Development of a Machine Learning (ML)-based computational model to estimate the engineering properties of Portland Cement Concrete (PCC)

Portland cement concrete (PCC) is the construction material most used worldwide. Hence, its proper characterization is fundamental for the daily-basis engineering practice. Nonetheless, the experimental measurements of the PCC’s engineering properties (i.e., Poisson’s Ratio -v-, Elastic Modulus -E-,...

Full description

Autores:
Polo Mendoza, Rodrigo
Martínez Arguelles, Gilberto
Peñabaena Niebles, Rita
Duque, Jose
Tipo de recurso:
Article of investigation
Fecha de publicación:
2024
Institución:
Corporación Universidad de la Costa
Repositorio:
REDICUC - Repositorio CUC
Idioma:
eng
OAI Identifier:
oai:repositorio.cuc.edu.co:11323/13827
Acceso en línea:
https://hdl.handle.net/11323/13827
https://repositorio.cuc.edu.co/
Palabra clave:
Computational modelling
Concrete structures
Construction materials
Deep neural networks
Machine learning
Portland cement concrete
Rights
openAccess
License
Atribución 4.0 Internacional (CC BY 4.0)
id RCUC2_3cc1056bc44b4c0bf486735d07ab2310
oai_identifier_str oai:repositorio.cuc.edu.co:11323/13827
network_acronym_str RCUC2
network_name_str REDICUC - Repositorio CUC
repository_id_str
dc.title.eng.fl_str_mv Development of a Machine Learning (ML)-based computational model to estimate the engineering properties of Portland Cement Concrete (PCC)
title Development of a Machine Learning (ML)-based computational model to estimate the engineering properties of Portland Cement Concrete (PCC)
spellingShingle Development of a Machine Learning (ML)-based computational model to estimate the engineering properties of Portland Cement Concrete (PCC)
Computational modelling
Concrete structures
Construction materials
Deep neural networks
Machine learning
Portland cement concrete
title_short Development of a Machine Learning (ML)-based computational model to estimate the engineering properties of Portland Cement Concrete (PCC)
title_full Development of a Machine Learning (ML)-based computational model to estimate the engineering properties of Portland Cement Concrete (PCC)
title_fullStr Development of a Machine Learning (ML)-based computational model to estimate the engineering properties of Portland Cement Concrete (PCC)
title_full_unstemmed Development of a Machine Learning (ML)-based computational model to estimate the engineering properties of Portland Cement Concrete (PCC)
title_sort Development of a Machine Learning (ML)-based computational model to estimate the engineering properties of Portland Cement Concrete (PCC)
dc.creator.fl_str_mv Polo Mendoza, Rodrigo
Martínez Arguelles, Gilberto
Peñabaena Niebles, Rita
Duque, Jose
dc.contributor.author.none.fl_str_mv Polo Mendoza, Rodrigo
Martínez Arguelles, Gilberto
Peñabaena Niebles, Rita
Duque, Jose
dc.subject.proposal.eng.fl_str_mv Computational modelling
Concrete structures
Construction materials
Deep neural networks
Machine learning
Portland cement concrete
topic Computational modelling
Concrete structures
Construction materials
Deep neural networks
Machine learning
Portland cement concrete
description Portland cement concrete (PCC) is the construction material most used worldwide. Hence, its proper characterization is fundamental for the daily-basis engineering practice. Nonetheless, the experimental measurements of the PCC’s engineering properties (i.e., Poisson’s Ratio -v-, Elastic Modulus -E-, Compressive Strength -ComS-, and Tensile Strength -TenS-) consume considerable amounts of time and financial resources. Therefore, the development of high-precision indirect methods is fundamental. Accordingly, this research proposes a computational model based on deep neural networks (DNNs) to simultaneously predict the v, E, ComS, and TenS. For this purpose, the Long-Term Pavement Performance database was employed as the data source. In this regard, the mix design parameters of the PCC are adopted as input variables. The performance of the DNN model was evaluated with 1:1 lines, goodness-of-fit parameters, Shapley additive explanations assessments, and running time analysis. The results demonstrated that the proposed DNN model exhibited an exactitude higher than 99.8%, with forecasting errors close to zero (0). Consequently, the machine learning-based computational model designed in this investigation is a helpful tool for estimating the PCC’s engineering properties when laboratory tests are not attainable. Thus, the main novelty of this study is creating a robust model to determine the v, E, ComS, and TenS by solely considering the mix design parameters. Likewise, the central contribution to the state-of-the-art achieved by the present research effort is the public launch of the developed computational tool through an open-access GitHub repository, which can be utilized by engineers, designers, agencies, and other stakeholders.
publishDate 2024
dc.date.accessioned.none.fl_str_mv 2024-11-25T18:03:51Z
dc.date.available.none.fl_str_mv 2024-11-25T18:03:51Z
dc.date.issued.none.fl_str_mv 2024-05-03
dc.type.none.fl_str_mv Artículo de revista
dc.type.coar.none.fl_str_mv http://purl.org/coar/resource_type/c_2df8fbb1
dc.type.content.none.fl_str_mv Text
dc.type.driver.none.fl_str_mv info:eu-repo/semantics/article
dc.type.redcol.none.fl_str_mv http://purl.org/redcol/resource_type/ART
dc.type.version.none.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.coarversion.none.fl_str_mv http://purl.org/coar/version/c_970fb48d4fbd8a85
format http://purl.org/coar/resource_type/c_2df8fbb1
status_str publishedVersion
dc.identifier.citation.none.fl_str_mv Polo-Mendoza, R., Martinez-Arguelles, G., Peñabaena-Niebles, R. et al. Development of a Machine Learning (ML)-Based Computational Model to Estimate the Engineering Properties of Portland Cement Concrete (PCC). Arab J Sci Eng 49, 14351–14365 (2024). https://doi.org/10.1007/s13369-024-08794-0
dc.identifier.issn.none.fl_str_mv 2193-567X
dc.identifier.uri.none.fl_str_mv https://hdl.handle.net/11323/13827
dc.identifier.doi.none.fl_str_mv 10.1007/s13369-024-08794-0
dc.identifier.eissn.none.fl_str_mv 2191-4281
dc.identifier.instname.none.fl_str_mv Corporación Universidad de la Costa
dc.identifier.reponame.none.fl_str_mv REDICUC - Repositorio CUC
dc.identifier.repourl.none.fl_str_mv https://repositorio.cuc.edu.co/
identifier_str_mv Polo-Mendoza, R., Martinez-Arguelles, G., Peñabaena-Niebles, R. et al. Development of a Machine Learning (ML)-Based Computational Model to Estimate the Engineering Properties of Portland Cement Concrete (PCC). Arab J Sci Eng 49, 14351–14365 (2024). https://doi.org/10.1007/s13369-024-08794-0
2193-567X
10.1007/s13369-024-08794-0
2191-4281
Corporación Universidad de la Costa
REDICUC - Repositorio CUC
url https://hdl.handle.net/11323/13827
https://repositorio.cuc.edu.co/
dc.language.iso.none.fl_str_mv eng
language eng
dc.relation.ispartofjournal.none.fl_str_mv Arabian journal for science and engineering
dc.relation.references.none.fl_str_mv Liu, Y.; Du, P.; Tan, K.H.; Du, Y.; Su, J.; Shi, C.: Experimental and analytical studies on residual flexural behaviour of reinforced alkali-activated slag-based concrete beams after exposure to fire. Eng. Struct. 298, 1–14 (2024). https://doi.org/10.1016/j.engstruct. 2023.117035
Singh, A.; Bhadauria, S.S.; Thakare, A.A.; Kumar, A.; Mudgal, M.; Chaudhary, S.: Durability assessment of mechanochemically activated geopolymer concrete with a low molarity alkali solution. Case Stud. Constr. Mater. 20, 1–19 (2024). https://doi.org/10.1016/ j.cscm.2023.e02715
Singh, P.R.; Vanapalli, K.R.; Jadda, K.: Durability assessment of fly ash, GGBS, and silica fume based geopolymer concrete with recycled aggregates against acid and sulfate attack. J. Build. Eng. 82, 1–17 (2024). https://doi.org/10.1016/j.jobe.2023.108354
Polo-Mendoza, R.; Mora, O.; Duque, J.; Turbay, E.; MartinezArguelles, G.; Fuentes, L.; Guerrero, O.; Perez, S.: Environmental and economic feasibility of implementing perpetual pavements (PPs) against conventional pavements: a case study of Barranquilla city, Colombia. Case Stud. Constr. Mater. 18, 1–21 (2023). https:// doi.org/10.1016/j.cscm.2023.e02112
Yuanliang, X.; Zhongshuai, H.; Chao, L.; Chao, Z.; Yamei, Z.: Unveiling the role of Portland cement and fly ash in pore formation and its influence on properties of hybrid alkali-activated foamed concrete. Constr. Build. Mater. 411, 1–10 (2024). https://doi.org/ 10.1016/j.conbuildmat.2023.134336
Yang, Y.; Yao, J.; Liu, J.; Kong, D.; Gu, C.; Wang, L.: Evaluation of the thermal and shrinkage stresses in restrained concrete: new method of investigation. Constr. Build. Mater. 411, 1–14 (2024). https://doi.org/10.1016/j.conbuildmat.2023.134493
Amin, M.N.; Khan, K.; Javed, M.F.; Aslam, F.; Qadir, M.G.; Faraz, M.I.: Prediction of mechanical properties of fly-ash/slag-based geopolymer concrete using ensemble and non-ensemble machinelearning techniques. Materials 15, 1–20 (2022). https://doi.org/10. 3390/ma15103478
Cao, R.; Fang, Z.; Jin, M.; Shang, Y.: Application of machine learning approaches to predict the strength property of geopolymer concrete. Materials 15, 1–15 (2022). https://doi.org/10.3390/ ma15072400
Huynh, A.T.; Nguyen, Q.D.; Xuan, Q.L.; Magee, B.; Chung, T.; Tran, K.T.; Nguyen, K.T.: A machine learning-assisted numerical predictor for compressive strength of geopolymer concrete based on experimental data and sensitivity analysis. Appl. Sci. 10, 1–16 (2020). https://doi.org/10.3390/app10217726
Nithurshan, M.; Elakneswaran, Y.: A systematic review and assessment of concrete strength prediction models. Case Stud. Constr. Mater. 18, 1–15 (2023). https://doi.org/10.1016/j.cscm.2023.e0 1830
Moein, M.M.; Saradar, A.; Rahmati, K.; Ghasemzadeh Mousavinejad, S.H.; Bristow, J.; Aramali, V.; Karakouzian, M.: Predictive models for concrete properties using machine learning and deep learning approaches: a review. J. Build. Eng. 63, 1–41 (2023). https://doi.org/10.1016/j.jobe.2022.105444
Ahmed, H.U.; Mohammed, A.S.; Qaidi, S.M.A.; Faraj, R.H.; Hamah Sor, N.; Mohammed, A.A.: Compressive strength of geopolymer concrete composites: a systematic comprehensive review, analysis and modeling. Eur. J. Environ. Civ. Eng. 27, 1383–1428 (2023). https://doi.org/10.1080/19648189.2022.20 83022
Mansouri, E.; Manfredi, M.; Hu, J.-W.: Environmentally friendly concrete compressive strength prediction using hybrid machine learning. Sustainability 14, 1–17 (2022). https://doi.org/10.3390/ su142012990
Marks, M.; Glinicki, M.A.; Gibas, K.: Prediction of the chloride resistance of concrete modified with high calcium fly ash using machine learning. Materials 8, 8714–8727 (2015). https://doi.org/ 10.3390/ma8125483
Najm, H.M.; Nanayakkara, O.; Ahmad, M.; Sabri Sabri, M.M.: Mechanical properties, crack width, and propagation of waste ceramic concrete subjected to elevated temperatures: a comprehensive study. Materials 15, 1–32 (2022). https://doi.org/10.3390/ ma15072371
Tang, Y.X.; Lee, Y.H.; Amran, M.; Fediuk, R.; Vatin, N.; Kueh, A.B.H.; Lee, Y.Y.: Artificial neural network-forecasted compression strength of alkaline-activated slag concretes. Sustainability 14, 1–20 (2022). https://doi.org/10.3390/su14095214
Shafigh, P.; Asadi, I.; Mahyuddin, N.B.: Concrete as a thermal mass material for building applications—A review. J. Build. Eng. 19, 14–25 (2018). https://doi.org/10.1016/j.jobe.2018.04.021
Rocha Segundo, I.; Silva, L.; Palha, C.; Freitas, E.; Silva, H.: Surface rehabilitation of Portland cement concrete (PCC) pavements using single or double surface dressings with soft bitumen, conventional or modified emulsions. Constr. Build. Mater. 281, 1–15 (2021). https://doi.org/10.1016/j.conbuildmat.2021.122611
Aquino Rocha, J.H.; Toledo Filho, R.D.: Microstructure, hydration process, and compressive strength assessment of ternary mixtures containing Portland cement, recycled concrete powder, and metakaolin. J. Clean. Prod. 434, 1–24 (2024). https://doi.org/10. 1016/j.jclepro.2023.140085
Zou, Y.; Zheng, C.; Alzahrani, A.M.; Ahmad, W.; Ahmad, A.; Mohamed, A.M.; Khallaf, R.; Elattar, S.: Evaluation of artificial intelligence methods to estimate the compressive strength of geopolymers. Gels 8, 1–23 (2022). https://doi.org/10.3390/gels80 50271
Shah, H.A.; Yuan, Q.; Akmal, U.; Shah, S.A.; Salmi, A.; Awad, Y.A.; Shah, L.A.; Iftikhar, Y.; Javed, M.H.; Khan, M.I.: Application of machine learning techniques for predicting compressive, splitting tensile, and flexural strengths of concrete with metakaolin. Materials 15, 1–36 (2022). https://doi.org/10.3390/ma15155435
Silva, V.P.; Carvalho, R.D.; Rêgo, J.H.; Evangelista, F., Jr.: Machine learning-based prediction of the compressive strength of Brazilian concretes: a dual-dataset study. Materials 16, 1–16 (2023). https:// doi.org/10.3390/ma16144977
FHWA. Long-Term Pavement Performance Information Management System User Guide. Fed. Highw. Adm. FHWA-HRT-2, 1–208 (2021)
Karlaftis, A.G.; Badr, A.: Predicting asphalt pavement crack initiation following rehabilitation treatments. Transp. Res. Part C Emerg. Technol. 55, 510–517 (2015). https://doi.org/10.1016/j.trc.2015.03 .031
Jia, Y.; Wang, S.; Huang, A.; Gao, Y.; Wang, J.; Zhou, W.: A comparative long-term effectiveness assessment of preventive maintenance treatments under various environmental conditions. Constr. Build. Mater. 273, 1–10 (2021). https://doi.org/10.1016/j. conbuildmat.2020.121717
Yu, Y.; Sun, L.: Effect of overlay thickness, overlay material, and pre-overlay treatment on evolution of asphalt concrete overlay roughness in LTPP SPS-5 experiment: a multilevel model approach. Constr. Build. Mater. 162, 192–201 (2018). https://doi. org/10.1016/j.conbuildmat.2017.12.039
Sollazzo, G.; Fwa, T.F.; Bosurgi, G.: An ANN model to correlate roughness and structural performance in asphalt pavements. Constr. Build. Mater. 134, 684–693 (2017). https://doi.org/10.1016/j.conb uildmat.2016.12.186
Gong, H.; Sun, Y.; Shu, X.; Huang, B.: Use of random forests regression for predicting IRI of asphalt pavements. Constr. Build. Mater. 189, 890–897 (2018). https://doi.org/10.1016/j.conbuild mat.2018.09.017
Gong, H.; Huang, B.; Shu, X.: Field performance evaluation of asphalt mixtures containing high percentage of RAP using LTPP data. Constr. Build. Mater. 176, 118–128 (2018). https://doi.org/ 10.1016/j.conbuildmat.2018.05.007
Chen, X.; Dong, Q.; Zhu, H.; Huang, B.: Development of distress condition index of asphalt pavements using LTPP data through structural equation modeling. Transp. Res. Part C Emerg. Technol. 68, 58–69 (2016). https://doi.org/10.1016/j.trc.2016.03.011
Gong, H.; Sun, Y.; Hu, W.; Polaczyk, P.A.; Huang, B.: Investigating impacts of asphalt mixture properties on pavement performance using LTPP data through random forests. Constr. Build. Mater. 204, 203–212 (2019). https://doi.org/10.1016/j.conbuildmat.2019. 01.198
Rashidian-Dezfouli, H.; Rangaraju, P.R.: Evaluation of selected durability properties of portland cement concretes containing ground glass fiber as a pozzolan. Transp. Res. Rec. 2672, 88–98 (2018). https://doi.org/10.1177/0361198118773198
Ogbodo, M.C.; Akpabot, A.I.: An assessment of some physical properties of different brands of cement in Nigeria. In: IOP Conference Series: Materials Science and Engineering, vol. 1048, pp. 1–5 (2021). https://doi.org/10.1088/1757-899X/1048/1/012013
Zemri, C.; Bachir Bouiadjra, M.: Comparison between physical–mechanical properties of mortar made with Portland cement (CEMI) and slag cement (CEMIII) subjected to elevated temperature. Case Stud. Constr. Mater. 12, 1–12 (2020). https://doi.org/10. 1016/j.cscm.2020.e00339
Latifoglu, L.; Ozger, M.: A novel approach for high-performance estimation of SPI data in drought prediction. Sustainability 15, 1–29 (2023). https://doi.org/10.3390/su151914046
Anysz, H.; Zbiciak, A.; Ibadov, N.: The influence of input data standardization method on prediction accuracy of artificial neural networks. Procedia Eng. 153, 66–70 (2016). https://doi.org/10. 1016/j.proeng.2016.08.081
Deo, R.C.; ¸Sahin, M.: Application of the Artificial Neural Network model for prediction of monthly Standardized Precipitation and Evapotranspiration Index using hydrometeorological parameters and climate indices in eastern Australia. Atmos. Res. 161–162, 65–81 (2015). https://doi.org/10.1016/j.atmosres.2015.03.018
Chollet Ramampiandra, E.; Scheidegger, A.;Wydler, J.; Schuwirth, N.: A comparison of machine learning and statistical species distribution models: quantifying overfitting supports model interpretation. Ecol. Model. 481, 1–11 (2023). https://doi.org/10.1016/ j.ecolmodel.2023.110353
Ookura, S.; Mori, H.: An efficient method for wind power generation forecasting by LSTM in consideration of overfitting prevention. IFAC Pap. 53, 12169–12174 (2020). https://doi.org/10.1016/ j.ifacol.2020.12.1008
Piotrowski, A.P.; Napiorkowski, J.J.: A comparison of methods to avoid overfitting in neural networks training in the case of catchment runoff modelling. J. Hydrol. 476, 97–111 (2013). https://doi. org/10.1016/j.jhydrol.2012.10.019
Bahtiyar, H.; Soydaner, D.; Yüksel, E.: Application of multilayer perceptron with data augmentation in nuclear physics. Appl. Soft Comput. 128, 1–9 (2022). https://doi.org/10.1016/j.asoc.2022.10 9470
Min, R.; Wang, Z.; Zhuang, Y.; Yi, X.: Application of semisupervised convolutional neural network regression model based on data augmentation and process spectral labeling in Raman predictive modeling of cell culture processes. Biochem. Eng. J. 191, 1–9 (2023). https://doi.org/10.1016/j.bej.2022.108774
Hao, R.; Zheng, H.; Yang, X.: Data augmentation based estimation for the censored composite quantile regression neural network model. Appl. Soft Comput. 127, 1–11 (2022). https://doi.org/10. 1016/j.asoc.2022.109381
Demir, S.; Mincev, K.; Kok, K.; Paterakis, N.G.: Data augmentation for time series regression: applying transformations, autoencoders and adversarial networks to electricity price forecasting. Appl. Energy 304, 1–19 (2021). https://doi.org/10.1016/j.apenergy.2021. 117695
Hao, R.; Weng, C.; Liu, X.; Yang, X.: Data augmentation based estimation for the censored quantile regression neural network model. Expert Syst. Appl. 214, 1–15 (2023). https://doi.org/10. 1016/j.eswa.2022.119097
Shorten, C.; Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6, 1–48 (2019). https://doi.org/ 10.1186/s40537-019-0197-0
Berrett, C.; Calder, C.A.: Data augmentation strategies for the Bayesian spatial probit regression model. Comput. Stat. Data Anal. 56, 478–490 (2012). https://doi.org/10.1016/j.csda.2011.08.020
Mazzoleni, M.; Breschi, V.; Formentin, S.: Piecewise nonlinear regression with data augmentation. IFAC Pap. 54, 421–426 (2021). https://doi.org/10.1016/j.ifacol.2021.08.396
Polo-Mendoza, R.; Martinez-Arguelles, G.; Peñabaena-Niebles, R.; Covilla-Valera, E.: Neural networks implementation for the environmental optimisation of the recycled concrete aggregate inclusion in warm mix asphalt. Road Mater. Pavement Des. (2023). https://doi.org/10.1080/14680629.2023.2230298
Himmeto ˘glu, S.; Delice, Y.; Aydo ˘gan, E.K.; Uzal, B.: Green building envelope designs in different climate and seismic zones: multi-objective ANN-based genetic algorithm. Sustain. Energy Technol. Assess. 53, 1–17 (2022). https://doi.org/10.1016/j.seta. 2022.102505
Minh, D.; Wang, H.X.; Li, Y.F.; Nguyen, T.N.: Explainable artificial intelligence: a comprehensive review. Artif. Intell. Rev. 55, 3503–3568 (2022). https://doi.org/10.1007/s10462-021-10088-y
Polo-Mendoza, R.; Martinez-Arguelles, G.; Peñabaena-Niebles, R.: A multi-objective optimization based on genetic algorithms for the sustainable design of Warm Mix Asphalt (WMA). Int. J. Pavement Eng. 24, 2074417 (2023). https://doi.org/10.1080/1029 8436.2022.2074417
Białek, J.; Bujalski, W.; Wojdan, K.; Guzek, M.; Kurek, T.: Dataset level explanation of heat demand forecasting ANN with SHAP. Energy 261, 1–12 (2022). https://doi.org/10.1016/j.energy.2022.12 5075
Polo-Mendoza, R.; Duque, J.; Mašín, D.; Turbay, E.; Acosta, C.: Implementation of deep neural networks and statistical methods to predict the resilient modulus of soils. Int. J. Pavement Eng. 24, 2257852 (2023). https://doi.org/10.1080/10298436.2023.2257852
Hamim, A.; Yusoff, N.I.M.; Omar, H.A.; Jamaludin, N.A.A.; Hassan, N.A.; El-Shafie, A.; Ceylan, H.: Integrated finite element and artificial neural network methods for constructing asphalt concrete dynamic modulus master curve using deflection time-history data. Constr. Build. Mater. 257, 1–14 (2020). https://doi.org/10.1016/j. conbuildmat.2020.119549
Polo-Mendoza, R.; Martinez-Arguelles, G.; Peñabaena-Niebles, R.: Environmental optimization of warm mix asphalt (WMA) design with recycled concrete aggregates (RCA) inclusion through artificial intelligence (AI) techniques. Res. Eng. 17, 1–15 (2023). https://doi.org/10.1016/j.rineng.2023.100984
Zdravkovi´c, S.; Kavitha, L.; Satari´c, M.V.; Zekovi´c, S.; Petrovi´c, J.: Modified extended tanh-function method and nonlinear dynamics of microtubules. Chaos Solitons Fractals 45, 1378–1386 (2012). https://doi.org/10.1016/j.chaos.2012.07.009
Wuraola, A.; Patel, N.: Resource efficient activation functions for neural network accelerators. Neurocomputing 482, 163–185 (2022)
Liu, K.; Shi,W.; Huang, C.; Zeng, D.: Cost effective Tanh activation function circuits based on fast piecewise linear logic. Microelectron. J. 138, 1–9 (2023). https://doi.org/10.1016/j.mejo.2023.10 5821
Kingma, D.P.; Ba, J.L.: Amax: a method for stochastic optimization. In: 3rd International Conference on Learning Representations (ICLR), pp. 1–15 (2015)
Pandi Chandran, P.; Hema Rajini, N.; Jeyakarthic, M.: Optimal deep belief network enabled malware detection and classification model. Intell. Autom. Soft Comput. (2023). https://doi.org/10.32 604/iasc.2023.029946
Obayya, M.; Maashi, M.S.; Nemri, N.; Mohsen, H.; Motwakel, A.; Osman, A.E.; Alneil, A.A.; Alsaid, M.I.: Hyperparameter optimizer with deep learning-based decision-support systems for histopathological breast cancer diagnosis. Cancers 15, 1–19 (2023). https://doi.org/10.3390/cancers15030885
Sadykov, M.; Haines, S.; Broadmeadow, M.; Walker, G.; Holmes, D.W.: Practical evaluation of lithium-ion battery state-of-charge estimation using time-series machine learning for electric vehicles. Energies 16, 1–34 (2023). https://doi.org/10.3390/en16041628
Zhang, S.; Lei, H.; Zhou, Z.; Wang, G.; Qiu, B.: Fatigue life analysis of high-strength bolts based on machine learning method and SHapley Additive exPlanations (SHAP) approach. Structures 51, 275–287 (2023). https://doi.org/10.1016/j.istruc.2023.03.060
Nicolson, A.; Paliwal, K.K.: Deep learning for minimum meansquare error approaches to speech enhancement. Speech Commun. 111, 44–55 (2019). https://doi.org/10.1016/j.specom.2019.06.002
Koya, B.P.; Aneja, S.; Gupta, R.; Valeo, C.: Comparative analysis of different machine learning algorithms to predict mechanical properties of concrete. Mech. Adv. Mater. Struct. 29, 4032–4043 (2022). https://doi.org/10.1080/15376494.2021.1917021
Vilares Ferro, M.; Doval Mosquera, Y.; Ribadas Pena, F.J.; Darriba Bilbao, V.M.: Early stopping by correlating online indicators in neural networks. Neural Netw. 159, 109–124 (2023). https://doi. org/10.1016/j.neunet.2022.11.035
Zeng, J.; Zhang, M.; Lin, S.-B.: Fully corrective gradient boosting with squared hinge: fast learning rates and early stopping. Neural Netw. 147, 136–151 (2022). https://doi.org/10.1016/j.neunet.2021. 12.016
Singh, V.; Pencina, M.; Einstein, A.J.; Liang, J.X.; Berman, D.S.; Slomka, P.: Impact of train/test sample regimen on performance estimate stability of machine learning in cardiovascular imaging. Sci. Rep. 11, 1–8 (2021). https://doi.org/10.1038/s41598-021-93 651-5
Xu, Y.; Goodacre, R.: On splitting training and validation set: a comparative study of cross-validation, bootstrap and systematic sampling for estimating the generalization performance of supervised learning. J. Anal. Test. 2, 249–262 (2018). https://doi.org/10. 1007/s41664-018-0068-2
Quinn, T.P.; Le, V.; Cardilini, A.P.A.: Test set verification is an essential step in model building. Methods Ecol. Evol. 12, 127–129 (2021). https://doi.org/10.1111/2041-210X.13495
Straub, J.: Machine learning performance validation and training using a ‘perfect’ expert system. MethodsX 8, 1–6 (2021). https:// doi.org/10.1016/j.mex.2021.101477
Polo-Mendoza, R.; Duque, J.; Mašín, D.: Prediction of California bearing ratio and modified proctor parameters using deep neural networks and multiple linear regression: a case study of granular soils. Case Stud. Constr. Mater. 20, 1–17 (2024). https://doi.org/ 10.1016/j.cscm.2023.e02800
Li, Z.: Extracting spatial effects from machine learning model using local interpretation method: an example of SHAP and XGBoost. Comput. Environ. Urban Syst. 96, 1–18 (2022). https://doi.org/10. 1016/j.compenvurbsys.2022.101845
Kim, Y.; Kim, Y.: Explainable heat-related mortality with random forest and SHapley Additive exPlanations (SHAP) models. Sustain. Cities Soc. 79, 1–15 (2022). https://doi.org/10.1016/j.scs.2022.10 3677
Lin, K.; Gao, Y.: Model interpretability of financial fraud detection by group SHAP. Expert Syst. Appl. 210, 1–9 (2022). https://doi. org/10.1016/j.eswa.2022.118354
Kashifi, M.T.: Investigating two-wheelers risk factors for severe crashes using an interpretable machine learning approach and SHAP analysis. IATSS Res. 47, 357–371 (2023). https://doi.org/ 10.1016/j.iatssr.2023.07.005
Meng, Y.; Yang, N.; Qian, Z.; Zhang, G.: What makes an online review more helpful: an interpretation framework using XGBoost and SHAP values. J. Theor. Appl. Electron. Commer. Res. 16, 466–490 (2021). https://doi.org/10.3390/jtaer16030029
Scavuzzo, C.M.; Scavuzzo, J.M.; Campero, M.N.; Anegagrie, M.; Aramendia, A.A.; Benito, A.; Periago, V.: Feature importance: opening a soil-transmitted helminth machine learning model via SHAP. Infect. Dis. Model. 7, 262–276 (2022). https://doi.org/10. 1016/j.idm.2022.01.004
Tang, Y.; Wang, C.: Performance modeling on DaVinci AI core. J. Parallel Distrib. Comput. 175, 134–149 (2023). https://doi.org/10. 1016/j.jpdc.2023.01.008
Dube, P.; Suk, T.; Wang, C.: AI gauge: runtime estimation for deep learning in the cloud. In: 31st International Symposium on Computer Architecture and High Performance Computing (SBACPAD), pp. 160–167 (2019)
Aghapour, Z.; Sharifian, S.; Taheri, H.: Task offloading and resource allocation algorithm based on deep reinforcement learning for distributed AI execution tasks in IoT edge computing environments. Comput. Netw. 223, 1–17 (2023). https://doi.org/10.1016/ j.comnet.2023.109577
Assaf, A.M.; Haron, H.; Hamed, H.N.A.H.; Ghaleb, F.A.; Dalam, M.E.; Eisa, T.A.E.: Improving solar radiation forecasting utilizing data augmentation model generative adversarial networks with convolutional support vector machine (GAN-CSVR). Appl. Sci. 13, 1–23 (2023). https://doi.org/10.3390/app132312768
Harrou, F.; Dairi, A.; Dorbane, A.; Sun, Y.: Energy consumption prediction in water treatment plants using deep learning with data augmentation. Res. Eng. 20, 1–14 (2023). https://doi.org/10.1016/ j.rineng.2023.101428
Liu, K.-H.; Xie, T.-Y.; Cai, Z.-K.; Chen, G.-M.; Zhao, X.-Y.: Datadriven prediction and optimization of axial compressive strength for FRP-reinforced CFST columns using synthetic data augmentation. Eng. Struct. 300, 1–16 (2024). https://doi.org/10.1016/j.engs truct.2023.117225
Mumuni, A.; Mumuni, F.: Data augmentation: a comprehensive survey of modern approaches. Array 16, 1–27 (2022). https://doi. org/10.1016/j.array.2022.100258
Maharana, K.; Mondal, S.; Nemade, B.: A review: data preprocessing and data augmentation techniques. Glob. Transitions Proc. 3, 91–99 (2022). https://doi.org/10.1016/j.gltp.2022.04.020
Walubita, L.F.; Martinez-Arguelles, G.; Polo-Mendoza, R.; IckLee, S.; Fuentes, L.: Comparative environmental assessment of rigid, flexible, and perpetual pavement: a case study of Texas. Sustainability 14, 1–22 (2022). https://doi.org/10.3390/su14169983
Gupta, S.; Chaudhary, S.: State of the art review on supplementary cementitious materials in India—II: characteristics of SCMs, effect on concrete and environmental impact. J. Clean. Prod. 357, 1–19 (2022). https://doi.org/10.1016/j.jclepro.2022.131945
Sharma, R.K.; Singh, D.; Dasaka, S.M.: Investigating supplementary cementitious materials’ effects on stabilized aggregate performance, behaviour, and design aspects. Constr. Build. Mater. 411, 1–16 (2024). https://doi.org/10.1016/j.conbuildmat.2023.13 4564
dc.relation.citationendpage.none.fl_str_mv 14365
dc.relation.citationstartpage.none.fl_str_mv 14351
dc.relation.citationissue.none.fl_str_mv 10
dc.relation.citationvolume.none.fl_str_mv 49
dc.rights.none.fl_str_mv © The Author(s) 2024.
dc.rights.license.none.fl_str_mv Atribución 4.0 Internacional (CC BY 4.0)
dc.rights.uri.none.fl_str_mv https://creativecommons.org/licenses/by/4.0/
dc.rights.accessrights.none.fl_str_mv info:eu-repo/semantics/openAccess
dc.rights.coar.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
rights_invalid_str_mv Atribución 4.0 Internacional (CC BY 4.0)
© The Author(s) 2024.
https://creativecommons.org/licenses/by/4.0/
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.extent.none.fl_str_mv 15 páginas
dc.format.mimetype.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Springer nature
dc.publisher.place.none.fl_str_mv Germany
publisher.none.fl_str_mv Springer nature
dc.source.none.fl_str_mv https://link.springer.com/article/10.1007/s13369-024-08794-0
institution Corporación Universidad de la Costa
bitstream.url.fl_str_mv https://repositorio.cuc.edu.co/bitstreams/640afd64-f03c-4432-8110-0b128dee2e56/download
https://repositorio.cuc.edu.co/bitstreams/8cf055cf-ed8d-4c7b-8f2c-67b2c2294da4/download
https://repositorio.cuc.edu.co/bitstreams/9d705359-a8b8-47cf-941c-34b11dd4c562/download
https://repositorio.cuc.edu.co/bitstreams/7fab4be2-3787-4eed-8146-d6507fe868ea/download
bitstream.checksum.fl_str_mv 79594e959ef1498796741ba97faf792a
73a5432e0b76442b22b026844140d683
bcd06dbcaa28451dcd13a9358418e60e
b32a28d234a79b8dbeaeb806a370cf9b
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositorio de la Universidad de la Costa CUC
repository.mail.fl_str_mv repdigital@cuc.edu.co
_version_ 1828166548441792512
spelling Atribución 4.0 Internacional (CC BY 4.0)© The Author(s) 2024.https://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Polo Mendoza, RodrigoMartínez Arguelles, GilbertoPeñabaena Niebles, RitaDuque, Jose2024-11-25T18:03:51Z2024-11-25T18:03:51Z2024-05-03Polo-Mendoza, R., Martinez-Arguelles, G., Peñabaena-Niebles, R. et al. Development of a Machine Learning (ML)-Based Computational Model to Estimate the Engineering Properties of Portland Cement Concrete (PCC). Arab J Sci Eng 49, 14351–14365 (2024). https://doi.org/10.1007/s13369-024-08794-02193-567Xhttps://hdl.handle.net/11323/1382710.1007/s13369-024-08794-02191-4281Corporación Universidad de la CostaREDICUC - Repositorio CUChttps://repositorio.cuc.edu.co/Portland cement concrete (PCC) is the construction material most used worldwide. Hence, its proper characterization is fundamental for the daily-basis engineering practice. Nonetheless, the experimental measurements of the PCC’s engineering properties (i.e., Poisson’s Ratio -v-, Elastic Modulus -E-, Compressive Strength -ComS-, and Tensile Strength -TenS-) consume considerable amounts of time and financial resources. Therefore, the development of high-precision indirect methods is fundamental. Accordingly, this research proposes a computational model based on deep neural networks (DNNs) to simultaneously predict the v, E, ComS, and TenS. For this purpose, the Long-Term Pavement Performance database was employed as the data source. In this regard, the mix design parameters of the PCC are adopted as input variables. The performance of the DNN model was evaluated with 1:1 lines, goodness-of-fit parameters, Shapley additive explanations assessments, and running time analysis. The results demonstrated that the proposed DNN model exhibited an exactitude higher than 99.8%, with forecasting errors close to zero (0). Consequently, the machine learning-based computational model designed in this investigation is a helpful tool for estimating the PCC’s engineering properties when laboratory tests are not attainable. Thus, the main novelty of this study is creating a robust model to determine the v, E, ComS, and TenS by solely considering the mix design parameters. Likewise, the central contribution to the state-of-the-art achieved by the present research effort is the public launch of the developed computational tool through an open-access GitHub repository, which can be utilized by engineers, designers, agencies, and other stakeholders.15 páginasapplication/pdfengSpringer natureGermanyhttps://link.springer.com/article/10.1007/s13369-024-08794-0Development of a Machine Learning (ML)-based computational model to estimate the engineering properties of Portland Cement Concrete (PCC)Artículo de revistahttp://purl.org/coar/resource_type/c_2df8fbb1Textinfo:eu-repo/semantics/articlehttp://purl.org/redcol/resource_type/ARTinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/version/c_970fb48d4fbd8a85Arabian journal for science and engineeringLiu, Y.; Du, P.; Tan, K.H.; Du, Y.; Su, J.; Shi, C.: Experimental and analytical studies on residual flexural behaviour of reinforced alkali-activated slag-based concrete beams after exposure to fire. Eng. Struct. 298, 1–14 (2024). https://doi.org/10.1016/j.engstruct. 2023.117035Singh, A.; Bhadauria, S.S.; Thakare, A.A.; Kumar, A.; Mudgal, M.; Chaudhary, S.: Durability assessment of mechanochemically activated geopolymer concrete with a low molarity alkali solution. Case Stud. Constr. Mater. 20, 1–19 (2024). https://doi.org/10.1016/ j.cscm.2023.e02715Singh, P.R.; Vanapalli, K.R.; Jadda, K.: Durability assessment of fly ash, GGBS, and silica fume based geopolymer concrete with recycled aggregates against acid and sulfate attack. J. Build. Eng. 82, 1–17 (2024). https://doi.org/10.1016/j.jobe.2023.108354Polo-Mendoza, R.; Mora, O.; Duque, J.; Turbay, E.; MartinezArguelles, G.; Fuentes, L.; Guerrero, O.; Perez, S.: Environmental and economic feasibility of implementing perpetual pavements (PPs) against conventional pavements: a case study of Barranquilla city, Colombia. Case Stud. Constr. Mater. 18, 1–21 (2023). https:// doi.org/10.1016/j.cscm.2023.e02112Yuanliang, X.; Zhongshuai, H.; Chao, L.; Chao, Z.; Yamei, Z.: Unveiling the role of Portland cement and fly ash in pore formation and its influence on properties of hybrid alkali-activated foamed concrete. Constr. Build. Mater. 411, 1–10 (2024). https://doi.org/ 10.1016/j.conbuildmat.2023.134336Yang, Y.; Yao, J.; Liu, J.; Kong, D.; Gu, C.; Wang, L.: Evaluation of the thermal and shrinkage stresses in restrained concrete: new method of investigation. Constr. Build. Mater. 411, 1–14 (2024). https://doi.org/10.1016/j.conbuildmat.2023.134493Amin, M.N.; Khan, K.; Javed, M.F.; Aslam, F.; Qadir, M.G.; Faraz, M.I.: Prediction of mechanical properties of fly-ash/slag-based geopolymer concrete using ensemble and non-ensemble machinelearning techniques. Materials 15, 1–20 (2022). https://doi.org/10. 3390/ma15103478Cao, R.; Fang, Z.; Jin, M.; Shang, Y.: Application of machine learning approaches to predict the strength property of geopolymer concrete. Materials 15, 1–15 (2022). https://doi.org/10.3390/ ma15072400Huynh, A.T.; Nguyen, Q.D.; Xuan, Q.L.; Magee, B.; Chung, T.; Tran, K.T.; Nguyen, K.T.: A machine learning-assisted numerical predictor for compressive strength of geopolymer concrete based on experimental data and sensitivity analysis. Appl. Sci. 10, 1–16 (2020). https://doi.org/10.3390/app10217726Nithurshan, M.; Elakneswaran, Y.: A systematic review and assessment of concrete strength prediction models. Case Stud. Constr. Mater. 18, 1–15 (2023). https://doi.org/10.1016/j.cscm.2023.e0 1830Moein, M.M.; Saradar, A.; Rahmati, K.; Ghasemzadeh Mousavinejad, S.H.; Bristow, J.; Aramali, V.; Karakouzian, M.: Predictive models for concrete properties using machine learning and deep learning approaches: a review. J. Build. Eng. 63, 1–41 (2023). https://doi.org/10.1016/j.jobe.2022.105444Ahmed, H.U.; Mohammed, A.S.; Qaidi, S.M.A.; Faraj, R.H.; Hamah Sor, N.; Mohammed, A.A.: Compressive strength of geopolymer concrete composites: a systematic comprehensive review, analysis and modeling. Eur. J. Environ. Civ. Eng. 27, 1383–1428 (2023). https://doi.org/10.1080/19648189.2022.20 83022Mansouri, E.; Manfredi, M.; Hu, J.-W.: Environmentally friendly concrete compressive strength prediction using hybrid machine learning. Sustainability 14, 1–17 (2022). https://doi.org/10.3390/ su142012990Marks, M.; Glinicki, M.A.; Gibas, K.: Prediction of the chloride resistance of concrete modified with high calcium fly ash using machine learning. Materials 8, 8714–8727 (2015). https://doi.org/ 10.3390/ma8125483Najm, H.M.; Nanayakkara, O.; Ahmad, M.; Sabri Sabri, M.M.: Mechanical properties, crack width, and propagation of waste ceramic concrete subjected to elevated temperatures: a comprehensive study. Materials 15, 1–32 (2022). https://doi.org/10.3390/ ma15072371Tang, Y.X.; Lee, Y.H.; Amran, M.; Fediuk, R.; Vatin, N.; Kueh, A.B.H.; Lee, Y.Y.: Artificial neural network-forecasted compression strength of alkaline-activated slag concretes. Sustainability 14, 1–20 (2022). https://doi.org/10.3390/su14095214Shafigh, P.; Asadi, I.; Mahyuddin, N.B.: Concrete as a thermal mass material for building applications—A review. J. Build. Eng. 19, 14–25 (2018). https://doi.org/10.1016/j.jobe.2018.04.021Rocha Segundo, I.; Silva, L.; Palha, C.; Freitas, E.; Silva, H.: Surface rehabilitation of Portland cement concrete (PCC) pavements using single or double surface dressings with soft bitumen, conventional or modified emulsions. Constr. Build. Mater. 281, 1–15 (2021). https://doi.org/10.1016/j.conbuildmat.2021.122611Aquino Rocha, J.H.; Toledo Filho, R.D.: Microstructure, hydration process, and compressive strength assessment of ternary mixtures containing Portland cement, recycled concrete powder, and metakaolin. J. Clean. Prod. 434, 1–24 (2024). https://doi.org/10. 1016/j.jclepro.2023.140085Zou, Y.; Zheng, C.; Alzahrani, A.M.; Ahmad, W.; Ahmad, A.; Mohamed, A.M.; Khallaf, R.; Elattar, S.: Evaluation of artificial intelligence methods to estimate the compressive strength of geopolymers. Gels 8, 1–23 (2022). https://doi.org/10.3390/gels80 50271Shah, H.A.; Yuan, Q.; Akmal, U.; Shah, S.A.; Salmi, A.; Awad, Y.A.; Shah, L.A.; Iftikhar, Y.; Javed, M.H.; Khan, M.I.: Application of machine learning techniques for predicting compressive, splitting tensile, and flexural strengths of concrete with metakaolin. Materials 15, 1–36 (2022). https://doi.org/10.3390/ma15155435Silva, V.P.; Carvalho, R.D.; Rêgo, J.H.; Evangelista, F., Jr.: Machine learning-based prediction of the compressive strength of Brazilian concretes: a dual-dataset study. Materials 16, 1–16 (2023). https:// doi.org/10.3390/ma16144977FHWA. Long-Term Pavement Performance Information Management System User Guide. Fed. Highw. Adm. FHWA-HRT-2, 1–208 (2021)Karlaftis, A.G.; Badr, A.: Predicting asphalt pavement crack initiation following rehabilitation treatments. Transp. Res. Part C Emerg. Technol. 55, 510–517 (2015). https://doi.org/10.1016/j.trc.2015.03 .031Jia, Y.; Wang, S.; Huang, A.; Gao, Y.; Wang, J.; Zhou, W.: A comparative long-term effectiveness assessment of preventive maintenance treatments under various environmental conditions. Constr. Build. Mater. 273, 1–10 (2021). https://doi.org/10.1016/j. conbuildmat.2020.121717Yu, Y.; Sun, L.: Effect of overlay thickness, overlay material, and pre-overlay treatment on evolution of asphalt concrete overlay roughness in LTPP SPS-5 experiment: a multilevel model approach. Constr. Build. Mater. 162, 192–201 (2018). https://doi. org/10.1016/j.conbuildmat.2017.12.039Sollazzo, G.; Fwa, T.F.; Bosurgi, G.: An ANN model to correlate roughness and structural performance in asphalt pavements. Constr. Build. Mater. 134, 684–693 (2017). https://doi.org/10.1016/j.conb uildmat.2016.12.186Gong, H.; Sun, Y.; Shu, X.; Huang, B.: Use of random forests regression for predicting IRI of asphalt pavements. Constr. Build. Mater. 189, 890–897 (2018). https://doi.org/10.1016/j.conbuild mat.2018.09.017Gong, H.; Huang, B.; Shu, X.: Field performance evaluation of asphalt mixtures containing high percentage of RAP using LTPP data. Constr. Build. Mater. 176, 118–128 (2018). https://doi.org/ 10.1016/j.conbuildmat.2018.05.007Chen, X.; Dong, Q.; Zhu, H.; Huang, B.: Development of distress condition index of asphalt pavements using LTPP data through structural equation modeling. Transp. Res. Part C Emerg. Technol. 68, 58–69 (2016). https://doi.org/10.1016/j.trc.2016.03.011Gong, H.; Sun, Y.; Hu, W.; Polaczyk, P.A.; Huang, B.: Investigating impacts of asphalt mixture properties on pavement performance using LTPP data through random forests. Constr. Build. Mater. 204, 203–212 (2019). https://doi.org/10.1016/j.conbuildmat.2019. 01.198Rashidian-Dezfouli, H.; Rangaraju, P.R.: Evaluation of selected durability properties of portland cement concretes containing ground glass fiber as a pozzolan. Transp. Res. Rec. 2672, 88–98 (2018). https://doi.org/10.1177/0361198118773198Ogbodo, M.C.; Akpabot, A.I.: An assessment of some physical properties of different brands of cement in Nigeria. In: IOP Conference Series: Materials Science and Engineering, vol. 1048, pp. 1–5 (2021). https://doi.org/10.1088/1757-899X/1048/1/012013Zemri, C.; Bachir Bouiadjra, M.: Comparison between physical–mechanical properties of mortar made with Portland cement (CEMI) and slag cement (CEMIII) subjected to elevated temperature. Case Stud. Constr. Mater. 12, 1–12 (2020). https://doi.org/10. 1016/j.cscm.2020.e00339Latifoglu, L.; Ozger, M.: A novel approach for high-performance estimation of SPI data in drought prediction. Sustainability 15, 1–29 (2023). https://doi.org/10.3390/su151914046Anysz, H.; Zbiciak, A.; Ibadov, N.: The influence of input data standardization method on prediction accuracy of artificial neural networks. Procedia Eng. 153, 66–70 (2016). https://doi.org/10. 1016/j.proeng.2016.08.081Deo, R.C.; ¸Sahin, M.: Application of the Artificial Neural Network model for prediction of monthly Standardized Precipitation and Evapotranspiration Index using hydrometeorological parameters and climate indices in eastern Australia. Atmos. Res. 161–162, 65–81 (2015). https://doi.org/10.1016/j.atmosres.2015.03.018Chollet Ramampiandra, E.; Scheidegger, A.;Wydler, J.; Schuwirth, N.: A comparison of machine learning and statistical species distribution models: quantifying overfitting supports model interpretation. Ecol. Model. 481, 1–11 (2023). https://doi.org/10.1016/ j.ecolmodel.2023.110353Ookura, S.; Mori, H.: An efficient method for wind power generation forecasting by LSTM in consideration of overfitting prevention. IFAC Pap. 53, 12169–12174 (2020). https://doi.org/10.1016/ j.ifacol.2020.12.1008Piotrowski, A.P.; Napiorkowski, J.J.: A comparison of methods to avoid overfitting in neural networks training in the case of catchment runoff modelling. J. Hydrol. 476, 97–111 (2013). https://doi. org/10.1016/j.jhydrol.2012.10.019Bahtiyar, H.; Soydaner, D.; Yüksel, E.: Application of multilayer perceptron with data augmentation in nuclear physics. Appl. Soft Comput. 128, 1–9 (2022). https://doi.org/10.1016/j.asoc.2022.10 9470Min, R.; Wang, Z.; Zhuang, Y.; Yi, X.: Application of semisupervised convolutional neural network regression model based on data augmentation and process spectral labeling in Raman predictive modeling of cell culture processes. Biochem. Eng. J. 191, 1–9 (2023). https://doi.org/10.1016/j.bej.2022.108774Hao, R.; Zheng, H.; Yang, X.: Data augmentation based estimation for the censored composite quantile regression neural network model. Appl. Soft Comput. 127, 1–11 (2022). https://doi.org/10. 1016/j.asoc.2022.109381Demir, S.; Mincev, K.; Kok, K.; Paterakis, N.G.: Data augmentation for time series regression: applying transformations, autoencoders and adversarial networks to electricity price forecasting. Appl. Energy 304, 1–19 (2021). https://doi.org/10.1016/j.apenergy.2021. 117695Hao, R.; Weng, C.; Liu, X.; Yang, X.: Data augmentation based estimation for the censored quantile regression neural network model. Expert Syst. Appl. 214, 1–15 (2023). https://doi.org/10. 1016/j.eswa.2022.119097Shorten, C.; Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6, 1–48 (2019). https://doi.org/ 10.1186/s40537-019-0197-0Berrett, C.; Calder, C.A.: Data augmentation strategies for the Bayesian spatial probit regression model. Comput. Stat. Data Anal. 56, 478–490 (2012). https://doi.org/10.1016/j.csda.2011.08.020Mazzoleni, M.; Breschi, V.; Formentin, S.: Piecewise nonlinear regression with data augmentation. IFAC Pap. 54, 421–426 (2021). https://doi.org/10.1016/j.ifacol.2021.08.396Polo-Mendoza, R.; Martinez-Arguelles, G.; Peñabaena-Niebles, R.; Covilla-Valera, E.: Neural networks implementation for the environmental optimisation of the recycled concrete aggregate inclusion in warm mix asphalt. Road Mater. Pavement Des. (2023). https://doi.org/10.1080/14680629.2023.2230298Himmeto ˘glu, S.; Delice, Y.; Aydo ˘gan, E.K.; Uzal, B.: Green building envelope designs in different climate and seismic zones: multi-objective ANN-based genetic algorithm. Sustain. Energy Technol. Assess. 53, 1–17 (2022). https://doi.org/10.1016/j.seta. 2022.102505Minh, D.; Wang, H.X.; Li, Y.F.; Nguyen, T.N.: Explainable artificial intelligence: a comprehensive review. Artif. Intell. Rev. 55, 3503–3568 (2022). https://doi.org/10.1007/s10462-021-10088-yPolo-Mendoza, R.; Martinez-Arguelles, G.; Peñabaena-Niebles, R.: A multi-objective optimization based on genetic algorithms for the sustainable design of Warm Mix Asphalt (WMA). Int. J. Pavement Eng. 24, 2074417 (2023). https://doi.org/10.1080/1029 8436.2022.2074417Białek, J.; Bujalski, W.; Wojdan, K.; Guzek, M.; Kurek, T.: Dataset level explanation of heat demand forecasting ANN with SHAP. Energy 261, 1–12 (2022). https://doi.org/10.1016/j.energy.2022.12 5075Polo-Mendoza, R.; Duque, J.; Mašín, D.; Turbay, E.; Acosta, C.: Implementation of deep neural networks and statistical methods to predict the resilient modulus of soils. Int. J. Pavement Eng. 24, 2257852 (2023). https://doi.org/10.1080/10298436.2023.2257852Hamim, A.; Yusoff, N.I.M.; Omar, H.A.; Jamaludin, N.A.A.; Hassan, N.A.; El-Shafie, A.; Ceylan, H.: Integrated finite element and artificial neural network methods for constructing asphalt concrete dynamic modulus master curve using deflection time-history data. Constr. Build. Mater. 257, 1–14 (2020). https://doi.org/10.1016/j. conbuildmat.2020.119549Polo-Mendoza, R.; Martinez-Arguelles, G.; Peñabaena-Niebles, R.: Environmental optimization of warm mix asphalt (WMA) design with recycled concrete aggregates (RCA) inclusion through artificial intelligence (AI) techniques. Res. Eng. 17, 1–15 (2023). https://doi.org/10.1016/j.rineng.2023.100984Zdravkovi´c, S.; Kavitha, L.; Satari´c, M.V.; Zekovi´c, S.; Petrovi´c, J.: Modified extended tanh-function method and nonlinear dynamics of microtubules. Chaos Solitons Fractals 45, 1378–1386 (2012). https://doi.org/10.1016/j.chaos.2012.07.009Wuraola, A.; Patel, N.: Resource efficient activation functions for neural network accelerators. Neurocomputing 482, 163–185 (2022)Liu, K.; Shi,W.; Huang, C.; Zeng, D.: Cost effective Tanh activation function circuits based on fast piecewise linear logic. Microelectron. J. 138, 1–9 (2023). https://doi.org/10.1016/j.mejo.2023.10 5821Kingma, D.P.; Ba, J.L.: Amax: a method for stochastic optimization. In: 3rd International Conference on Learning Representations (ICLR), pp. 1–15 (2015)Pandi Chandran, P.; Hema Rajini, N.; Jeyakarthic, M.: Optimal deep belief network enabled malware detection and classification model. Intell. Autom. Soft Comput. (2023). https://doi.org/10.32 604/iasc.2023.029946Obayya, M.; Maashi, M.S.; Nemri, N.; Mohsen, H.; Motwakel, A.; Osman, A.E.; Alneil, A.A.; Alsaid, M.I.: Hyperparameter optimizer with deep learning-based decision-support systems for histopathological breast cancer diagnosis. Cancers 15, 1–19 (2023). https://doi.org/10.3390/cancers15030885Sadykov, M.; Haines, S.; Broadmeadow, M.; Walker, G.; Holmes, D.W.: Practical evaluation of lithium-ion battery state-of-charge estimation using time-series machine learning for electric vehicles. Energies 16, 1–34 (2023). https://doi.org/10.3390/en16041628Zhang, S.; Lei, H.; Zhou, Z.; Wang, G.; Qiu, B.: Fatigue life analysis of high-strength bolts based on machine learning method and SHapley Additive exPlanations (SHAP) approach. Structures 51, 275–287 (2023). https://doi.org/10.1016/j.istruc.2023.03.060Nicolson, A.; Paliwal, K.K.: Deep learning for minimum meansquare error approaches to speech enhancement. Speech Commun. 111, 44–55 (2019). https://doi.org/10.1016/j.specom.2019.06.002Koya, B.P.; Aneja, S.; Gupta, R.; Valeo, C.: Comparative analysis of different machine learning algorithms to predict mechanical properties of concrete. Mech. Adv. Mater. Struct. 29, 4032–4043 (2022). https://doi.org/10.1080/15376494.2021.1917021Vilares Ferro, M.; Doval Mosquera, Y.; Ribadas Pena, F.J.; Darriba Bilbao, V.M.: Early stopping by correlating online indicators in neural networks. Neural Netw. 159, 109–124 (2023). https://doi. org/10.1016/j.neunet.2022.11.035Zeng, J.; Zhang, M.; Lin, S.-B.: Fully corrective gradient boosting with squared hinge: fast learning rates and early stopping. Neural Netw. 147, 136–151 (2022). https://doi.org/10.1016/j.neunet.2021. 12.016Singh, V.; Pencina, M.; Einstein, A.J.; Liang, J.X.; Berman, D.S.; Slomka, P.: Impact of train/test sample regimen on performance estimate stability of machine learning in cardiovascular imaging. Sci. Rep. 11, 1–8 (2021). https://doi.org/10.1038/s41598-021-93 651-5Xu, Y.; Goodacre, R.: On splitting training and validation set: a comparative study of cross-validation, bootstrap and systematic sampling for estimating the generalization performance of supervised learning. J. Anal. Test. 2, 249–262 (2018). https://doi.org/10. 1007/s41664-018-0068-2Quinn, T.P.; Le, V.; Cardilini, A.P.A.: Test set verification is an essential step in model building. Methods Ecol. Evol. 12, 127–129 (2021). https://doi.org/10.1111/2041-210X.13495Straub, J.: Machine learning performance validation and training using a ‘perfect’ expert system. MethodsX 8, 1–6 (2021). https:// doi.org/10.1016/j.mex.2021.101477Polo-Mendoza, R.; Duque, J.; Mašín, D.: Prediction of California bearing ratio and modified proctor parameters using deep neural networks and multiple linear regression: a case study of granular soils. Case Stud. Constr. Mater. 20, 1–17 (2024). https://doi.org/ 10.1016/j.cscm.2023.e02800Li, Z.: Extracting spatial effects from machine learning model using local interpretation method: an example of SHAP and XGBoost. Comput. Environ. Urban Syst. 96, 1–18 (2022). https://doi.org/10. 1016/j.compenvurbsys.2022.101845Kim, Y.; Kim, Y.: Explainable heat-related mortality with random forest and SHapley Additive exPlanations (SHAP) models. Sustain. Cities Soc. 79, 1–15 (2022). https://doi.org/10.1016/j.scs.2022.10 3677Lin, K.; Gao, Y.: Model interpretability of financial fraud detection by group SHAP. Expert Syst. Appl. 210, 1–9 (2022). https://doi. org/10.1016/j.eswa.2022.118354Kashifi, M.T.: Investigating two-wheelers risk factors for severe crashes using an interpretable machine learning approach and SHAP analysis. IATSS Res. 47, 357–371 (2023). https://doi.org/ 10.1016/j.iatssr.2023.07.005Meng, Y.; Yang, N.; Qian, Z.; Zhang, G.: What makes an online review more helpful: an interpretation framework using XGBoost and SHAP values. J. Theor. Appl. Electron. Commer. Res. 16, 466–490 (2021). https://doi.org/10.3390/jtaer16030029Scavuzzo, C.M.; Scavuzzo, J.M.; Campero, M.N.; Anegagrie, M.; Aramendia, A.A.; Benito, A.; Periago, V.: Feature importance: opening a soil-transmitted helminth machine learning model via SHAP. Infect. Dis. Model. 7, 262–276 (2022). https://doi.org/10. 1016/j.idm.2022.01.004Tang, Y.; Wang, C.: Performance modeling on DaVinci AI core. J. Parallel Distrib. Comput. 175, 134–149 (2023). https://doi.org/10. 1016/j.jpdc.2023.01.008Dube, P.; Suk, T.; Wang, C.: AI gauge: runtime estimation for deep learning in the cloud. In: 31st International Symposium on Computer Architecture and High Performance Computing (SBACPAD), pp. 160–167 (2019)Aghapour, Z.; Sharifian, S.; Taheri, H.: Task offloading and resource allocation algorithm based on deep reinforcement learning for distributed AI execution tasks in IoT edge computing environments. Comput. Netw. 223, 1–17 (2023). https://doi.org/10.1016/ j.comnet.2023.109577Assaf, A.M.; Haron, H.; Hamed, H.N.A.H.; Ghaleb, F.A.; Dalam, M.E.; Eisa, T.A.E.: Improving solar radiation forecasting utilizing data augmentation model generative adversarial networks with convolutional support vector machine (GAN-CSVR). Appl. Sci. 13, 1–23 (2023). https://doi.org/10.3390/app132312768Harrou, F.; Dairi, A.; Dorbane, A.; Sun, Y.: Energy consumption prediction in water treatment plants using deep learning with data augmentation. Res. Eng. 20, 1–14 (2023). https://doi.org/10.1016/ j.rineng.2023.101428Liu, K.-H.; Xie, T.-Y.; Cai, Z.-K.; Chen, G.-M.; Zhao, X.-Y.: Datadriven prediction and optimization of axial compressive strength for FRP-reinforced CFST columns using synthetic data augmentation. Eng. Struct. 300, 1–16 (2024). https://doi.org/10.1016/j.engs truct.2023.117225Mumuni, A.; Mumuni, F.: Data augmentation: a comprehensive survey of modern approaches. Array 16, 1–27 (2022). https://doi. org/10.1016/j.array.2022.100258Maharana, K.; Mondal, S.; Nemade, B.: A review: data preprocessing and data augmentation techniques. Glob. Transitions Proc. 3, 91–99 (2022). https://doi.org/10.1016/j.gltp.2022.04.020Walubita, L.F.; Martinez-Arguelles, G.; Polo-Mendoza, R.; IckLee, S.; Fuentes, L.: Comparative environmental assessment of rigid, flexible, and perpetual pavement: a case study of Texas. Sustainability 14, 1–22 (2022). https://doi.org/10.3390/su14169983Gupta, S.; Chaudhary, S.: State of the art review on supplementary cementitious materials in India—II: characteristics of SCMs, effect on concrete and environmental impact. J. Clean. Prod. 357, 1–19 (2022). https://doi.org/10.1016/j.jclepro.2022.131945Sharma, R.K.; Singh, D.; Dasaka, S.M.: Investigating supplementary cementitious materials’ effects on stabilized aggregate performance, behaviour, and design aspects. Constr. Build. Mater. 411, 1–16 (2024). https://doi.org/10.1016/j.conbuildmat.2023.13 456414365143511049Computational modellingConcrete structuresConstruction materialsDeep neural networksMachine learningPortland cement concretePublicationORIGINALDevelopment of a Machine Learning (ML)-Based Computational Model.pdfDevelopment of a Machine Learning (ML)-Based Computational Model.pdfapplication/pdf2763682https://repositorio.cuc.edu.co/bitstreams/640afd64-f03c-4432-8110-0b128dee2e56/download79594e959ef1498796741ba97faf792aMD51LICENSElicense.txtlicense.txttext/plain; charset=utf-815543https://repositorio.cuc.edu.co/bitstreams/8cf055cf-ed8d-4c7b-8f2c-67b2c2294da4/download73a5432e0b76442b22b026844140d683MD52TEXTDevelopment of a Machine Learning (ML)-Based Computational Model.pdf.txtDevelopment of a Machine Learning (ML)-Based Computational Model.pdf.txtExtracted texttext/plain59311https://repositorio.cuc.edu.co/bitstreams/9d705359-a8b8-47cf-941c-34b11dd4c562/downloadbcd06dbcaa28451dcd13a9358418e60eMD53THUMBNAILDevelopment of a Machine Learning (ML)-Based Computational Model.pdf.jpgDevelopment of a Machine Learning (ML)-Based Computational Model.pdf.jpgGenerated Thumbnailimage/jpeg15392https://repositorio.cuc.edu.co/bitstreams/7fab4be2-3787-4eed-8146-d6507fe868ea/downloadb32a28d234a79b8dbeaeb806a370cf9bMD5411323/13827oai:repositorio.cuc.edu.co:11323/138272024-11-26 04:00:33.545https://creativecommons.org/licenses/by/4.0/© The Author(s) 2024.open.accesshttps://repositorio.cuc.edu.coRepositorio de la Universidad de la Costa CUCrepdigital@cuc.edu.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