In this study, gene expressionprogramming (GEP) and multi gene expressionprogramming (MEP) are utilized to formulate new prediction models for determining the compaction parameters (rho(dmax) and wopt) of expansive ...
详细信息
In this study, gene expressionprogramming (GEP) and multi gene expressionprogramming (MEP) are utilized to formulate new prediction models for determining the compaction parameters (rho(dmax) and wopt) of expansive soils. A total of 195 datasets with five input parameters (i.e., clay fraction C-F, plastic limit w(P), plasticity index IP, specific gravity Gs, maximum dry density rho(dmax)), and two output *** and wopt are collected from the literature comprising 119 internationally published research articles to develop the GEP and MEP models. Simplified mathematical expressions were derived for these models to determine the rho(dmax) and w(opt) of expansive soils. The performance of the models was tested using mean absolute error (MAE), root mean square error (RMSE), Nash-Sutcliffe efficiency (NSE), and correlation coefficient (R). Sensitivity and parametric analyses were also performed on the GEP and MEP models. Additionally, external validation of the models was also verified using commonly recognized statistical criteria. It is clear from the results that the GEP and MEP methods accurately characterize the compaction characteristics of expansive soils resulting in reasonable prediction performance, however, GEP model yielded relatively better performance. Also, the proposed predictive models were compared with previously available empirical models and they exhibited robust and superior performance. Moreover, the rho(dmax) model provided significantly improved results as compared to the w(opt) prediction model in the case of GEP, and vice versa in the MEP model. It is therefore recommended that the proposed GP based models can reliably be used for determining the compaction parameters of expansive soils which effectively reduces the time-consuming and laborious testing, hence attaining sustainability in the field of geoenvironmental engineering.
Intelligence is strongly related to the ability of solving different problems by a single system. General problems solvers such as Artificial Neural Networks, Evolutionary Algorithms, Particle Swarm etc, have traditio...
详细信息
ISBN:
(纸本)9781595931085
Intelligence is strongly related to the ability of solving different problems by a single system. General problems solvers such as Artificial Neural Networks, Evolutionary Algorithms, Particle Swarm etc, have traditionally been tested against one problem at one time. The purpose of this research is to build a complex and adaptive system able to solve multiple (and different) problems. The proposed system, called A-Brain, consists of several connected components (a Decision Maker, a Trainer and several Problem Solvers) which provide a base for building complex problem solvers. The A-Brain system is applied for solving some well-known problems in the field of symbolic regression. Numerical experiments show that A-Brain system is able to perform very well on the considered test problems.
This data article presents information on the measurement of Indirect Tensile Stiffness Modulus of laboratory and field asphalt mixtures. The asphalt mixes are composed of three distinct binders that were categorised ...
详细信息
This data article presents information on the measurement of Indirect Tensile Stiffness Modulus of laboratory and field asphalt mixtures. The asphalt mixes are composed of three distinct binders that were categorised by their penetration grade (40/55-TLA, 60/75-TLA, and 60/70-MB) and aggregates (limestone, sharp sand, and filler). The asphalt mixtures are called dense-graded hot mix asphalt (HMA) and gap-graded stone matrix asphalt (SMA). The variables in the dataset were selected in accordance with the specifications of the dynamic modulus models that are currently in use as well as the needs for the quality control and assurance (QC & QA) assessment of asphalt concrete mixes. The data parameters included are temperature, asphalt content, and binder viscosity, air void content, cumulative percent retained on 19, 12.5, and 4.75 mm sieves, maximum theoretical specific gravity, aggregate passing #200 sieve, effective asphalt content, density, flow, marshal stability, coarse-to-fine particle ratio and the Indirect Tensile Stiffness Modulus (ITSM). Utilising soft computing techniques, models were developed utilising the data thus eliminating the requirement for complex and timeconsuming laboratory testing.
暂无评论