Proposed Genetic Programming Model Research Articles

A New Approach to Determining the Network Fractality with Application to Robot-Laser-Hardened Surfaces of Materials

A new method to determine a fractal network in chaotic systems is presented together with its application to the microstructure recognition of robot-laser-hardened (RLH) steels under various angles of a laser beam. The method is based on fractal geometry. An experimental investigation was conducted by investigating the effect of several process parameters on the final microstructures of material that has been heat-treated. The influences of the surface temperature, laser speed, and different orientation angles of the laser beam on the microstructural geometry of the treated surfaces were considered. The fractal network of the microstructures of robot-laser-hardened specimens was used to describe how the geometry was changed during the heat treatment of materials. In order to predict the fractal network of robot-laser-hardened specimens, we used a method based on intelligent systems, namely genetic programming (GP) and a convolutional neural network (CNN). The proposed GP model achieved a prediction accuracy of 98.4%, while the proposed CNN model reached 96.5%. The performed analyses demonstrate that the angles of the robot laser cell have a noticeable effect on the final microstructures. The specimen laser-hardened under the conditions of 4 mm/s, 1000 °C, and an impact angle of the laser beam equal to 75° presented the maximum fractal network. The minimum fractal network was observed for the specimen before the robot-laser-hardening process.

Drought classification using gradient boosting decision tree

This paper compares the classification and prediction capabilities of decision tree (DT), genetic programming (GP), and gradient boosting decision tree (GBT) techniques for one-month ahead prediction of standardized precipitation index in Ankara province and standardized precipitation evaporation index in central Antalya region. The evolved models were developed based on multi-station prediction scenarios in which observed (reanalyzed) data from nearby stations (grid points) were used to predict drought conditions in a target location. To tackle the rare occurrence of extreme dry/wet conditions, the drought series at the target location was categorized into three classes of wet, normal, and dry events. The new models were trained and validated using the first 70% and last 30% of the datasets, respectively. The results demonstrated the promising performance of GBT for meteorological drought classification. It provides better performance than DT and GP in Ankara; however, GP predictions for Antalya were more accurate in the testing period. The results also exhibited that the proposed GP model with a scaled sigmoid function at root can effortlessly classify and predict the number of dry, normal, and wet events in both case studies.

Predicting the shear strength of saw-tooth jointed rocks using genetic programming

The geometrical and mechanical properties of joints play an important role in the determination of shear strength of jointed rocks. In this research, we propose a nonlinear model to estimate the shear strength of jointed rocks with unfilled saw-tooth triangular asperities using the basic friction angle φb, the tensile strength of intact rock σt, and the joint inclination angle i under various normal stress σn conditions. In order to propose the new shear strength model, firstly, a rock database of saw-tooth jointed rocks containing experimental and numerical data is established. The experimental data are collected from publications. The numerical data are generated by the particle flow code (PFC) model. Then, the genetic programming (GP) is used to analyze the database to propose the GP shear strength model. The prediction performance of the proposed GP model is tested and compared with that of the Patton model and the Ladanyi and Archambault (LA) model. Comparison results show that the proposed GP model has the best prediction performance compared with the Patton model and the LA model. The proposed GP model can capture the nonlinear shear strength behavior of saw-tooth jointed rocks and its input parameters can be easily estimated.

Genetic Programming Approach to Detect Hate Speech in Social Media

Social media sites, which became central to our everyday lives, enable users to freely express their opinions, feelings, and ideas due to a certain level of depersonalization and anonymity they provide. If there is no control, these platforms may be used to propagate hate speech. In fact, in recent years, hate speech has increased on social media. Therefore, there is a need to monitor and prevent hate speech on these platforms. However, manual control is not feasible due to the high traffic of content production on social media sites. Moreover, the language used and the length of the messages provide a challenge when using classical machine learning approaches as prediction methods. This paper presents a genetic programming (GP) model for detecting hate speech where each chromosome represents a classifier employing a universal sentence encoder as a feature. A novel mutation technique that affects only the feature values in combination with the standard one-point mutation technique improved the performance of the GP model by enriching the offspring pool with alternative solutions. The proposed GP model outperformed all state-of-the-art systems for the four publicly available hate speech datasets.

Sarima-arch versus genetic programming in stock price prediction

In financial time series, one of the most challenging problems is predicting stock prices since the data generally exhibit deviation from the assumptions of stationary and homoscedasticity. For homogenous non-stationary time series, the Autoregressive Integrated Moving Average (ARIMA) model is the most commonly used linear class including some transformation such as differencing and variance stabilizing process. However, stock market data is often nonlinear, which indicates that more advanced methods are necessary. Genetic Programming (GP) is one of the evolutionary computational methods that could capture both linear and nonlinear patterns in time series data. The present study aims to build a machine learning tool using GP for prediction The Istanbul Stock Exchange National 100 (XU100) index and compare the obtained results with conventional seasonal ARIMA(SARIMA) and ARCH models. In order to achieve this goal, it was first modeled with the SARIMA model after appropriate transfor- mations were made to the stock price series and the diagnostic control result showed that the residual of the SARIMA model have the heteroscedasticity problem. Then, the ARCH model was applied to SARIMA residuals to eliminate this effect and an integrated SARIMA-ARCH model is obtained. Since it is possible and capable to model nonlinear and non-stationary time series using GP without any pre-assumptions, we proposed GP to predict the stock price series. The function set of GP consists of not only arithmetic but also trigonometric functions. To the best of our knowledge, this study is the first to predict XU100 stock price data using GP. In this experiment, the data set consists of the daily closing prices of the XU100 index over 775 days from the beginning of 2017 until the end of January 2020. The experimental results obtained show that the accuracy metrics used in the study are lower in the proposed GP model compared to other models. These results reveal that the GP method provides better predictive results for the financial time series data of the XU100 index than traditional methods.

Application of Tree-Based Predictive Models to Forecast Air Overpressure Induced by Mine Blasting

In surface mines and underground excavations, every blasting operation can have some destructive environmental impacts, among which air overpressure (AOp) is of major significance. Therefore, it is essential to minimize the related environmental damage by precisely evaluating the intensity of AOp before any blasting operation. The present study primarily aimed to develop two different tree-based data mining algorithms, namely M5′ decision tree and genetic programming (GP) for accurately predicting blast-induced AOp in granite quarries. In addition, a multiple linear regression technique was adopted to check the accuracy of the GP and M5′ models. To achieve the aims of this research, 125 blasts were explored and their respective AOp values were carefully recorded. In each operation, six influential parameters of AOp, i.e., stemming length, powder factor, blasting index, joint aperture, maximum charge weight per delay and distance of the blast points, were recorded and considered as inputs for modeling. After developing the predictive models of AOp, their performances were examined in terms of coefficient of determination (R2), root-mean-squared error (RMSE) and mean absolute error (MAE). Based on the computed results, the GP (with RMSE of 1.3997, R2 of 0.8621 and MAE of 0.9472) outperformed the other developed models. Then, a sensitivity analysis was employed to identify the most influential parameters in predicting the AOp values. Finally, the generality of the proposed GP model was validated by investigating its predictive results with respect to the two most effective predictor variables. The study findings demonstrated the robustness and applicability of the proposed GP model for predicting blast-induced AOp.

Estimation of spatiotemporal response of rooted soil using a machine learning approach

In this study, a machine learning method, i.e. genetic programming (GP), is employed to obtain a simplified statistical model to describe the variation of soil suction in drying cycles using five selected influential parameters. The data used for model development was recorded by an in-situ experiment. The image processing technology is used to quantify several tree canopy parameters. Based on four accuracy metrics, i.e. root mean square error (RMSE), mean absolute percentage error (MAPE), coefficient of determination (R2), and relative error, the performance of the proposed GP model was evaluated. The results indicate that the model can give a reasonable estimation for the spatiotemporal variations of soil suction around a tree with acceptable errors. Global sensitivity analysis for the statistical model obtained using limited data of a specific region demonstrates the drying time as the most influential variable and the initial soil suction as the second most influential variable for the soil suction variations. A case study was conducted using a set of assumed input variable values and validated that the simplified GP model can be used to estimate and predict the spatiotemporal variations of soil suction in rooted soil at a certain range.

Spatial Downscaling of MODIS Chlorophyll-a with Genetic Programming in South Korea

Chlorophyll-a (Chl-a) is one of the major indicators for water quality assessment and recent developments in ocean color remote sensing have greatly improved the ability to monitor Chl-a on a global scale. The coarse spatial resolution is one of the major limitations for most ocean color sensors including Moderate Resolution Imaging Spectroradiometer (MODIS), especially in monitoring the Chl-a concentrations in coastal regions. To improve its spatial resolution, downscaling techniques have been suggested with polynomial regression models. Nevertheless, polynomial regression has some restrictions, including sensitivity to outliers and fixed mathematical forms. Therefore, the current study applied genetic programming (GP) for downscaling Chl-a. The proposed GP model in the current study was compared with multiple polynomial regression (MPR) to different degrees (2nd-, 3rd-, and 4th-degree) to illustrate their performances for downscaling MODIS Chl-a. The obtained results indicate that GP with R2 = 0.927 and RMSE = 0.1642 on the winter day and R2 = 0.763 and RMSE = 0.5274 on the summer day provides higher accuracy on both winter and summer days than all the applied MPR models because the GP model can automatically produce appropriate mathematical equations without any restrictions. In addition, the GP model is the least sensitive model to the changes in the input parameters. The improved downscaling data provide better information to monitor the status of oceanic and coastal marine ecosystems that are also critical for fisheries and fishing farming.

Forecasting of TBM advance rate in hard rock condition based on artificial neural network and genetic programming techniques

The efficiency of tunnel boring machine (TBM) is regarded as a key factor in successfully undertaking any mechanical tunneling project. In fact, an accurate forecasting of TBM performance, especially in a specified rock mass condition, can minimize capital costs and scheduling for tunnel excavation. This study puts an effort to propose two accurate and practical predictive models of TBM performance via artificial neural network (ANN) and genetic programming (GP) approaches. To set a certain prediction target for the proposed models, the advance rate (AR) of TBM is considered as its performance metric. For modeling purpose, a large experimental database containing 1286 data sets was set up as the result of conducting site investigation operations for a tunneling project in Malaysia, called the Pahang–Selangor Raw Water Transfer Tunnel and performing a number of laboratory tests on the collected rock samples. To design the desired intelligent models of AR based on the training and test patterns, a mix of rock and machine characteristics with the most influence on AR has been used as input parameters, i.e., rock quality designation (RQD), uniaxial compressive strength (UCS), rock mass rating (RMR), Brazilian tensile strength (BTS), thrust force (TF), and revolution per minute (RPM). In addition, a series of statistical indices, such as root mean squared error (RMSE), determination coefficient (R-square), and variance account for (VAF) are utilized to evaluate and compare the prediction precision of the developed models. Based on the simulation results and the computed values of indices, it is observed that the proposed GP model with the training and test RMSE values 0.0427 and 0.0388, respectively, performs noticeably better than the proposed ANN model giving RMSE values 0.0509 and 0.0472 for the training and test sets, respectively. Additionally, a parametric analysis has been conducted on the proposed GP model to further verify its generalization capability. The obtained results demonstrate that this GP-based model could provide a new applicable equation for accuratly predicting TBM performance.

Strength evaluation of granite block samples with different predictive models

Over the last decade, application of soft computing techniques has rapidly grown up in different scientific fields, especially in rock mechanics. One of these cases relates to indirect assessment of uniaxial compressive strength (UCS) of rock samples with different artificial intelligent-based methods. In fact, the main advantage of such systems is to readily remove some difficulties arising in direct assessment of UCS, such as time-consuming and costly UCS test procedure. This study puts an effort to propose four accurate and practical predictive models of UCS using artificial neural network (ANN), hybrid ANN with imperialism competitive algorithm (ICA–ANN), hybrid ANN with artificial bee colony (ABC–ANN) and genetic programming (GP) approaches. To reach the aim of the current study, an experimental database containing a total of 71 data sets was set up by performing a number of laboratory tests on the rock samples collected from a tunnel site in Malaysia. To construct the desired predictive models of UCS based on training and test patterns, a combination of several rock characteristics with the most influence on UCS has been used as input parameters, i.e. porosity (n), Schmidt hammer rebound number (R), p-wave velocity (Vp) and point load strength index (Is(50)). To evaluate and compare the prediction precision of the developed models, a series of statistical indices, such as root mean squared error (RMSE), determination coefficient (R2) and variance account for (VAF) are utilized. Based on the simulation results and the measured indices, it was observed that the proposed GP model with the training and test RMSE values 0.0726 and 0.0691, respectively, gives better performance as compared to the other proposed models with values of (0.0740 and 0.0885), (0.0785 and 0.0742), and (0.0746 and 0.0771) for ANN, ICA–ANN and ABC–ANN, respectively. Moreover, a parametric analysis is accomplished on the proposed GP model to further verify its generalization capability. Hence, this GP-based model can be considered as a new applicable equation to accurately estimate the uniaxial compressive strength of granite block samples.

Predicting temperature drop rate of mass concrete during an initial cooling period using genetic programming

Thermal cracking on concrete dams depends upon the rate at which the concrete is cooled (temperature drop rate per day) within an initial cooling period during the construction phase. Thus, in order to control the thermal cracking of such structure, temperature development due to heat of hydration of cement should be dropped at suitable rate. In this study, an attempt have been made to formulate the relation between cooling rate of mass concrete with passage of time (age of concrete) and water cooling parameters: flow rate and inlet temperature of cooling water. Data measured at summer season (April-August from 2009 to 2012) from recently constructed high concrete dam were used to derive a prediction model with the help of Genetic Programming (GP) software “Eureqa”. Coefficient of Determination (R) and Mean Square Error (MSE) were used to evaluate the performance of the model. The value of R and MSE is 0.8855 and 0.002961 respectively. Sensitivity analysis was performed to evaluate the relative impact on the target parameter due to input parameters. Further, testing the proposed model with an independent dataset those not included during analysis, results obtained from the proposed GP model are close enough to the real field data.

New Formulations for Dynamic Behavior of Sand-Waste Tire Mixtures in a Small Range of Strain Amplitudes

This paper describes the results of a series of cyclic triaxial tests on sand - waste tire mixtures, and applications of genetic programming (GP) and stepwise regression (SR) for the prediction of damping ratio and shear modulus of the mixtures tested. In the tests, shear modulus, and damping ratio of the geomaterials were measured for a strain range of 0.0001% up to 0.04%. The input variables in the developed GP and SR models are the waste tire content (0%, 10%, 20%, and 30%), waste tire type (tire crumbs or tire buffings), strain, and confining pressures (40 kPa, 100 kPa, and 200 kPa), and outputs are shear modulus and damping ratio. Test results show that the shear modulus and the damping ratio of the mixtures are strongly influenced by the waste tire inclusions. The performance of the proposed GP models (R2 = 0.95 for shear modulus, and R2 = 0.94 for damping ratio) are observed to be more accurate than that of the SR models (R2 = 0.87 for shear modulus, and R2 = 0.91 for damping ratio).

Genetic programming (GP) approach for prediction of supercritical CO2 thermal conductivity

Gas thermal conductivity is one of the thermophysical properties that inevitably enters into mathematical models of real systems used in the design of chemical engineering processes or in the gas industry. In this study, via implementing a powerful and newly applied equation generator algorithm known as, genetic programming (GP) mathematical strategy, a novel correlation for estimation of supercritical CO2 thermal conductivity is established. The proposed correlation is developed and validated based on a comprehensive databank of 752 thermal conductivity datasets from open literature. By using various statistical quality measures, the result of the proposed GP model was compared with commonly used literature models. As a result, the proposed GP model gives the best fit and satisfactory agreement with the target data with an average absolute relative error of 2.31% and R2=0.997. A parametric sensitivity analysis showed that pressure and density of the CO2 gas stream have considerable impact on the thermal conductivity at supercritical condition. The results of this study can be of enormous practical worth for scientist and expertise in order to efficiently compute the thermal conductivity in any supercritical industry involving CO2.

Investment opportunities forecasting: a genetic programming-based dynamic portfolio trading system under a directional-change framework

This paper presents an autonomous effective trading system devoted to the support of decision-making processes in the financial market domain. Genetic programming (GP) has been used effectively as an artificial intelligence technique in the financial field, especially for forecasting tasks in financial markets. In this paper, GP is employed as a means of automatically generating short-term trading rules on financial markets using technical indicators and fundamental parameters. The majority of forecasting tools use a fixed physical timescale, which makes the flow of price fluctuations discontinuous. Therefore, using a fixed physical timescale may expose investors to risks, due to their ignorance of some significant activities. Instead of using fixed timescales for this purpose, the trading rules are generated under a directional-change (DC) event framework.We examine the profitability of the trading systems for the Saudi Stock Exchange, and evaluate the GP forecasting performance under a DC framework through agent-based simulation market index trading. The performance of the forecasting model is compared with a number of benchmark forecasts, namely the buy-and-hold and technical analysis trading strategies. Our numerical results show that the proposed GP model under a DC framework significantly outperforms other traditional models based on fixed physical timescales in terms of portfolio return.

Predicting the shear strength parameters of sandstone using genetic programming

The strength of intact rock is, together with the rock mass structure, probably the most important properties for rock engineering. To accurately estimate the Mohr–Coulomb (MC) strength parameters—cohesion c and angle of friction ϕ—of a rock, triaxial tests must be carried out at different stress levels so that a failure envelope can be obtained to be linearized. However, this involves a higher budget and time requirements that are often not available at the early stages of a project; thus faster and cheaper indirect methods have been developed as an alternative. In this paper, we use genetic programming (GP) to develop a predictive model to estimate the MC shear strength parameters of intact sandstone using other strength measures (the uniaxial compressive strength, UCS, and uniaxial tensile strength, UTS) under different stress conditions which shear failure takes place. The reliability of the proposed GP model is evaluated and compared with alternative linear regression models based on UCS or UTS only, and with the traditional triaxial-based approach. Results show that, although the triaxial method provides the better estimations, the proposed GP model has the best prediction performance in the absence of triaxial data, so that it can be used for practical strength estimations for intact sandstone at the early stage of projects or when triaxial test data are not available.

Modeling multiple-response environmental and manufacturing characteristics of EDM process

Among the machining operations, Electrical discharge machining (EDM) process is widely used in production industries because of its ability to machine the materials of any hardness. However, the machining of advanced materials including ceramics, composites, and super-alloys requiring the precise surface finish and dimensional accuracy also increases the energy consumption and cost simultaneously. As such, both environmental and economic performances are compromised. Also, EDM process is itself considered hazardous because of the large toxic liquid and solid wastes and gases produced due to reaction products developed from highly energized dielectric media placed between tool and workpiece. Thus, an appropriate balance between manufacturing and environmental aspects is highly desirable for ensuring higher productivity and environmental sustainability of the process. In this context, the present work proposes two variants of optimization approach of genetic programming (GP) in modeling the multi-response characteristics, i.e. two environmental aspects (thermal energy consumption and dielectric consumption) and one manufacturing aspect (relative tool to wear ratio) of the EDM process. These variants are proposed by introducing two model selection criteria from statistical learning theory to be used as fitness functions in the framework of GP. The performance of the proposed GP models is evaluated against the experimental data based on five statistical error metrics and the two hypothesis tests. Further, the relationships between manufacturing, environmental aspects and the input process parameters are unveiled, which can be used by industry users to optimize the process economically and environmentally. It was found that the input peak current has the highest impact on the environmental aspects of the EDM process.

Real‐time identification of traffic conditions prone to injury and non‐injury crashes on freeways using genetic programming

SummaryThis study applied the genetic programming (GP) model to identify traffic conditions prone to injury and property‐damage‐only (PDO) crashes in different traffic states on freeways. It was found that the traffic conditions prone to injury and PDO crashes can be classified into a high‐speed and a low‐speed traffic state. The random forest (RF) analyses were conducted to identify the contributing factors to injury and PDO crashes in these two traffic states. Four separate GP models were then developed to link the risks of injury and PDO crashes in two traffic states to the variables selected by the RF. An overall GP model was also developed for the combined dataset. It was found that the separate GP models that considered different traffic states and crash severity provided better predictive performance than the overall model, and the traffic flow variables that affected injury and PDO crashes were quite different across different traffic states. The proposed GP models were also compared with the traditional logistic regression models. The results suggested that the GP models outperformed the logistic regression models in terms of the prediction accuracy. More specifically, the GP models increased the prediction accuracy of injury crashes by 10.7% and 8.0% in the low‐speed and high‐speed traffic states. For PDO crashes, the GP models increased the prediction accuracy by 7.4% and 6.0% in the low‐speed and high‐speed traffic states. Copyright © 2016 John Wiley & Sons, Ltd.

Functionalized copper oxide–zinc oxide nanocomposite: synthesis and genetic programming model of dye adsorption

The functionalized copper oxide–zinc oxide nanocomposite (FCZN) was synthesized and characterized using Fourier transform infrared, scanning electron microscopy, X-ray diffraction, X-ray fluorescence, and BET. Dye removal from aqueous solution was done in a batch system using FCZN as an adsorbent. The effects of adsorbent dosage, initial dye concentration, pH, temperature, and additive salts on dye removal were investigated. Isotherms, kinetics, and thermodynamics of dye adsorption were studied. Equilibrium and kinetic data were fitted by Langmuir isotherm and pseudo-second-order kinetic, respectively. The thermodynamic data showed that dye adsorption was spontaneous, endothermic, and physical reaction. In addition, genetic programming (GP) was applied in order to predict dye removal using an explicit formula. The results of proposed GP models were in close agreement with the experimental data.

Evolution of Software Reliability Growth Models: A Comparison of Auto-Regression and Genetic Programming Models

reliability growth models to predict software reliability and identify and remove errors is both a necessity and a challenge for software testing engineers and project managers. Being able to predict the number of faults in software helps significantly in determining the software release date and in effectively managing project resources. Most of the growth models consider two or three parameters to estimate the accumulated faults in the testing process. Interest in using evolutionary computation to solve prediction and modeling problems has grown in recent years. In this paper, we explore the use of genetic programming (GP) as a tool to help in building growth models that can accurately predict the number of faults in software early on in the testing process. The proposed GP model is based on a recursive relation derived from the history of measured faults. The developed model is tested on real-time control, military, and operating system applications. The dataset was developed by John Musa of Bell Telephone Laboratories. The results of a comparison of the GP model with the traditional and simpler auto-regression model are presented. Keywordsreliability, genetic programming, evolutionary Computation

Rutting prediction of asphalt mixtures modified by polypropylene fibers via repeated creep testing by utilising genetic programming

A novel application of genetic programming (GP) for modelling and presenting closed form solutions to the rutting prediction for polypropylene (PP) modified asphalt mixtures is investigated. Various PP fibers have been utilised for bitumen modification and repeated creep (RC) tests have been carried out. Marshall specimens, fabricated with multifilament 3 mm (M-03) type PP fibers at optimum bitumen content of 5% have been tested under different load values and patterns at 50 °C to investigate their rutting potential. It has been shown that the service lives of PP fiber-reinforced Marshall specimens are respectively longer than the control specimens under the same testing conditions (5 to 12 times). Input variables in the developed GP model use the physical properties of Marshall specimens such as PP type, specimen height, unit weight, voids in mineral aggregate, voids filled with asphalt, air voids, rest period and pulse counts. The performance of the accuracy of the proposed GP model is observed to be quite satisfactory. To obtain the main effects plot, detailed parametric studies have been performed. The presented closed form solution will also help further researchers willing to perform studies on the prediction of the rutting potential of asphalt without carrying out destructive tests for similar type of aggregate sources, bitumen, aggregate gradation, modification technique and laboratory conditions.