Performance Of Gene Expression Programming Research Articles

Predictive Modeling Approach for Surface Water Quality: Development and Comparison of Machine Learning Models

Water pollution is an increasing global issue that societies are facing and is threating human health, ecosystem functions and agriculture production. The distinguished features of artificial intelligence (AI) based modeling can deliver a deep insight pertaining to rising water quality concerns. The current study investigates the predictive performance of gene expression programming (GEP), artificial neural network (ANN) and linear regression model (LRM) for modeling monthly total dissolved solids (TDS) and specific conductivity (EC) in the upper Indus River at two outlet stations. In total, 30 years of historical water quality data, comprising 360 TDS and EC monthly records, were used for models training and testing. Based on a significant correlation, the TDS and EC modeling were correlated with seven input parameters. Results were evaluated using various performance measure indicators, error assessment and external criteria. The simulated outcome of the models indicated a strong association with actual data where the correlation coefficient above 0.9 was observed for both TDS and EC. Both the GEP and ANN models remained the reliable techniques in predicting TDS and EC. The formulated GEP mathematical equations depict its novelty as compared to ANN and LRM. The results of sensitivity analysis indicated the increasing trend of input variables affecting TDS as HCO3− (22.33%) > Cl− (21.66%) > Mg2+ (16.98%) > Na+ (14.55%) > Ca2+ (12.92%) > SO42− (11.55%) > pH (0%), while, in the case of EC, it followed the trend as HCO3− (42.36%) > SO42−(25.63%) > Ca2+ (13.59%) > Cl− (12.8%) > Na+ (5.01%) > pH (0.61%) > Mg2+ (0%). The parametric analysis revealed that models have incorporated the effect of all the input parameters in the modeling process. The external assessment criteria confirmed the generalized outcome and robustness of the proposed approaches. Conclusively, the outcomes of this study demonstrated that the formulation of AI based models are cost effective and helpful for river water quality assessment, management and policy making.

Predictive modeling of the compressive strength of bacteria-incorporated geopolymer concrete using a gene expression programming approach

The performance of gene expression programming (GEP) in predicting the compressive strength of bacteriaincorporated geopolymer concrete (GPC) was examined in this study. Ground-granulated blast-furnace slag (GGBS), new bacterial strains, fly ash (FA), silica fume (SF), metakaolin (MK), and manufactured sand were used as ingredients in the concrete mixture. For the geopolymer preparation, an 8 M sodium hydroxide (NaOH) solution was used, and the ambient curing temperature (28oC) was maintained for all mixtures. The ratio of sodium silicate (Na2SiO3) to NaOH was 2.33, and the ratio of alkaline liquid to binder was 0.35. Based on experimental data collected from the literature, an evolutionary-based algorithm (GEP) was proposed to develop new predictive models for estimating the compressive strength of GPC containing bacteria. Data were classified into training and testing sets to obtain a closed-form solution using GEP. Independent variables for the model were the constituent materials of GPC, such as FA, MK, SF, and Bacillus bacteria. A total of six GEP formulations were developed for predicting the compressive strength of bacteria-incorporated GPC obtained at 1, 3, 7, 28, 56, and 90 days of curing. 80% and 20% of the data were used for training and testing the models, respectively. R2 values in the range of 0.9747 and 0.9950 (including train and test dataset) were obtained for the concrete samples, which showed that GEP can be used to predict the compressive strength of GPC containing bacteria with minimal error. Moreover, the GEP models were in good agreement with the experimental datasets and were robust and reliable. The models developed could serve as a tool for concrete constructors using geopolymers within the framework of this research.

A Comparative Study on the Performance of Gene Expression Programming and Machine Learning Methods

Usually, evolutionary algorithms are used to provide strong approximations to problems that are difficult to solve with other methods. Gene expression programming (GEP) is a type of evolutionary algorithm used in computer programming to generate computer programs or models. These computer programs are complex tree structures that, like a living organism, learn and adapt by modifying their sizes, shapes, and composition. In the present work, a comparison study was made among GEP and the standard prediction techniques to find the best predicting model on the BOSTON HOUSING dataset. Three approaches viz. GEP, ANN and polynomial regression were implemented on the dataset. The study showed how the three methods solve the problem of high bias and high variance and which one outperforms the other. The research work, however, gave a glimpse of the actual limitations and advantages of the methods on one another indicating the dependency of method on the type of data used. The results conclude the comparison of different methods on different performance metrics. The GEP model however reduced the problem of high bias and high variance by giving a slight difference between the train and test accuracy but was not able to outperform ANN and polynomial regression in terms of performance metrics.

Alternative heuristics equations to the Priestley–Taylor approach: assessing reference evapotranspiration estimation

The radiation-based Priestley–Taylor (PT) model is a common way of modeling evapotranspiration (ET0) when only air temperature and solar radiation records are obtainable. However, this method presents the crucial drawback of requiring an initial local calibration. Most of the existing calibration procedures usually utilize similar patterns (data) for calibrating and testing the ET0 models. In the current research, the PT model and its calibrated versions were evaluated by utilizing meteorological data from 29 weather stations in Iran. Thoroughgoing local and external data scrutinizing procedures (using k-fold validation) were adopted to evaluate the models. Additionally, the externally calibrated models were reevaluated considering vapor pressure deficit (VPD) and net radiation (Rn) records. A similar plan was replicated for assessing the performance of gene expression programming (GEP)–based equations fed with the air temperature and solar radiation data. Both local and external calibrations of the PT model generally improved the accuracy of original PT for estimating ET0, especially in humid and arid stations. External calibration using VPD and Rn data was found to be comparable to locally calibrated and non-calibrated PT models. Local GEP models generally performed more accurately than locally calibrated and non-calibrated PT models. Higher accuracy was also obtained using external GEP models in comparison with non-calibrated PT models.

Prediction of riprap stone size under overtopping flow using data-driven models

ABSTRACTRock riprap is commonly used to protect levees, embankment dam, steep channels, and other structures being vulnerable to deteriorative erosion caused by overtopping flow. A review of the literature in this context indicates that over 24 riprap design expressions exist to predict the stone size in the riprap layer. However, each equation was originally derived on the basis of limited data sets under certain experimental conditions. In this investigation, Gene-Expression Programming (GEP), Model Tree (MT), and Evolutionary Polynomial Regression (EPR) were evaluated to estimate riprap stone sizing by virtue of 102 experimental data sets. Efficiency and performance of GEP, MT, and EPR approaches for training and testing stages were analysed and discussed. Results analysis revealed that the EPR technique provided an accurate prediction of riprap sizing in testing stage compared with other selected data-driven models as well as the empirical equations. The robustness of the developed data-driven predictive techniques was verified through the external validation: the selected data-driven models are definitely valid, have the strong capability to predict the riprap stone size which was not achieved by a chance. The prediction uncertainties of the data-driven models were quantified and compared with the selected empirical equations.

Computation of design coefficients in ogee-crested spillway structure using GEP and regression models

The ogee-crested spillway is a passage in a dam through which the design flood could be disposed of safely to the downstream. Spillways of improper design or insufficient capacities have caused failures of dams. Therefore, the spillway must be hydraulically and structurally adequate. This paper presents Gene-Expression Programming (GEP) models as an alternative approach to prediction of design coefficients in ogee-crested spillway structure. New formulations for prediction of design coefficient are developed using GEP and regression models. The performance of GEP was found to be satisfactory and encouraging when compared with regression model in predicting of design coefficient. This capability of GEP makes it unique and more effective when compared with regression models evaluated in this paper. The superior performance of GEP is attributed to the powerful Artificial Intelligence (AI) techniques for computer learning inspired by natural evolution to find the appropriate mathematical model (expression) to fit a set of fits. This study highlights the utility of AI-based models with a view to increase their usage by engineers and planners working on spillway design problems.

Scour Prediction at Bridge Piers in Cohesive Bed Using Gene Expression Programming

Accurate and reliable estimation of the scour depth at a bridge pier is essential for the safe and economical design of the bridge foundation. The phenomenon of scour at the pier placed on sediments is extremely complex in nature. Only a limited number of studies have been reported on local scour around bridge piers in cohesive sediment mainly due to the fact that scour modeling in cohesive beds is relatively more complex than that in sandy beds. Recent research has made good progress in the development of data-driven technique based on artificial intelligence (AI). It has been reported that AI-based inductive modeling techniques are frequently used to model complex process due to their powerful and non-linear model structures and their increased capabilities to capture the cause and effect relationship of such complex processes. Gene Expression Programming (GEP) is one of the AI techniques that have emerged as a powerful tool in modeling complex phenomenon into simpler chromosomal architecture. This technique has been proved to be more accurate and much simpler than other AI tools. In the present study, an attempt has been made to implement GEP for the development of scour depth prediction model at bridge piers in cohesive sediments using laboratory data available in literature. The present study reveals that the performance of GEP is better than nonlinear regression model for the prediction of scour depth at piers in cohesive beds.

GEP PREDICTION OF SCOUR AROUND A SIDE WEIR IN CURVED CHANNEL

Side-weirs have been widely used in hydraulic and environmental engineering applications. Side-weir is known as a lateral intake structure, which are significant parts of the distribution channel in irrigation, land drainage, and urban sewerage system, by flow diversion device. Local scour involves the removal of material around piers, abutments, side-weir, spurs, and embankments. Clearwater scour depth based on five dimensional parameters: approach flow velocity (V1/Vc), water head ratio (h1–p)/h1, side-weir length (L/r), side-weir crest height (b/p) and angle of bend θ. The aim of this study is to develop a new formulation for prediction of clear-water scour of side-weir intersection along curved channel using Gene Expression Programming (GEP) which is an algorithm based on genetic algorithms (GA) and genetic programming (GP). In addition, the explicit formulations of the developed GEP models are presented. Also equations are obtained using multiple linear regressions (MLR) and multiple nonlinear regressions (MNRL). The performance of GEP is found more influential than multiple linear regression equation for predicting the clearwater scour depth at side-weir intersection along curved channel. Multiple nonlinear regression equation was quite close to GEP, which serve much simpler model with explicit formulation.

Generalizability of Gene Expression Programming-based approaches for estimating daily reference evapotranspiration in coastal stations of Iran

Summary When dealing with climatic variables, the performance assessment of many Artificial Intelligence (AI) and/or data mining applications is based on a single data set assignment of the training and test sets. Further, it is very usual that this assignment is defined according to a local and temporary criterion, i.e. the models are trained and tested using data of the same station. Based on this procedure, the performance of the models outside the training location cannot be inferred. The present work evaluates the performance of Gene Expression Programming (GEP) based models for estimating reference evapotranspiration (ET0) according to temporal and spatial criteria and data set scanning procedures in coastal environments of Iran. The accuracy differences between the local and the external performance depend on the specific climatic trends of the test stations, as well as on the input combination used to feed the models. When relying on a suitable input selection, externally trained models might be a valid alternative to locally trained ones, which would be a crucial advantage in places where only limited climatic variables are available. K-fold testing is a good choice to prevent partially valid conclusions derived from model assessments based on a simple data set assignment. Further, calibration of the GEP model may not be needed, if enough climatic data are available at other stations for external model application. The performance of the GEP model fluctuates chronologically and spatially. A suitable assessment of the model should consider a complete local and/or external scan of the data set used.

Bridge pier scour prediction by gene expression programming

Extensive research has been carried out to predict bridge pier scour, with laboratory and field data, using different modelling techniques. This study introduces a new soft computing technique called gene expression programming (GEP) for pier scour depth prediction using field data. A functional relationship has been established using GEP and its performance is compared with other inductive modelling techniques such as artificial neural networks (ANNs) and conventional regression-based techniques. Field data comprising 370 data sets were collected from the published literature and divided into calibration and validation (testing) data sets. The performance of GEP was found to be satisfactory and encouraging when compared with regression and ANN models in predicting bridge pier scour depth. GEP has the unique capability of providing a compact and explicit mathematical expression for computing bridge scour. This advantage of GEP over ANN is one of the main motivations for this work. The resulting GEP models add to the existing literature on artificial intelligence based inductive models that can be used effectively for bridge scour modelling.