alizadeh, M. Lewis, M. H. F. Zarandi, F. Jolai, “Determining significant parameters in the design of ANFIS”, 2011 Annual Meeting of the North American Fuzzy Information Processing Society, 18-20 March 2011 El Paso, TX, USA.
• W. Phootrakornchai, S. Jiriwibhakorn, “Online critical clearing time estimation using an adaptive neuro-fuzzy inference system (ANFIS)”, Int J Elec Power, 73, 170-181, 2015.
• N. Meghanathan, “Assortativity Analysis of Real-World Network Graphs based on Centrality Metrics”, Comput Inf Sci, 9(3), 2016.