Hybrid machine learning for predicting strength of sustainable concrete
作者： Anh-Duc Pham , Ngoc-Tri Ngo , Quang-Trung Nguyen , Ngoc-Son Truong , None
DOI: 10.1007/S00500-020-04848-1
关键词: Random forest 、 Compressive strength 、 Computational intelligence 、 Mean absolute percentage error 、 Support vector machine 、 Correlation coefficient 、 Artificial neural network 、 Mathematical optimization 、 Mathematics 、 Least squares
摘要: Foamed concrete material is a sustainable which widely used in the construction industry due to their sustainability. Accurate prediction of compressive strength vital for structural design. However, empirical methods are limited consider simultaneously all influencing factors predicting foamed materials. Thus, this study proposed novel hybrid artificial intelligence (AI) model couples least squares support vector regression (LSSVR) with grey wolf optimization (GWO) effectively and improve predictive accuracy concrete’s strength. Performance was evaluated using real-world dataset. Comparison results confirm that GWO–LSSVR superior than regression, neural networks, random forest, M5Rules improvement rate 144.2–284.0% mean absolute percentage error (MAPE). Notably, evaluation show showed good agreement between actual predicted values correlation coefficient 0.991 MAPE 3.54%. AI suggested as an effective tool designing
springer.com
sci-hub.se 参考文章(39)
Eid Emary, Hossam M Zawbaa, Aboul Ella Hassanien, None, Binary grey wolf optimization approaches for feature selection Neurocomputing. ,vol. 172, pp. 371- 381 ,(2016) , 10.1016/J.NEUCOM.2015.06.083
Jos De Brabanter, Tony Van Gestel, Joos Vandewalle, Bart De Moor, Johan A K Suykens, Least Squares Support Vector Machines ,(2002)
Maryamsadat Hejazi, S. A. R. Al-Haddad, Yashwant Prasad Singh, Shaiful Jahari Hashim, Ahmad Fazli Abdul Aziz, Multiclass Support Vector Machines for Classification of ECG Data with Missing Values Applied Artificial Intelligence. ,vol. 29, pp. 660- 674 ,(2015) , 10.1080/08839514.2015.1051887
Zhihua Pan, Fujiwara Hiromi, Tionghuan Wee, Preparation of high performance foamed concrete from cement, sand and mineral admixtures Journal of Wuhan University of Technology-materials Science Edition. ,vol. 22, pp. 295- 298 ,(2007) , 10.1007/S11595-005-2295-4
Maryamsadat Hejazi, Yashwant Prasad Singh, ONE-CLASS SUPPORT VECTOR MACHINES APPROACH TO ANOMALY DETECTION Applied Artificial Intelligence. ,vol. 27, pp. 351- 366 ,(2013) , 10.1080/08839514.2013.785791
K. Ramamurthy, E.K. Kunhanandan Nambiar, G. Indu Siva Ranjani, A classification of studies on properties of foam concrete Cement & Concrete Composites. ,vol. 31, pp. 388- 396 ,(2009) , 10.1016/J.CEMCONCOMP.2009.04.006
E.P Kearsley, P.J Wainwright, The effect of high fly ash content on the compressive strength of foamed concrete Cement and Concrete Research. ,vol. 31, pp. 105- 112 ,(2001) , 10.1016/S0008-8846(00)00430-0
Jie Zhao, Khee Poh Lam, Influential factors analysis on LEED building markets in U.S. East Coast cities by using Support Vector Regression Sustainable Cities and Society. ,vol. 5, pp. 37- 43 ,(2012) , 10.1016/J.SCS.2012.05.009
Seyedali Mirjalili, Seyed Mohammad Mirjalili, Andrew Lewis, Grey Wolf Optimizer Advances in Engineering Software. ,vol. 69, pp. 46- 61 ,(2014) , 10.1016/J.ADVENGSOFT.2013.12.007
Ameer A Hilal, Nicholas Howard Thom, Andrew Robert Dawson, None, On void structure and strength of foamed concrete made without/with additives Construction and Building Materials. ,vol. 85, pp. 157- 164 ,(2015) , 10.1016/J.CONBUILDMAT.2015.03.093