Gene Expression Programming Method Research Articles

Predicting the compaction characteristics of expansive soils using two genetic programming-based algorithms

In this study, gene expression programming (GEP) and multi gene expression programming (MEP) are utilized to formulate new prediction models for determining the compaction parameters (ρdmax and wopt) of expansive soils. A total of 195 datasets with five input parameters (i.e., clay fraction CF, plastic limit wP, plasticity index IP, specific gravity Gs, maximum dry density ρdmax), and two output variables ρdmax 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 ρdmax and wopt 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 ρdmax model provided significantly improved results as compared to the wopt 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 geo-environmental engineering.

Evaluation of Accuracy of Hybrid Model of Gene Expression Planning - Fuzzy Logic in Estimation of Land Subsidence Risk

Land subsidence is a nonlinear and complex process that data-driven computational intelligence models can model it. In this study, the accuracy and efficiency of hybrid fuzzy logic gene expression planning hybrid model in estimating land subsidence risk and its factors in Varamin aquifer standardized. For this purpose, after selecting and gathering information from 15 factors affecting the subsidence event based on research records in the GIS environment, they were first standardized by fuzzy membership functions and then gene expression programming method was used to integrate the layers. Finally, using seven important statistical benchmarks based on radar image data, the model was validated in 4 different scenarios in input data and operators. The results showed scenario 1 with input parameters of bedrock level, Debi of pumping wells, groundwater drawdown, geology and operators, +, - ×, ÷, sqr, exp, Ln, ^ 2, ^ 3,3Rt, sin, cos, Atan, is the best model in training and testing. Accordingly, the groundwater drawdown parameter had the highest effect on land subsidence in the study area.

Experimental investigation and prediction of compressive strength of high-strength concrete containing waste ceramic powder using gene expression programming

The high volume of carbon dioxide produced in cement plants and the feasibility of reusing waste materials from factories in recent years has become one of the main concerns of research centers and environmental associations. Therefore, the main purpose of this research is to evaluate the feasibility of reusing waste materials with a focus on waste ceramic powder (WCP), as a semi-active aluminosilicate material that can be replaced as a percentage of cement used in concrete. WCP, in addition to activating the potential of using a waste material in concrete, can also reduce cement consumption. Therefore, in this research, cement replacement percentages between 0 and 50% in three water to cement ratios of 0.3, 0.4 and 0.5 in 24 concrete mixtures have been used to perform compressive strength tests. In order to provide a usable computational model, the gene expression programming (GEP) method has been used to predict the compressive strength of the samples. The results of experimental research indicate that in the ratio of water to cement 0.3 at the age of 90 days, the sample containing 20% of WCP has reached a compressive strength of 72.57 MPa. This result is almost equal to the control sample and therefore the use of this percentage is recommended for this ratio of water to cementitious materials. Finally, the results indicate the very good performance of the GEP method by increasing the number of chromosomes and increasing the correlation coefficient between experimental and numerical data up to 98%. Therefore, the GEP method has a significant advantage over other methods by providing an analytical relationship and high accuracy.

Dam failure peak outflow prediction through GEP-SVM meta models and uncertainty analysis

Abstract Accurate prediction of a breached dam's peak outflow is a significant factor for flood risk analysis. In this study, the capability of Support Vector Machine and Kernel Extreme Learning Machine as kernel-based approaches and Gene Expression Programming method was assessed in breached dam peak outflow prediction. Two types of modeling were considered. First, only dam reservoir height and volume at the failure time were used as the input combinations (state 1). Then, soil characteristics were added to input combinations to investigate particularly the impact of soil characteristics (state 2). Results showed that the use of only soil characteristics did not lead to a desired accuracy; however, adding soil characteristics to input combinations (state 2) improved the models' accuracy up to 40%. The outcome of the applied models was also compared with existing empirical equations and it was found the applied models yielded better results. Sensitivity analysis results showed that dam height had the most important role in the peak outflow prediction, while the strength parameters did not have significant impacts. Furthermore, for assessing the best-applied model dependability, uncertainty analysis was used and the results indicated that the SVM model had an allowable degree of uncertainty in peak outflow modelling.

QSAR Studies on the IC50 of a Class of Thiazolidinone/Thiazolide Based Hybrids as Antitrypanosomal Agents

Background:: Trypanosomiasis is a widespread zoonotic disease and the existing drugs are not enough to prevent and treat it. Objective:: This study aimed to build a quantitative structure-activity relationship model by the chemical structures of a class of thiazolidone/thiazolidamide based hybrids. The model was used to screen new antitrypanosomal agents and predict the properties of composite molecules. Methods:: All compounds were randomly divided into a training set and a test set. A large number of descriptors were calculated by the software, then some of the best descriptors were selected to build the models. The linear model was built by the heuristic method and the nonlinear model was built by gene expression programming method. Results:: In the heuristic method, the correlation coefficients ,R2, R2cv, F and S2 were 0.581, 0.457, 14.053 and 15.311, respectively. In gene expression programming, the R2 and S2 were 0.715, 10.997 in the training set and 0.617, 22.778 in the test set. The results showed that the relative number of S atoms and the minimum bond order of an H atom had a significant positive contribution to IC50. Meanwhile, the relative number of double bonds and the count of hydrogen-bonding acceptor sites had a great negative impact on IC50. Conclusion:: Both the heuristic method and gene expression programming had a good predictive performance. By contrast, the gene expression programming method fitted well with the experimental values and it was expected to be beneficial in the synthesis of new antitrypanosomal drugs.

Using of gene expression programming method for prediction of daily components of tidal cycle in tidal rivers

The forecasting of tide or ebb elevation is a conventional issue. However, prediction of different components of tidal cycle in tidal rivers is a new aspect in geology and river engineering. For this purpose, this study utilizes the Gene Expression Programming (GEP) method in the Khosro-Abad, Khorramshahr, and Arvand Rood tidal stations (from 2001 to 2008). For short-term forecasts, normality and stationary of data time series are necessary. Existence of trends and skewness reduces accuracy of short-term predictions. Therefore, the modified Mann-Kendall trend test (MK3) method was applied and this test did not show any significant trend in daily tidal data time series. Due to the large skewness in a number of data time series, the Box-Cox transformation function was applied for minimization of skewness coefficient. Then, Augmented Dickey-Fuller (ADF) and Kwiatkowski, Phillips, Schmidt, and Shin (KPSS) tests showed that different normalized tidal data time series are stationary. The autocorrelation function (ACF) and partial autocorrelation function (PACF) diagrams illustrate that maximum number of effective lags is 3 days and the GEP must use data of 1 to 3 days ago. The GEP method stated different equations for forecasting of different components of tidal cycle in three tidal stations. By comparison between observed data and predicted values by these derived equations, it is observed that the range of R and root mean square error (RMSE) are from 0.867 to 0.944 and from 0.058 to 0.149 m.

Prediction of the depth of local scouring at a bridge pier using a gene expression programming method

Local scouring around the piers of a bridge is the one of the major reasons for bridge failure, potentially resulting in heavy losses in terms of both the economy and human life. Prediction of accurate depth of local scouring is a difficult task due to the many factors that contribute to this process, however. The main aim of this study is thus to offer a new formula for the prediction the local depth of scouring around the pier of a bridge using a modern fine computing modelling technique known as gene expression programming (GEP), with data obtained from numerical simulations used to compare GEP performance with that of a standard non-linear regression (NLR) model. The best technique for prediction of the local scouring depth is then determined based on three statistical parameters: the determination coefficient (R2), mean absolute error (MAE), and root mean squared error (RMSE). A total data set of 243 measurements, obtained by numerical simulation in Flow-3D, for intensity of flow, ratio of pier width, ratio of flow depth, pier Froude number, and pier shape factor is divided into training and validation (testing) datasets to achieve this. The results suggest that the formula from the GEP model provides better performance for predicting the local depth of scouring as compared with conventional regression with the NLR model, with R2 = 0.901, MAE = 0.111, and RMSE = 0.142. The sensitivity analysis results further suggest that the ratio of the depth of flow has the greatest impact on the prediction of local scour depth as compared to the other input parameters. The formula obtained from the GEP model gives the best predictor of depth of scouring, and, in addition, GEP offers the special feature of providing both explicit and compressed arithmetical terms to allow calculation of such depth of scouring.

Gene expression programming and ensemble methods for bushfire susceptibility mapping: a case study of Victoria, Australia

Bushfire susceptibility mapping helps the government authorities predict and provide the required disaster management plans to reduce the adverse impacts from bushfires. In this paper, we investigated Gene Expression Programming (GEP) and ensemble methods to create bushfire susceptibility maps for Victoria, Australia, as a case study. Bushfire susceptibility maps indicate that the eastern part of Victoria where forests are predominant has the highest probability of bushfire. Western part of Victoria which is covered by cropland, shrubland and grassland has the lowest bushfire probability. Two ensemble methods, namely an ensemble of GEP and Frequency Ratio (GEPFR) and an ensemble of Logistic Regression and Frequency Ratio (LRFR), were proposed and compared with stand-alone GEP and stand-alone Frequency Ratio (FR) methods. The proposed methods were evaluated by Area Under Curve (AUC). AUCs of GEPFR, LRFR, GEP and FR are 0.860, 0.852, 0.850, and 0.840, respectively. It can be concluded that GEPFR outperforms the other three methods, and the ensemble methods outperform the stand-alone methods. GEPFR, LRFR and GEP produced the bushfire probability with an accuracy in the range of 90.79%−92.27%, and therefore they are equally useful for policy makers and managers to have better natural hazard management plans.

PREDICTION OF TBM PENETRATION RATE OF WATER CONVEYANCE TUNNELS IN IRAN USING MODERN METHODS

TBM has been used extensively in civil engineering activities and plays an important role in tunnelling projects. Hence, the penetration rate of these machines plays a crucial role in the success of their application. Therefore, in order to predict the TBM penetration rate in this study in several water conveyance tunnels including the tunnels of Karaj, Ghomrood, Golab, Nosoud and Sabzkooh, four intelligence techniques including multiple linear and nonlinear regression analysis, Gene Expression Programming (GEP) method, and Support Vector Machine (SVM) were applied. The obtained values of R2 and RMSE included 0.43 and 3.08 for linear regression, 0.68 and 2.3 for nonlinear regression, 0.74 and 2.09 for GEP method and 0.97 and 0.6 for SVM method, respectively which were utilized to predict TBM penetration rate. By investigating the tunnels database, the results indicated that the SVM method had the most accurate prediction of penetration rate (in terms of R2 and RMSE) and the maximum amount of R2 and the minimum amount of RMSE among all predictive modelings. Finally, respecting the amount of R2 and RMSE, the other methods like GEP method, nonlinear regression, and linear regression are listed to have the required accuracy in predicting penetration rate.

Comparison of artificial neural networks (ANN), support vector machine (SVM) and gene expression programming (GEP) approaches for predicting TBM penetration rate

The history of tunnel boring machine (TBM) tunnelling dates back to nearly 50 years ago. Due to high construction cost, the investigation on TBM performance is regarded as one of the crucial issues which should be considered from different aspects. The prediction of TBM penetration rate is one of the most important part of every mechanized tunnelling project which plays a key role in selecting the machine as well. One of the major difficulties and challenges in TBM performance prediction is to apply novel approaches to predict the TBMs penetration rate. Considering the importance of this issue, the objective of this research work is to attain more realistic models for predicting TBM penetration rate in Iranian water conveyance tunneling. With this respect, a database comprises field data and machine parameters in Chamshir water conveyance tunneling project were established. The data were then analyzed through artificial neural networks (ANN), support vector machine (SVM) and gene expression programming (GEP). Results demonstrated that obtained values of the coefficient of determination (R2) and the root mean square error (RMSE) found to be 0.99 and 0.15 for ANN, 0.95 and 0.37 for SVM, 0.99 and 0.11 for GEP, respectively. These models can be applied to predict TBM penetration rate in the Chamshir water conveyance tunnel. Moreover, it can be concluded that the GEP method has the higher accuracy (maximum R2 and minimum RMSE) among all predictive models.

Life cycle assessment of eco-friendly concrete mixtures incorporating natural zeolite in sulfate-aggressive environment

The incorporation of natural pozzolans into the binder has been considered as an effective method for reducing the climate change impact of concrete mixtures. When quantifying the environmental impacts of concrete mixtures with and without natural pozzolans and with equivalent mechanical properties, their lifespan has been usually overlooked. The importance of lifespan in the life cycle assessment (LCA) is more pronounced when the concrete structure is exposed to an aggressive environment. In this study, the system boundaries of LCA were expanded to a cradle-to-grave scope and the lifespan of concrete mixtures was incorporated into the reference flow calculation. To have a representative experimental result for the lifespan calculation, 54 mixtures with three binder contents and three water-to-cementitious materials ratios with six replacement rates of natural zeolite (NZ) were cast. The hardened specimens were tested against sulfate attack, the prevalent deterioration mechanism in the Caspian Sea. The experimental program was followed by a gene expression programming (GEP) modeling to predict the strength reduction and service life of the mixtures. The contribution of the concrete mixtures with and without NZ to global warming potential (GWP) was evaluated using the characterization factors of the IPCC 2013 model for a 100-year time horizon. The results show that the mechanical and durability performances of NZ mixtures are better than those in the mixtures without NZ. The incorporation of 20% NZ considerably increased the durability properties of mixtures, for example, a 27% reduction in water permeability. Based on the test results, the service life of the modified concrete exposed to a sodium sulfate attack was precisely predicted via the GEP method. The LCA results indicate that replacing 20% of PC with NZ reduced GWP by up to 69.7%, suggesting NZ has the potential to make an eco-friendly concrete mixture.

A novel soft computing model for predicting blast - induced ground vibration in open - pit mines using gene expression programming

The efforts of this study are to develop and propose a state - of - the - art model for predicting blast - induced ground vibration in open - pit mines with high accuracy anf ability based on the gene expression programming (GEP) technique. 25 blasts were conducted in the Tan Dong Hiep quarry mines with a total of 83 blasting events that were collected for this study. The GEP method was then applied to develop a non - linear equation for predicting blast - induced ground vibration based on a variety of influential parameters. A traditional empirical equation, namely Sadovski, was also applied to compare with the proposed GEP model. The results indicated that the GEP model can predict blast - induced ground vibration in open - pit mines better than the Sadovski model with an RMSE of 0.986 and R2 of 0.867. Meanwhile, the traditional empirical model (Sadovski) only provided an accuracy with an RMSE of 1.850 và R2 of 0.767.

Estimating the Saturated Hydraulic Conductivity of Soil Using Gene Expression Programming Method and Comparing It with the Pedotransfer Functions

Estimating the Saturated Hydraulic Conductivity of Soil Using Gene Expression Programming Method and Comparing It with the Pedotransfer Functions

Enhancing gene expression programming based on space partition and jump for symbolic regression

When solving a symbolic regression problem, the gene expression programming (GEP) algorithm could fall into a premature convergence which terminates the optimization process too early, and may only reach a poor local optimum. To address the premature convergence problem of GEP, we propose a novel algorithm named SPJ-GEP, which can maintain the GEP population diversity and improve the accuracy of the GEP search by allowing the population to jump efficiently between segmented subspaces. SPJ-GEP first divides the space of mathematical expressions into k subspaces that are mutually exclusive. It then creates a subspace selection method that combines the multi-armed bandit and the ∊-greedy strategy to choose a jump subspace. In this way, the analysis is made on the population diversity and the range of the number of subspaces. The analysis results show that SPJ-GEP does not significantly increase the computational complexity of time and space than classical GEP methods. Besides, an evaluation is conducted on a set of standard SR benchmarks. The evaluation results show that the proposed SPJ-GEP keeps a higher population diversity and has an enhanced accuracy compared with three baseline GEP methods.

Metal-doped bioceramic nanopowders with tunable structural properties aimed at enhancing bone density: Rapid synthesis and modeling

Metal doped bioceramic nanopowders were prepared by solid-state mechanochemical reactions. Also, genetic programming (GP) and gene expression programming (GEP) models were developed to predict the structural features of the mechanosynthesized nanopowders aimed at developing an innovative solution to enhance bone mineral density. The substitution of Ca2+ with different ions in the apatite structure was confirmed from chemical analysis and structural assessment, where irregular changes in the lattice parameters and unit cell volume were observed due to the replacement of the Ca2+ bivalent cation with monovalent, bivalent or trivalent ions as well as the carbonate ions effects on the apatite lattice. It was found that the crystallite size and micro-strain of the substituted bioceramics were between ~11 and 98 nm and ~0.31–2.49%, respectively. From the functional group analysis, the intensity of the hydroxyl groups decreased as the dopant content increased. The electron microscopy images showed that both undoped and low-doped samples consist of spheroidal particles in the nano regime, whereas the high-doped specimens exhibited a high propensity to agglomerate. The results of cytotoxicity assays corroborated that appropriate ionic substitution can prevent the toxic effects of Li on Mus musculus fibroblast cells, and thus by increasing dopant concentration up to z = 0.25, cell viability of around 90% was observed. The results obtained from the modeling demonstrated that both GP and GEP methods are reliable in predicting the structural properties of the synthetic metal-doped bioceramic nanopowders.

Discharge coefficients for ogee weirs including the effects of a sloping upstream face

Abstract Discharge coefficients (C0) for ogee weirs are essential factors for predicting the discharge-head relationship. The present study investigates three influences on the C0: effect of approach depth, weir upstream face slope, and the actual head, which may differ from the design head. This study uses experimental data with multiple non-linear regression techniques and Gene Expression Programming (GEP) models that are applied to introduce practical equations that can be used for design. Results show that the GEP method is superior to the regression analysis for predicting the discharge coefficient. Performance criteria for GEP are R2 = 0.995, RMSE = 0.021 and MAE = 0.015. Design examples are presented that show that the proposed GEP equation correlates well with the data and eliminates linear interpolation using existing graphs.

RANS turbulence model development using CFD-driven machine learning

This paper presents a novel CFD-driven machine learning framework to develop Reynolds-averaged Navier-Stokes (RANS) models. The CFD-driven training is an extension of the gene expression programming method Weatheritt and Sandberg (2016) [8], but crucially the fitness of candidate models is now evaluated by running RANS calculations in an integrated way, rather than using an algebraic function. Unlike other data-driven methods that fit the Reynolds stresses of trained models to high-fidelity data, the cost function for the CFD-driven training can be defined based on any flow feature from the CFD results. This extends the applicability of the method especially when the training data is limited. Furthermore, the resulting model, which is the one providing the most accurate CFD results at the end of the training, inherently shows good performance in RANS calculations. To demonstrate the potential of this new method, the CFD-driven machine learning approach is applied to model development for wake mixing in turbomachines. A new model is trained based on a high-pressure turbine case and then tested for three additional cases, all representative of modern turbine nozzles. Despite the geometric configurations and operating conditions being different among the cases, the predicted wake mixing profiles are significantly improved in all of these a posteriori tests. Moreover, the model equation is explicitly given and available for analysis, thus it could be deduced that the enhanced wake prediction is predominantly due to the extra diffusion introduced by the CFD-driven model.

Ice-Seabed interaction analysis in sand using a gene expression programming-based approach

Arctic subsea pipelines are usually buried for physical protection against the ice-induced scours. Determination of the maximum horizontal deformations for guaranteed operational integrity and cost-effective design is probably the most challenging aspect of subsea pipelines in ice-prone areas. The large uncertainties associated with the design of ice-protected subsea pipeline using the existing empirical equations, advanced experimental and sophisticated numerical studies with significant time and cost impacts are usually preferred to ensure the sufficiency and the cost-effectiveness of the pipeline design against the ice attack. This has caused the industry to keep looking for more effective and less-costly solutions for modeling the ice impact on buried pipelines. In this study, a Gene Expression Programming (GEP) model representing the Artificial Intelligence (AI) approaches was used for the first time to simulate the subgouge soil deformation in the sand. A database was constructed using some of the published experimental studies identifying the key input parameters including soil depth, bearing pressure, the maximum vertical extent of subgouge deformation, attack angle, and dilation index. Subsequently, six GEP models were developed and validated by using a K-fold cross-validation method. The performance of the GEP method was compared with an Artificial Neural Network (ANN) model, and uncertainty analysis (UA) along with a partial derivative sensitivity analysis (PDSA) was conducted to assess the influence domain of the key parameters. The study showed that the evolutionary numerical methods could be used as an accurate and cost-effective alternative for modeling of the ice-induced subgouge deformations.

Estimation of uniaxial compressive strength of pyroclastic rocks (Cappadocia, Turkey) by gene expression programming

Compressive strength of rocks is an important factor in structural design in rock engineering. Compressive strength can be determined in the laboratory by means of the uniaxial compressive strength (UCS) test, or it can be estimated indirectly by simple experiments such as point load strength (PLT) test and Schmidt hammer rebound test. Although the UCS test method is time-consuming and expensive, it is simple when compared to other methods. Therefore, many studies have been performed to estimate UCS values of rocks. Studies indicated that correlation coefficient of rock groups is low unless they are classified as metamorphic, sedimentary, or volcanic. Pyroclastic rocks are widely used as construction materials because of the fact that they crop out over extensive areas in the world. To estimate the UCS values of pyroclastic rocks in Central and Western Anatolia region, Turkey, multiple linear regression (MLR) analysis and gene expression programming (GEP) were employed and during the analysis, and PLT, ρd, ρs, and n were used as the independent variables. Based on the analysis results, it was detected that the GEP methods gave better results than MLR method. Additionally, the correlation coefficient (R2) values of training and sets of validation of the GEP-I model are 0.8859 and 0.9325, respectively, and this model, thereby, is detected the best of generation individuals for prediction of the UCS.

Determination of Joint Roughness Coefficient of 2D Rock Joint Profile Based on Fractal Dimension by Using of the Gene Expression Programming

Rock joint roughness influence the shear behavior of rock joints, which have been extensively studied in last a few decades. Various parameters were recommended to quantify the joint roughness, in these parameters, the joint roughness coefficients (JRC value) were widely applied to depict the joint roughness quantitatively by many researchers. Through analysis the references, it is found that the empirical formula of the JRC value based on fractal dimension were commonly adopted, however, the empirical formulas were determined frequently by a limited number of data point, meanwhile, the type of empirical formula were chosen based on the researchers’ subjectively. For obtaining a suitable and objective empirical formula of JRC values based on fractal dimension, a large number of experimental data were collected from the references, by using the gene expression programming method, an empirical formula was determined objectively. The obtained formula can reflect the relationship between the JRC values and fractal dimension extensively, the empirical formula is \( JRC = 21.0810 - \frac{0.0656}{(\sqrt D - 0.9969)D} \).