Predicting discharge coefficient of triangular labyrinth weir using extreme learning machine,artificial neural network and genetic programming

Weirs are a type of hydraulic structure used to direct and transfer water flows in the canals and overflows in the dams. The important index in computing flow discharge over the weir is discharge coefficient (C _d). The aim of this study is accurate determination of the C _d in triangular labyrinth side weirs by applying three intelligence models [i.e., artificial neural network (ANN), genetic programming (GP) and extreme learning machine (ELM)]. The calculated discharge coefficients were then compared with some experimental results. In order to examine the accuracy of C _d predictions by ANN, GP and ELM methods, five statistical indices including coefficient of determination (R ²), root-mean-square error (RMSE), mean absolute percentage error (MAPE), SI and δ have been used. Results showed that R ² values in the ELM, ANN and GP methods were 0.993, 0.886 and 0.884, respectively, at training stage and 0.971, 0.965 and 0.963, respectively, at test stage. The ELM method, having MAPE, RMSE, SI and δ values of 0.81, 0.0059, 0.0082 and 0.81, respectively, at the training stage and 0.89, 0.0063, 0.0089 and 0.88, respectively, at the test stage, was superior to ANN and GP methods. The ANN model ranked next to the ELM model.

     

Neuro-genetic,neuro-imperialism and genetic programing models in predicting ultimate bearing capacity of pile

Prediction of pile-bearing capacity developing artificial intelligence models has been done over the last decade. Such predictive tools can assist geotechnical engineers to easily determine the ultimate pile bearing capacity instead of conducting any difficult field tests. The main aim of this study is to predict the bearing capacity of pile developing several smart models, i.e., neuro-genetic, neuro-imperialism, genetic programing (GP) and artificial neural network (ANN). For this purpose, a number of concrete pile characteristics and its dynamic load test specifications were investigated to select pile cross-sectional area, pile length, pile set, hammer weight and drop height as five input variables which have the most impacts on pile bearing capacity as the single output variable. It should be noted that all the aforementioned parameters were measured by conducting a series of pile driving analyzer tests on precast concrete piles located in Pekanbaru, Indonesia. The recorded data were used to establish a database of 50 test cases. With regard to data modelling, many smart models of neuro-genetic, neuro-imperialism, GP and ANN were developed and then evaluated based on the three most common statistical indices, i.e., root mean squared error (RMSE), coefficient determination (R²) and variance account for (VAF). Based on the simulation results and the computed indices’ values, it is observed that the proposed GP model with training and test RMSE values of 0.041 and 0.040, respectively, performs noticeably better than the proposed neuro-genetic model with RMSE values of 0.042 and 0.040, neuro-imperialism model with RMSE values of 0.045 and 0.059, and ANN model with RMSE values of 0.116 and 0.108 for training and test sets, respectively. Therefore, this GP-based model can provide a new applicable equation to effectively predict the ultimate pile bearing capacity.

     

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 (V_p) 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.

     

Comparison of genetic programming with neuro-fuzzy systems for predicting short-term water table depth fluctuations

This paper investigates the ability of genetic programming (GP) and adaptive neuro-fuzzy inference system (ANFIS) techniques for groundwater depth forecasting. Five different GP and ANFIS models comprising various combinations of water table depth values from two stations, Bondville and Perry, are developed to forecast one-, two- and three-day ahead water table depths. The root mean square errors (RMSE), scatter index (SI), Variance account for (VAF) and coefficient of determination (R²) statistics are used for evaluating the accuracy of models. Based on the comparisons, it was found that the GP and ANFIS models could be employed successfully in forecasting water table depth fluctuations. However, GP is superior to ANFIS in giving explicit expressions for the problem.     

Function identification for the intrinsic strength and elastic properties of granitic rocks via genetic programming (GP)

Symbolic Regression (SR) analysis, employing a genetic programming (GP) approach, was used to analyse laboratory strength and elasticity modulus data for some granitic rocks from selected regions in Turkey. Total porosity (n), sonic velocity (vp), point load index (Is) and Schmidt Hammer values (SH) for test specimens were used to develop relations between these index tests and uniaxial compressive strength (σ_c), tensile strength (σ_t) and elasticity modulus (E). Three GP models were developed. Each GP model was run more than 50 times to optimise the GP functions. Results from the GP functions were compared with the measured data set and it was found that simple functions may not be adequate in explaining strength relations with index properties. The results also indicated that GP is a potential tool for identifying the key and optimal variables (terminals) for building functions for predicting the elasticity modulus and the strength of granitic rocks.     

A hybrid computational approach to derive new ground-motion prediction equations

A novel hybrid method coupling genetic programming and orthogonal least squares, called GP/OLS, was employed to derive new ground-motion prediction equations (GMPEs). The principal ground-motion parameters formulated were peak ground acceleration (PGA), peak ground velocity (PGV) and peak ground displacement (PGD). The proposed GMPEs relate PGA, PGV and PGD to different seismic parameters including earthquake magnitude, earthquake source to site distance, average shear-wave velocity, and faulting mechanisms. The equations were established based on an extensive database of strong ground-motion recordings released by Pacific Earthquake Engineering Research Center (PEER). For more validity verification, the developed equations were employed to predict the ground-motion parameters of the Iranian plateau earthquakes. A sensitivity analysis was carried out to determine the contributions of the parameters affecting PGA, PGV and PGD. The sensitivity of the models to the variations of the influencing parameters was further evaluated through a parametric analysis. The obtained GMPEs are effectively capable of estimating the site ground-motion parameters. The equations provide a prediction performance better than or comparable with the attenuation relationships found in the literature. The derived GMPEs are remarkably simple and straightforward and can reliably be used for the pre-design purposes.     

Nonlinear mathematical modeling of seed spacing uniformity of a pneumatic planter using genetic programming and image processing

The purpose of this research was to represent the new laboratory test procedure that could be applicable in the field condition. Therefore, the performance of a pneumatic planter was investigated under laboratory conditions for maize, castor, fababean, sorghum, sugar beet, watermelon and cucumber seeds. The effect of operational speed [(1) 2.5–4 km/h and (2) 6–8.5 km/h] and vacuum pressure was evaluated by examining the quality of feed index, precision in spacing (coefficient of variation), miss index and multiple index. The most perfect operating parameter values for maize, castor, sorghum and sugar beet seeds were obtained at the first level of operating speed and 4.0 kPa pressure; for watermelon seed: second level of speed and 4.5 kPa pressure; and for cucumber seed: first level of speed and 4.5 kPa pressure. Furthermore, in order to determine the relationship between most important operating parameters affecting the performance of the pneumatic metering device and seed physical properties, regression models were developed using genetic programming (GP) algorithm. According to the results, the developed model using GP encompasses all physical properties of seeds as well as operational parameters. The model strongly describes the effect of investigated factors on seed spacing uniformity with values of the coefficient of determination R ² of 0.938, RMSE of 3.01 and MAE of 3.362087. Furthermore, the associated P value of 2.9851e−17 represents that the model is statistically significant. Model obtained from GP approach not only has a higher value of the coefficient of determination compared to regression model but is able to present the relationship between two operating parameters affecting the performance of row crop pneumatic metering device and seed physical properties, as well.

     

Genetic programing and non-linear multiple regression techniques to predict backbreak in blasting operation

In addition to all benefits of blasting in mining and civil engineering applications, it has some undesirable environmental impacts. Backbreak is an unwanted phenomenon of blasting which can cause instability of mine walls, decreasing efficiency of drilling, falling down of machinery, etc. Recently, the use of new approaches such as artificial intelligence (AI) is greatly recommended by many researchers. In this paper, a new AI technique namely genetic programing (GP) was developed to predict BB. To prepare a sufficient database, 175 blasting works were investigated in Sungun copper mine, Iran. In these operations, the most influential parameters on BB including burden, spacing, stemming length, powder factor and stiffness ratio were measured and used to develop BB predictive models. To demonstrate capability of GP technique, a non-linear multiple regression (NLMR) model was also employed for prediction of BB. Value account for (VAF), root mean square error (RMSE) and coefficient of determination (R ²) were used to control the capacity performance of the predictive models. The performance indices obtained by GP approach indicate the higher reliability of GP compared to NLMR model. RMSE and VAF values of 0.327 and 97.655, respectively, for testing datasets of GP approach reveal the superiority of this model in predicting BB, while these values were obtained as 0.865 and 81.816, respectively, for NLMR model.     

An equation-discovery approach to earthquake-ground-motion prediction

In active seismic regions an earthquake's peak ground acceleration (PGA) is required information when designing a building. In this study we employ the state-of-the-art, Lagramge, equation-discovery system to induce an equation that is suitable for modeling the PGA and investigate its applicability. In contrast to traditional modeling techniques the Lagramge system does not presume the structure of the equation and then identify the parameter values; instead, it finds the equation's structure as well. From the large amount of background knowledge on earthquake engineering we formalize a context-free grammar, which is then used as a guideline for the equation-building procedure. The PF-L data set used for the experiments is taken from the study of Peru? and Fajfar (2010), which is based on the data sets of Chiou et al. (2008) in the project Next Generation Attenuation of Ground Motion and the study of Akkar and Bommer (2010). The best model derived from the grammar is then quantitatively and qualitatively evaluated and compared. The presented results support the proposal to use an equation-discovery tool as an aid to the PGA modeling work and to potentially contribute new knowledge to the field of earthquake engineering.     

Feature extraction and dimensionality reduction by genetic programming based on the Fisher criterion

Abstract: Feature extraction helps to maximize the useful information within a feature vector, by reducing the dimensionality and making the classification effective and simple. In this paper, a novel feature extraction method is proposed: genetic programming (GP) is used to discover features, while the Fisher criterion is employed to assign fitness values. This produces non‐linear features for both two‐class and multiclass recognition, reflecting the discriminating information between classes. Compared with other GP‐based methods which need to generate c discriminant functions for solving c‐class (c>2) pattern recognition problems, only one single feature, obtained by a single GP run, appears to be highly satisfactory in this approach. The proposed method is experimentally compared with some non‐linear feature extraction methods, such as kernel generalized discriminant analysis and kernel principal component analysis. Results demonstrate the capability of the proposed approach to transform information from the high‐dimensional feature space into a single‐dimensional space by automatically discovering the relationships between data, producing improved performance.     

A spatial panel approach to the statistical assessment of seismic impacts and building damages: Case study of Taichung,Taiwan

A set of seismic-related statistical models is developed, using pseudo-data generated by an earthquake-engineering simulation model. The Peak Ground Acceleration (PGA) is the principal measure of seismic hazard, the Peak Ground Displacement (PGD) represents secondary impacts, and land-use patterns characterize urban vulnerability. A PGA model based on earthquake magnitude, epicenter-to-site distances, and source depth is formulated as a spatial lag panel (SLP) model to account for PGA spatial interactions (neighborhood effects). A PGD spatial lag panel model is also specified to account for soil liquefaction effects. Finally, a model of seismic damages to buildings is formulated, relating monetary damages (loss in property values) to seismic hazards (PGA and PGD) and urban vulnerabilities (residential, commercial, industrial, and facility building stocks). Pseudo-data are generated under 22 simulated historical seismic events for the city of Taichung, Taiwan. These data are then used for model estimation. By combining the three models, monetary damages can be estimated as a function of land-use patterns, PGA, PGD, their neighborhood effects, and other seismic characteristics. These models can therefore provide seismic information for policy making and help in allocating land to new activities while minimizing potential seismic damages.     

Sparse Gaussian Process regression model based on ℓ 1/2 regularization

Gaussian Process (GP) model is an elegant tool for the probabilistic prediction. However, the high computational cost of GP prohibits its practical application on large datasets. To address this issue, this paper develops a new sparse GP model, referred to as GPHalf. The key idea is to sparsify the GP model via the newly introduced ? _1/2 regularization method. To achieve this, we represent the GP as a generalized linear regression model, then use the modified ? _1/2 half thresholding algorithm to optimize the corresponding objective function, thus yielding a sparse GP model. We proof that the proposed model converges to a sparse solution. Numerical experiments on both artificial and real-world datasets validate the effectiveness of the proposed model.     

The prediction of heating energy consumption in a model house by using artificial neural networks in Denizli–Turkey

Turkey does not have petrol and natural gas reserves on a large scale. National energy resources are lignite and hydropower. Together with increasing environmental problems and diminishing fossil resources, studies focusing on energy reduction as well as usage of renewable energy resources have accelerated. However, taking the technological and economical impossibilities into account, the most logical solution is energy saving by providing energy efficiency in households. In this study, an artificial neural network (ANN) model is developed in order to predict hourly heating energy consumption of a model house designed in Denizli which is located in Central Aegean Region of Turkey. Hourly heating energy consumption of the model house is calculated by degree-hour method. ANN model is trained with heating energy consumption values of years 2004–2007 and tested with heating energy consumption values of year 2008. The training and test figures were depicted for February month of these years. Best estimate is found with 29 neurons and a good coherence is observed between calculated and predicted values. According to the results obtained, root-mean-squared error (RMSE), absolute fraction (R²) and mean absolute percentage error (MAPE) values are 1.2575, 0.9907, and 0.2091 for training phase and 1.2125, 0.9880, and 0.2081 for testing phase respectively.     

A Penman-Monteith evapotranspiration model with bulk surface conductance derived from remotely sensed spatial contextual information

ABSTRACT

A novel approach involving the use of the contextual information in a scatter plot of Moderate Resolution Imaging Spectrometer (MODIS) derived Land Surface Temperature versus Fraction of Vegetation (LST vs. F_v) has been proposed in this study to obtain pixel-wise values of bulk surface conductance (G_s) for use in the Penman-Monteith (PM) model for latent heat flux (λ_ET) estimation. Using a general expression for G_s derived by assuming a two-source total λ_ET (canopy transpiration plus soil evaporation) approach proposed by previous researchers, minimum and maximum values of G_s for a given region can be inferred from a trapezoidal scatter plot of pixel-wise values of LST and corresponding F_v. Using these as limiting values, G_s values for each pixel can be derived through interpolation and subsequently used with the PM model to estimate λ_ET for each pixel. The proposed methodology was implemented in 5 km × 5 km areas surrounding each of four flux towers located in tropical south-east Asia. Using climate data from the tower and derived G_s values the PM model was used to obtain pixel-wise instantaneous λ_ET values on six selected dates/times at each tower. Excellent comparisons were obtained between tower measured λ_ET and those estimated by the proposed approach for all four flux tower locations (R² = 0.85–0.96; RMSE = 18.27–33.79 W m^–2). Since the LST- F_v trapezoidal method is simple, calibration-free and easy to implement, the proposed methodology has the potential to provide accurate estimates of regional evapotranspiration with minimal data inputs.     

Estimation of dry matter content in leaves using normalized indexes and PROSPECT model inversion

This work applies remote sensing techniques to estimate dry matter (DM) content in tree leaves. Two methods were used to estimate DM content: a normalized index obtained from the radiative transfer model (RTM) leaf optical properties spectra (PROSPECT) in direct mode and the inversion of the PROSPECT model. The data were obtained from the Leaf Optical Properties Experiment 93 (LOPEX93) database, and only 11 species were used in this study. The species selection was based mainly on the availability of data on fresh and dry samples. The estimation of DM content was obtained from an exponential function that correlated the values of the index proposed, (R₂₃₀₅???R₁₄₉₅)/(R₂₃₀₅?+?R₁₄₉₅), against the DM content of fresh and dry leaf samples. The determination coefficient obtained (r ²?=?0.672) was higher than the coefficient obtained from the inversion of the PROSPECT model (r ²?=?0.507). The data set used to validate the normalized index was provided by the Accelerated Canopy Chemistry Program (ACCP). The determination coefficient between the values obtained from ACCP data and the values estimated for the normalized index was r ²?=?0.767.     

Computation of stabilizing PI-PD controllers

The PI-PD controller structure provides an excellent four-parameter controller for control of integrating, unstable and resonant processes to set point changes while the conventional PID controller has limitations in controlling such systems. In this paper, a graphical method for the computation of all stabilizing PI-PD controllers is given. The proposed method is based on plotting the stability boundary locus, which is a locus dependent on the parameters of the controller and frequency, in the parameter plane. The stability boundary loci are first obtained in the (K _d , K _f ) and (K _p , K _i ) planes and then it is shown that all the stabilizing values of the parameters of a PI-PD controller can be found. Computation of stabilizing PI-PD controllers which achieve user specified gain and phase margins is also studied. The method is used to design robust PI-PD controllers for control systems with parametric uncertainties. A design procedure for interval control systems is proposed. Examples are given to show the benefit of the method presented. Recommended by Editorial Board member Jietae Lee under the direction of Editor Young Il Lee. Nusret Tan was born in Malatya, Turkey, in 1971. He received his B.Sc. degree in Electrical and Electronics Engineering from Hacettepe University, Ankara, Turkey, in 1994. He received the Ph.D. degree in Control Engineering from University of Sussex, Brighton, U.K., in 2000. He is currently working as an Associate Professor in the Department of Electrical and Electronics Engineering at Inonu University, Malatya, Turkey. His primary research interest lies in the area of systems and control.     

Exact Schema Theory for Genetic Programming and Variable-Length Genetic Algorithms with One-Point Crossover

A few schema theorems for genetic programming (GP) have been proposed in the literature in the last few years. Since they consider schema survival and disruption only, they can only provide a lower bound for the expected value of the number of instances of a given schema at the next generation rather than an exact value. This paper presents theoretical results for GP with one-point crossover which overcome this problem. First, we give an exact formulation for the expected number of instances of a schema at the next generation in terms of microscopic quantities. Due to this formulation we are then able to provide an improved version of an earlier GP schema theorem in which some (but not all) schema creation events are accounted for. Then, we extend this result to obtain an exact formulation in terms of macroscopic quantities which makes all the mechanisms of schema creation explicit. This theorem allows the exact formulation of the notion of effective fitness in GP and opens the way to future work on GP convergence, population sizing, operator biases, and bloat, to mention only some of the possibilities.     

Performance evaluation of hybrid FFA-ANFIS and GA-ANFIS models to predict particle size distribution of a muck-pile after blasting

Accurately predicting the particle size distribution of a muck-pile after blasting is always an important subject for mining industry. Adaptive neuro-fuzzy inference system (ANFIS) has emerged as a synergic intelligent system. The main contribution of this paper is to optimize the premise and consequent parameters of ANFIS by firefly algorithm (FFA) and genetic algorithm (GA). To the best of our knowledge, no research has been published that assesses FFA and GA with ANFIS for fragmentation prediction and no research has tested the efficiency of these models to predict the fragmentation in different time scales as of yet. To show the effectiveness of the proposed ANFIS-FFA and ANFIS-GA models, their modelling accuracy has been compared with ANFIS, support vector regression (SVR) and artificial neural network (ANN). Intelligence predictions of fragmentation by ANFIS-FFA, ANFIS-GA, ANFIS, SVR and ANN are compared with observed values of fragmentation available in 88 blasting event of two quarry mines, Iran. According to the results, both ANFIS-FFA and ANFIS-GA prediction models performed satisfactorily; however, the lowest root mean square error (RMSE) and the highest correlation of determination (R²) values were obtained from ANFIS-GA model. The values of R² and RMSE obtained from ANFIS-GA, ANFIS-FFA, ANFIS, SVR and ANN models were equal to (0.989, 0.974), (0.981, 1.249), (0.956, 1.591), (0.924, 2.016) and (0.948, 2.554), respectively. Consequently, the proposed ANFIS-GA model has the potential to be used for predicting aims on other fields.

     

Bare surface soil moisture retrieval from the synergistic use of optical and thermal infrared data

Land surface soil moisture (SSM) is crucial to research and applications in hydrology, ecology, and meteorology. To develop a SSM retrieval model for bare soil, an elliptical relationship between diurnal cycles of land surface temperature (LST) and net surface shortwave radiation (NSSR) is described and further verified using data that were simulated with the Common Land Model (CoLM) simulation. In addition, with a stepwise linear regression, a multi-linear model is developed to retrieve daily average SSM in terms of the ellipse parameters x₀ (horizontal coordinate of the ellipse centre), y₀ (vertical coordinate of the ellipse centre), a (semi-major axis), and θ (rotation angle), which were acquired from the elliptical relationship. The retrieval model for daily average SSM proved to be independent of soil type for a given atmospheric condition. Compared with the simulated daily average SSM, the proposed model was found to be of higher accuracy. For eight cloud-free days, the root mean square error (RMSE) ranged from 0.003 to 0.031 m³ m^?3, while the coefficient of determination (R²) ranged from 0.852 to 0.999. Finally, comparison and validation were conducted using simulated and measured data, respectively. The results indicated that the proposed model showed better accuracy than a recently reported model using simulated data. A simple calibration decreased RMSE from 0.088 m³ m^?3 to 0.051 m³ m^?3 at Bondville Companion site, and from 0.126 m³ m^?3 to 0.071 m³ m^?3 at the Bondville site. Coefficients of determination R² = 0.548 and 0.445 were achieved between the estimated daily average SSM and the measured values at the two sites, respectively. This paper suggests a promising avenue for retrieving regional SSM using LST and NSSR derived from geostationary satellites in future developments.     

Landslides and catchment sedimentation in the Ta-Chia River influenced by the 1999 Taiwan Chi-Chi earthquake

In the Ta-Chia River catchment, large numbers of landslides were induced by the 1999 Chi-Chi earthquake (M _w?=?7.6), during which about 1.5?×?10⁶ m³ of earth was driven from broken slopes. The impact of this earthquake not only increased fracturing of the bedrocks but also changed the river morphology of the Western Foothills area. The main purpose of this study is to investigate the correlation of catchment sedimentation and landslides before and after the 1999 Chi-Chi earthquake. The study comprises two major parts: the preparation of databases of landslide inventory and catchment sedimentation and analyses of the correlation of catchment sedimentation and landslides. A conceptual model is developed to investigate the control factors of catchment sedimentation. Multi-variable analysis was applied to study the impact of landslides, triggered by the typhoons Herb (1996), Toraji (2001) and Mindulle (2004), on sediment production and sediment transportation.