journal article·2023-07Open access

Mechanical behaviour of E-waste aggregate concrete using a novel machine learning algorithm: Multi expression programming (MEP)

Sultan Shah, Moustafa Houda, Sangeen Khan, Fadi Althoey, Maher Abuhussain, Mohammed Awad Abuhussain, Mujahid Ali, Abdulaziz Alaskar, Muhammad Faisal Javed

Abstract

Technological advancement encourages the usage of electronic appliances in daily life and makes it possible for users to switch to more advanced devices very easily and at a reasonable cost. As new devices are produced and manufactured at an alarming rate around the world, outdated old devices become e-waste. This research work aims at using a popular machine learning (ML) method known as multi-expression programming (MEP) to examine the compressive strength (CS) and tensile strength (TS) of E-waste aggregate-based concrete (EWAC). 279 and 105 scientific entries for CS and TS, respectively, were culled from reputable literature. The ten convincing input parameters selected based on multicollinearity analysis (correlation matrix and variance inflation factor) were E-waste coarse aggregate (ECA%), E-waste fine aggregate (EFA%), water-cement ratio (w/c), age of concrete (A in days), fine aggregate water-absorption (WAF%), coarse aggregate water-absorption (WAC%), E-waste aggregate water-absorption (WAE%), E-waste aggregate specific-gravity (SGE), coarse aggregate specific-gravity (SGC), and fine aggregate specific-gravity (SGF). To estimate the functioning of the projected models, root-squared-error (RSE), mean-absolute error (MAE), mean-absolute-percent error (MAPE), Nash-Sutcliffe-efficiency (NSE), root-mean-squared error (RMSE), objective-function (OF), coefficient-of-correlation (R), root-mean-squared-logarithmic error (RMSLE), and performance-index (PI) were used. The R-value for both MEP models exceeds 0.9, showing “excellent” with MAPE values in the testing stage equals to 6.68% and 6.78% for the CS-MEP and TS-MEP models, respectively. While for non-linear regression (NLR) models, the MAPE exceeds 20% and 30%, respectively, making them unsuitable for future prediction. Moreover, the sensitivity analysis carried out to evaluate the MEP equations' consistency with the observed physical phenomena, indicates that for both CS and TS, the w/c, ECA%, and EFA% remain the most sensitive parameters with a sensitivity index greater than 0.60. Due to the accuracy and viability of developed models, they can be used to reduce the time needed for laborious laboratory tests.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Recycled Aggregate Concrete Performance · Innovations in Concrete and Construction Materials · Innovative concrete reinforcement materials

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (100+)

Show source-provided references
1. A comparative study on the practical utilization of iron tailings as a complete replacement of normal aggregates in dam concrete with different gradation10.1016/j.jclepro.2018.11.107 ↗
2. Characterization of concrete composites with recycled plastic aggregates from postconsumer material streams10.1016/j.conbuildmat.2018.06.083 ↗
3. Prospects for a saturation of humanity's resource use? An analysis of material stocks and flows in nine world regions from 1900 to 203510.1016/j.gloenvcha.2021.102410 ↗
4. Embodied energy and carbon emissions of building materials in China10.1016/j.buildenv.2021.108434 ↗
5. Performance and optimisation study of waste plastic aggregate based sustainable concrete–A machine learning approach10.1016/j.clwas.2022.100014 ↗
6. Physical, chemical and mineralogical properties of fine recycled aggregates made from concrete waste10.1016/j.conbuildmat.2015.03.112 ↗
7. Formulation of estimation models for the compressive strength of concrete mixed with nanosilica and carbon nanotubes10.1016/j.dibe.2022.100113 ↗
8. Comparative study of evolutionary artificial intelligence approaches to predict the rheological properties of fresh concrete
9. Global E-waste: unintended consequences of marketing strategies necessitates A plan for change
10. Inconsistencies of e-waste management in developing nations–Facts and plausible solutions10.1016/j.jenvman.2020.110234 ↗
11. Towards the effective E-waste management in Bangladesh: a review10.1007/s11356-018-3626-2 ↗
12. Evolutionary artificial intelligence approach for performance prediction of bio-composites10.1016/j.conbuildmat.2021.123254 ↗
13. Genetic programming in civil engineering: advent, applications and future trends10.1007/s10462-020-09894-7 ↗
14. Past, present and perspective methodology for groundwater modeling-based machine learning approaches10.1007/s11831-022-09715-w ↗
15. Roles of artificial intelligence in construction engineering and management: a critical review and future trends10.1016/j.autcon.2020.103517 ↗
16. Investigating photovoltaic solar power output forecasting using machine learning algorithms10.1080/19942060.2022.2126528 ↗
17. Evaluating urban flood risk using hybrid method of TOPSIS and machine learning10.1016/j.ijdrr.2021.102614 ↗
18. Towards an ensemble machine learning model of random subspace based functional tree classifier for snow avalanche susceptibility mapping10.1109/ACCESS.2020.3014816 ↗
19. Review of nitrogen compounds prediction in water bodies using artificial neural networks and other models10.3390/su12114359 ↗
20. A review of the hybrid artificial intelligence and optimization modelling of hydrological streamflow forecasting10.1016/j.aej.2021.04.100 ↗
21. Prediction of compression index of fine-grained soils using a gene expression programming model10.3390/infrastructures4020026 ↗
22. New prediction model for the ultimate axial capacity of concrete-filled steel tubes: an evolutionary approach10.3390/cryst10090741 ↗
23. Prediction of compressive strength of rice husk ash concrete through different machine learning processes10.3390/cryst11040352 ↗
24. Estimating CO2-Brine diffusivity using hybrid models of ANFIS and evolutionary algorithms10.1080/19942060.2020.1774422 ↗
25. ANFIS pattern for molecular membranes separation optimization10.1016/j.molliq.2018.11.017 ↗
26. A water cycle-based error minimization technique in predicting the bearing capacity of shallow foundation10.1007/s00366-021-01289-8 ↗
27. Agricultural risk management using fuzzy TOPSIS analytical hierarchy process (AHP) and failure mode and effects analysis (FMEA)10.3390/agriculture10110504 ↗
28. Prediction of compressive and splitting tensile strength of concrete with fly ash by using gene expression programming10.1002/suco.202100213 ↗
29. Inclusive multiple model using hybrid artificial neural networks for predicting evaporation10.3389/fenvs.2021.789995 ↗
30. Predicting the parameters of vortex bladeless wind turbine using deep learning method of long short-term memory10.3390/en14164867 ↗
31. Comprehensive review of deep reinforcement learning methods and applications in economics10.3390/math8101640 ↗
32. Groundwater salinity susceptibility mapping using classifier ensemble and Bayesian machine learning models10.1109/ACCESS.2020.3014908 ↗
33. New prediction models for the compressive strength and dry-thermal conductivity of bio-composites using novel machine learning algorithms10.1016/j.jclepro.2022.131364 ↗
34. Prediction models for marshall mix parameters using bio-inspired genetic programming and deep machine learning approaches: a comparative study
35. Indirect estimation of swelling pressure of expansive soil: GEP versus MEP modelling10.1155/2023/1827117 ↗
36. Numerical modeling of concrete strength under multiaxial confinement pressures using linear genetic programming10.1016/j.autcon.2013.08.016 ↗
37. Predviđanje tlačne čvrstoće betona pomoću umjetnih neuronskih mreža
38. Prediction of the compressive strength of normal and high-performance concretes using M5P model tree algorithm10.1016/j.conbuildmat.2017.03.061 ↗
39. A new predictive model for compressive strength of HPC using gene expression programming10.1016/j.advengsoft.2011.09.014 ↗
40. Compressive strength estimation of fly ash/slag based green concrete by deploying artificial intelligence models10.3390/ma15103722 ↗
41. High performance concrete compressive strength forecasting using ensemble models based on discrete wavelet transform10.1016/j.engappai.2012.10.014 ↗
42. Machine learning-based compressive strength prediction for concrete: an adaptive boosting approach10.1016/j.conbuildmat.2019.117000 ↗
43. Compressive strength prediction of high-performance concrete using gradient tree boosting machine10.1016/j.conbuildmat.2020.120198 ↗
44. Forecasting strength of CFRP confined concrete using multi expression programming10.3390/ma14237134 ↗
45. Sustainable use of fly-ash: use of gene-expression programming (GEP) and multi-expression programming (MEP) for forecasting the compressive strength geopolymer concrete10.1016/j.asej.2021.03.018 ↗
46. Forecasting compressive strength of RHA based concrete using multi-expression programming10.3390/ma15113808 ↗
47. Performance evaluation of soft computing for modeling the strength properties of waste substitute green concrete10.3390/su13052867 ↗
48. A comparative study for the prediction of the compressive strength of self-compacting concrete modified with fly ash10.3390/ma14174934 ↗
49. Data-driven compressive strength prediction of fly ash concrete using ensemble learner algorithms10.3390/buildings12020132 ↗
50. Microstructure and chemical characterizations with soft computing models to evaluate the influence of calcium oxide and silicon dioxide in the fly ash and cement kiln dust on the compressive strength of cement mortar, Resources
51. Analysis and prediction of the effect of Nanosilica on the compressive strength of concrete with different mix proportions and specimen sizes using various numerical approaches10.1002/suco.202200718 ↗
52. Predicting modulus elasticity of recycled aggregate concrete using M5′ model tree algorithm10.1016/j.conbuildmat.2015.06.055 ↗
53. New design equations for elastic modulus of concrete using multi expression programming10.3846/13923730.2014.893910 ↗
54. Prediction of self-compacting concrete elastic modulus using two symbolic regression techniques10.1016/j.autcon.2015.12.026 ↗
55. Computational AI models for investigating the radiation shielding potential of high-density concrete10.3390/ma15134573 ↗
56. Evaluate and predict the resist electric current and compressive strength of concrete modified with GGBS and steelmaking slag using mathematical models10.1007/s40831-022-00631-8 ↗
57. Modeling the impact of liquid polymers on concrete stability in terms of a slump and compressive strength10.3390/app13021208 ↗
58. Sustainable utilization of foundry waste: forecasting mechanical properties of foundry sand based concrete using multi-expression programming10.1016/j.scitotenv.2021.146524 ↗
59. A multi expression programming application to high performance concrete
60. A multi-model approach to analysis of environmental phenomena10.1016/j.envsoft.2005.12.026 ↗
61. Recent advances and future challenges for artificial neural systems in geotechnical engineering applications
62. Prediction of compression index of fine-grained soils using a gene expression programming model10.3390/infrastructures4020026 ↗
63. An ensemble genetic programming model for seasonal precipitation forecasting
64. Genetic programming as a means for programming computers by natural selection10.1007/BF00175355 ↗
65. Genetic programming model for estimating soil suction in shallow soil layers in the vicinity of a tree10.1016/j.enggeo.2020.105506 ↗
66. Using artificial neural network and genetics algorithm to estimate the resilient modulus for stabilized subgrade and propose new empirical formula10.1016/j.trgeo.2020.100358 ↗
67. Ferreira · 2006 · Vol. 21
68. Gene Expression Programming as a data classification tool. A review
69. A comparison of several linear genetic programming techniques10.25088/ComplexSystems.14.4.285 ↗
70. Multi expression programming
71. Development of applicable design models for concrete columns confined with aramid fiber reinforced polymer using Multi-Expression Programming, Structures
72. Sustainable use of fly-ash: Use of gene-expression programming (GEP) and multi-expression programming (MEP) for forecasting the compressive strength geopolymer concrete10.1016/j.asej.2021.03.018 ↗
73. D.E. Goldberg, Genetic algorithms, Pearson Education India2006.
74. Sustainable use of chemically modified tyre rubber in concrete: machine learning based novel predictive model
75. Design equations for prediction of pressuremeter soil deformation moduli utilizing expression programming systems10.1007/s00521-012-1144-6 ↗
76. Partial replacement of E-plastic waste as coarse-aggregate in concrete10.1016/j.proenv.2016.07.079 ↗
77. Utilization of E-waste as a partial replacement of coarse aggregate in concrete
78. Amalgamation of E-waste plastics in concrete with super plasticizer for better strength10.1016/j.matpr.2019.11.253 ↗
79. A review of maintenance management models: application for the clinic and hospital environment
80. An experimental study on concrete by using E-waste as partial replacement for course aggregate
81. Use of e-plastic waste in concrete as a partial replacement of coarse mineral aggregate
82. Determination of strength characteristics of concrete by partial replacement of aggregates with e waste and hdpe granules
83. An overview of electronic waste as aggregate in concrete
84. Zarbade · Evolution of concrete using recycled aggregate, coconut shells and E-waste as a coarse aggregate · 2015
85. Lakshmi · Investigations on durability characteristics of E-plastic waste incorporated concrete · 2011
86. Use of Non-Metallic e-waste as a coarse aggregate in a concrete10.15623/ijret.2015.0403040 ↗
87. Development of ecofriendly concrete incorporating recycled high-impact polystyrene from hazardous electronic waste10.1061/(ASCE)HZ.2153-5515.0000265 ↗
88. Performance study about ductility behaviour in electronic waste concrete10.1016/j.matpr.2020.07.049 ↗
89. A study on partial replacement of fine aggregate with E-waste (NMPCB) in eco-friendly PCC concrete
90. An experimental study on the mechanical and durability properties assessment of E-waste concrete
91. Experimental study on the properties of green concrete by replacement of e-plastic waste as aggregate10.1016/j.procs.2020.05.145 ↗
92. Performance of recycled E-waste as aggregates in green concrete
93. Re-cycle of E-waste in concrete by partial replacement of coarse aggregate10.26480/gwk.01.2019.05.08 ↗
94. Selvam · Experimental investigation on partial replacement of E-waste as coarse aggregate in concrete · 2020
95. S. Prashant, M. Kumar, Effect of partial replacement of coarse aggregates with e-waste on strength properties of concrete, Sustainable Construction and Building Materials, Springer2019, pp. 555-560.10.1007/978-981-13-3317-0_48 ↗
96. V. Srivastava, A. Singh, Utilisation of E-waste in concrete-an experimental investigation.
97. An experimental study on properties of concrete produced with M-sand and E-sand10.1016/j.matpr.2020.08.086 ↗
98. Experimental investigation on concrete with E-waste-A way to minimize solid waste deposition
99. An experimental study on e-waste concrete10.17485/ijst/2016/v9i2/86345 ↗
100. Utilization of waste printed circuit board powder in concrete over conventional concrete10.1016/j.matpr.2020.11.161 ↗