Search

The research aims to classify alluvial fans' morphometric properties using the SOM algorithm. It also determines the relationship between morphometric characteristics and erosion rate and lithology using the GMDH algorithm. For this purpose, alluvial fans of 4 watersheds in Iran are extracted semi-automatically using GIS and digital elevation model (DEM) analysis. The relationships between 25 morphometric features of these watersheds, the amount of erosion, and formation material are investigated using the self-organizing map (SOM) method. Principal component analysis (PCA), Greedy, Best first, Genetic search, Random search as feature selection algorithms are used to select the most important parameters affecting erosion and formation material. The group method of data handling (GMDH) algorithm is employed to predict erosion and formation material based on morphometries. The results indicated that the semi-automatic method in GIS could detect alluvial fans. The SOM algorithm determined that the morphometric factors affecting the formation material were fan length, minimum height of fan, and minimum fan slope. The main factors affecting erosion were fan area (Af) and minimum fan height (Hmin-f). The feature selection algorithm identified (Hmin-f), maximum fan height (Hmax-f), minimum fan slope, and fan length (Lf) to be the morphometries most important for determining formation material, and basin area, fan area, (Hmax-f) and compactness coefficient (Cirb) were the most important characteristics for determining erosion rates. The GMDH algorithm predicted the fan formation materials and rates of erosion with high accuracy (R2 = 0.94, R2 = 0.87). [ABSTRACT FROM AUTHOR]

The research aims to classify alluvial fans' morphometric properties using the SOM algorithm. It also determines the relationship between morphometric characteristics and erosion rate and lithology using the GMDH algorithm. For this purpose, alluvial fans of 4 watersheds in Iran are extracted semi-automatically using GIS and digital elevation model (DEM) analysis. The relationships between 25 morphometric features of these watersheds, the amount of erosion, and formation material are investigated using the self-organizing map (SOM) method. Principal component analysis (PCA), Greedy, Best first, Genetic search, Random search as feature selection algorithms are used to select the most important parameters affecting erosion and formation material. The group method of data handling (GMDH) algorithm is employed to predict erosion and formation material based on morphometries. The results indicated that the semi-automatic method in GIS could detect alluvial fans. The SOM algorithm determined that the morphometric factors affecting the formation material were fan length, minimum height of fan, and minimum fan slope. The main factors affecting erosion were fan area (Af) and minimum fan height (Hmin-f). The feature selection algorithm identified (Hmin-f), maximum fan height (Hmax-f), minimum fan slope, and fan length (Lf) to be the morphometries most important for determining formation material, and basin area, fan area, (Hmax-f) and compactness coefficient (Cirb) were the most important characteristics for determining erosion rates. The GMDH algorithm predicted the fan formation materials and rates of erosion with high accuracy (R2 = 0.94, R2 = 0.87). [ABSTRACT FROM AUTHOR]

Energy shortages, air pollution, and stringent environmental requirements have been gaining increasing concern. Since the scarcity of energy resources, it is imperative to consider the economic and environmental issues of growth in manufacturing. This paper presented an energy evaluation method (considering cutting edges, workpiece hardness, material removal rate, and rotation speed) for machining system based on the group method of data handling (GMDH) algorithm. First, a response surface experimental was carried out with three materials to determine whether the cutting edges, workpiece hardness, spindle speed, and material removal rate (MRR) affect the processing energy. It was concluded that cutting edges number and hardness obviously have a significant influence on energy consumption. Then, further experimentations were designed, and an evaluation model of the electrical energy demand based on GMDH algorithm has been proposed, in which the application in a milling machine tool indicates that the predicted output values were found to correlate closely with the measured values. Finally, the proposed model is applied to a workpiece machining process, and the results show that the approach presented in this paper is effective, and hence, this paper provides an important addition to existing machining processes energy-evaluating methods. [ABSTRACT FROM AUTHOR]

The Zambezi watershed is essential for water supply, irrigation, fishing activities, and river transport of the populations of Southern Africa. The importance and variability of these water resources make it necessary to develop studies that may help understand and manage them. Despite this need, water resources studies for this region are still scarce. Therefore, the present work aims to present a strategy for forecasting the daily water flow of the Zambezi River in the Cahora Bassa dam, located in Mozambique, an important energy producer in the country and the fourth largest dam in Africa. Historical rainfall, evaporation, and humidity records collected from 2003 to 2011 are used for training and testing a model that forecasts water flow using the Group Method of Data Handling algorithm. The results achieved were compared, through error metrics, with those of other models to prove the effectiveness of the assembled model. They revealed that the proposed model achieves a satisfactory performance for the forecast horizon and could become a helpful tool in monitoring hydrographic basins and forecasting their daily streamflow values. [ABSTRACT FROM AUTHOR]

Group Method of Data Handling (GMDH) - type neural network algorithm is the heuristic self-organizing algorithm to model the sophisticated systems. In this study, we propose a new algorithm assembling different classifiers based on GMDH algorithm for binary classification. A Monte Carlo simulation study is conducted to compare diverse classifier ensemble based on GMDH (dce-GMDH) algorithm to the other well-known classifiers and to give recommendations for applied researchers on the selection of appropriate classifier under the different conditions. The simulation study illustrates the proposed approach is more successful than the other classifiers in classification in most scenarios generated under the different conditions. Our proposed method is compared to the other classifiers on Cleveland heart disease data. An implementation of the proposed approach is demonstrated on urine data. Moreover, the proposed algorithm is released under R package GMDH2 under the name of "dceGMDH" for implementation. [ABSTRACT FROM AUTHOR]

Banks, financial, and credit institutions encountering the weakening financial system and increased risk factors cause high inflation and great losses for an economy. Detecting financial risks in advance could help financial institutions avoid losses, and the financial system could be eventually affected less. Early warning systems for banks could be helpful to identify financial risks and take measures to deal with hazardous situations. Various approaches have already been put forward. However, inaccuracy issues in risk detection are one of the main issues. Combining semantic hierarchy with the GMDH neural network to predict financial risks is proposed. A semantic hierarchy approach based on converting risk-related values and picking influential variables could be practical in risk detection. Besides, the GMDH algorithm utilizing neural networks based on available data has the capability of predicting possible risks that could occur in the future. The outcomes of the proposed method when compared to non-data mining methods suggest that it improves accuracy by almost 20%. [ABSTRACT FROM AUTHOR]

Asphaltene precipitation is the reason behind some of the most destructive issues in the oil industry such as wettability alteration, formation plugging, and reduction of the relative permeability. There are different experimental and modeling methods to study the asphaltene phase behavior. However, those approaches are either time-consuming or costly. In addition, the prediction of asphaltene precipitation is challenging due to the nonlinear dependence. Therefore, in this study, three advanced computational algorithms including group method of data handling (GMDH), emotional neural network (ENN), and minimax probability machine regression (MPMR) are developed and applied to the comprehensive dataset to estimate the amount of asphaltene precipitation as the function of temperature, dilution ratio, and the molecular weight of the n-alkanes. Many different performance metrics are used to evaluate the predictive performance of intelligent algorithms. Obtained results of the modeling reveal that intelligent computational algorithms have a great ability to mimic the nonlinear relationships between the target variable and its influential variables. The results indicate MPMR as the best predictive model with the highest R-squared value on both training and testing datasets with values of R2 = 0.992 and R2 = 0.991, respectively. In addition, MPMR is compared and outperformed empirical correlations. [ABSTRACT FROM AUTHOR]

Developing fragility functions is the essential step in incorporating important uncertainties in next-generation performance-based earthquake engineering (PBEE) methodology. The present paper is aimed to involve record-to-record variability as well as modelling uncertainty sources in developing the fragility curves at the collapse limit state. In this article, in order to reduce the dispersion of uncertainties, Group Method of Data Handling (GMDH) in combination with Monte Carlo Simulation (MCS) is used to develop structural collapse fragility curve, considering effects of epistemic and aleatory uncertainties. A Steel Moment Resisting Frame (SMRF) is chosen as the tested structure. The fragility curves obtained by the proposed method which belongs to GMDH approaches are compared with those resulted from simple and well-known available methods such as First-Order Second-Moment (FOSM), Approximate Second-Order Second-Moment (ASOSM) and Monte Carlo (MC)/Response Surface Method (RSM), somehow, as an accurate method. The results of the application of the proposed approach indicate increasing accuracy and precision of the outputs as well as power with the same computational time compared to aforementioned methods. The GMDH method introduced here can be applied to the other performance levels. [ABSTRACT FROM AUTHOR]

Precise knowledge of thermal contact conductance (TCC) across fixed solid contacts of flat-flat and curvilinear surfaces is becoming a crucial topic in advanced industrial applications such as thermal management of electronic packaging and nuclear energy production. In this study, at first, TCC across fixed solid contacts of flat-flat and cylinder-cylinder contacts has been calculated by inverse solution method. Furthermore, the accuracy of inverse method for estimation of TCC between flat-flat and cylinder-cylinder contacts has been evaluated based on the error analysis. Then, the GMDH (group method of data handling) algorithm has been used for heat transfer function estimation between contact surfaces based on input–output data which has been achieved from the experimental investigation and the inverse method using the Conjugate Gradient Method (CGM) with Adjoint problem. Different models of GMDH algorithm are applied and the optimal model is selected based on the common error criteria of RMSE (root mean square error). According to the results, the inverse method is accurate enough to predict TCC between flat-flat and cylinder-cylinder contacts with the root mean square error of 0.167 and 0.205, respectively. Also, it has shown that among the different models of GMDH algorithm, Genetic algorithm obtained by SVD method, make the best algorithm for TTC identification in fixed flat-flat and cylinder-cylinder contacting surfaces. Meanwhile, the attained Root Mean Square Error (RMSE) of the Genetic algorithm obtained by SVD method compared with the experimental results for flat-flat and cylinder-cylinder are 0.1459 and 0.1758, respectively. [ABSTRACT FROM AUTHOR]

In this paper, the evaluation procedures of the natural frequency and the stress intensity factor in the opening mode are established for the Euler–Bernoulli cracked beam by using (a) a technique in the framework of the finite element method, (b) a group method of data handling (GMDH), and (c) the software ABAQUS software. In the first one, the stiffness and mass matrices of the beam are enriched according to the depth and location of the crack for the determination of the natural frequency. A discrete spring model is used to simulate the crack in the structure based on the energy release rate. The continuity conditions in a cracked element are applied to connect two sub-elements of both sides of the crack. In the second method, the natural frequency and the stress intensity factor are determined using the GMDH algorithm. Design of experiments technique is employed to create an optimum arrangement for the application in the GMDH neural network. A few case studies are examined to investigate the results of the analysis, in addition, to identify the priority and the comparison of the three methods. The procedure of the analysis explains the advantages and limitations of the finite element-based technique, the GMDH method, and ABAQUS. [ABSTRACT FROM AUTHOR]

• A new method is developed for flood flow prediction in ungauged basins. • New method uses fewer inputs and without regionalization, yet more accurate. • Classic Group Method of Data Handling algorithms were improved using new encoding. The lack of stream gauging data worldwide has inspired an abundance of methods attempting to predict the complex natural process of streamflow. A set of traditional regression equations have been developed by the U.S. Geological Survey for the state of Iowa. However, several inconsistencies were noted, including irregular region definition and varying input parameters between regions. To overcome the common problems faced in modelling, and to combat the irregularities in the regression equations, a new Group Method of Data Handling (GMDH) algorithm has been proposed using a combination of the classical combinatorial GMDH and multilayer GMDH to predict the 2-year peak flow. Data from 365 stream gauges located in the state of Iowa were used in the model development. The new algorithm was compared to the two classical algorithms and the traditional linear regression equations developed by the U.S. Geological Survey. The new algorithm which requires fewer input parameters without relying on regionalization was found to be the best method. The developed algorithm is based on a more robust hydrologic theory and therefore is a reliable method for predicting the 2-year peak flow for ungauged basins. The two main hypotheses inspired by the past regression equations and suggested in this study were that regionalization is not necessary and that using fewer input parameters to avoid redundancy still produces a robust prediction method. This study has developed a novel and reliable prediction method for peak flow prediction at ungauged basins while advancing insight into the most influential variables governing the magnitude of the flow. [ABSTRACT FROM AUTHOR]

The tunnel boring machine (TBM), developed within the past few decades, is designed to make the process of tunnel excavation safer and more economical. The use of TBMs in civil and mining construction projects is controlled by several factors including economic considerations and schedule deadlines. Hence, improved methods for estimating TBM performance are important for future projects. This paper presents a new model based on the group method of data handling (GMDH) for predicting the penetration rate (PR) of a TBM. In order to achieve this aim, after investigation of the most effective parameters of PR, rock quality designation, uniaxial compressive strength, rock mass rating, Brazilian tensile strength, weathering zone, thrust force per cutter and revolutions per minute were selected and measured to estimate TBM PR. A database composed of 209 datasets was prepared according to the mentioned model inputs and output. Then, based on the most influential factors of GMDH, a series of parametric investigations were carried out on the established database. In the following, five different datasets with different sets of training and testing were selected and used to construct GMDH models. Aside from that, five multiple regression (MR) models/equations were also proposed to predict TBM PR for comparison purposes. After that, a ranking system was used in order to evaluate the obtained results. As a result, performance prediction results of [i.e. coefficient of determination (R2) = 0.946 and 0.924, root mean square error (RMSE) = 0.141 and 0.169 for training and testing datasets, respectively] demonstrated a high accuracy level of GMDH model in estimating TBM PR. Although both methods are applicable for estimation of PR, GMDH is able to provide a higher degree of accuracy and can be introduced as a new model in this field. [ABSTRACT FROM AUTHOR]

Highlights • ITS of modified asphalt is higher than conventional asphalt. • Model values showed a very good regression with the experimental results. • Performance of HMA modified with silica is improved. • Nano-silica can improve moisture sensitivity of asphalt Mixtures. • Use of nano silica resulted in a significant increase in compressive strength. Abstract The primary objectives of the design and implementation of asphalt pavement on road and road surfaces are to achieve the best performance in different climatic conditions. Asphalt pavement performance depends on the adhesion and bonding of binder and aggregates that the moisture causes it to disappear and it results in bleeding and stripping. Although the moisture susceptibility mechanism is not fully known, factors such as binder properties, aggregates properties, asphalt mixture properties, quality control during congestion, the dynamic effect of traffic load and the type of anti-stripping additive play a significant role in creating a moisture susceptibility and aggravation of failures. In this paper, Group Method of Data Handling (GMDH)-type neural networks have been used for modeling and prediction of moisture susceptibility of nano silica-modified asphalt concrete. To achieve this goal, 5 types of mixtures with different percentage of nano-silica (0, 0.2, 0.4, 0.7 & 0.9%) were prepared and the moisture susceptibility of modified mixtures was evaluated. Results showed that nano-silica can improve the moisture susceptibility of asphalt mixtures. For modeling, the experimental data were divided into train and test sections (70% for training and 30% for testing). The predicted values were compared with those of experimental values in order to estimate the performance of the GMDH-neural network. The model values showed a very good regression with the experimental results. [ABSTRACT FROM AUTHOR]

The maximum dry density (γd,max) and optimum moisture content (ωopt) determined from the results of the Proctorr test are very important for geotechnical engineering and earth structures. As the Proctor test is relatively time consuming and laborious, in present research Group Method of Data Handling (GMDH) type neural network (NN) is used to estimate the compaction parameters (γd,max and ωopt) of soils indirectly from more simply determined index properties such as liquid limit (LL), plastic limit (PL) and fine-grained content (FC) as well as sand content (SC). A database containing 212 data-sets were used for the training and testing of the models. A comparison was carried out between the experimentally measured compaction parameters with the predictions in order to evaluate the performance of the GMDH method. The results demonstrate that generalised GMDH-type NN has a great ability for prediction of the γd,max and ωopt. At the end, sensitivity analysis of the obtained model has been carried out to study the influence of input parameters on model outputs, and shows that the LL and PL are the most influential parameters on the compaction parameters. [ABSTRACT FROM AUTHOR]

Abstract Piano Key Side Weirs (PKSW) are new devices that are used to discharge the additional flow in hydraulic structures. The main objective of performing these structures is to enhance the performance of the traditional side weirs. In this paper based on GMDH and DGMDH methods, discharge coefficient (C d) of PKSW has been predicted and compared using experimental data. To this end 239 experiments were conducted on type-C of PKSWs in rigid curved channel. Data were collected in two position angles on the curved channel, namely; 30° and 120°. Results of Cd (after data normalization) obtained by the mentioned two methods showed that the algorithm DGMDH presents a better performance than the other technique. In fact, R2, MAE and RMSE values for testing data in DGMDH technique are 0.938, 0.0372 and 0.053, respectively, while these values for GMDH are 0.875, 0.0501 and 0.0792, respectively. Highlights • Piano Key Side Weirs (PKSW) are new devices that are used to discharge the additional flow in hydraulic structures. • Discharge coefficient (Cd) of PKSW is to be predicted and compared using experimental data. • Rigid curved channel including type-C of PKSWs is used to collect 239 experimental data. • Data were collected in two position angles on the curved channel, namely; 30° and 120°. • The algorithm DGMDH presents a better performance than the other technique. [ABSTRACT FROM AUTHOR]

The importance of severe accident management is being re-examined because severe accident management failed during the Fukushima nuclear accident. Having an accurate estimation of a severe accident is important for coping properly with unfavorable conditions. In this study, the extended group method of data handling (GMDH) with a fuzzy concept is proposed as a means of predicting the major severe accident events that represent the severe accident management guideline (SAMG) entry time, including the time at which the reactor vessel (RV) water level decreases, the time when the core exit temperature (CET) reaches 450 degrees-centigrade, the time when the hydrogen concentration in the containment is over 4%, and the time when the reactor coolant system (RCS) pressure is over 2.86 MPa under loss of coolant accidents (LOCAs) in pressurized water reactors (PWRs). To train the extended GMDH model, it was necessary to acquire the data needed from a number of numerical simulations due to the lack of actual LOCA data. The data was obtained by carrying out simulations using the MAAP5 code. To optimize the developed model, the optimal input selection processes were performed using the clustering analysis including self-organizing feature map (SOFM), hierarchical and non-hierarchical clustering methods. The prediction accuracy of the three types of initiating accident, small break (SB), medium break (MB), and large break (LB) LOCAs, was high enough to predict the SAMG entry time. When compared with other artificial intelligence (AI) methods, the extended GMDH was found to be superior to the original GMDH and support vector regression (SVR). Therefore, it is expected that the extended GMDH model will help operators to properly mitigate severe accidents in PWRs. [ABSTRACT FROM AUTHOR]

The status of nuclear power plants’ conditions must be checked to avoid initial events which may eventually lead to accidents. Axial power and axial offset (AO) are key parameters which are usually used to state 3-dimensional core power peaking, in the form of a practical parameter. Group method of data handling (GMDH) has a wide range of applications. Here, a GMDH is used and modified as an efficient method to predict the axial power and AO of the reactor core as well as fuel assemblies. In this paper, axial power offset of the whole reactor core is reconstructed by using in-core detectors. By using the developed GMDH algorithm, the optimum relationship between the independent in-core detector signals and the dependent variables, the core axial power and AO, is determined. Two separate sets of big data are prepared and analyzed. The first set includes power at each of 24 axial nodes at different core states. The second set is similar to the first set except as it also contains fuel assembly data. [ABSTRACT FROM AUTHOR]

Forecasting daily traffic flow in the future is one of the most critical components in traffic management to improve operational efficiency. This article aims to address the daily traffic flow forecasting problem given historical data. Because the traffic flow pattern is strongly correlated with contextual factors, we propose a match‐then‐predict method which integrates contextual matching and time series prediction based on group method of data handling (GMDH) algorithm. From a Seattle‐based case study, we show that the contextual matching can significantly improve the prediction accuracy. We also show that the proposed method can in general outperform alternative prediction methods in daily traffic flow forecasting in terms of prediction accuracy. In addition, further analysis using data from other cities and applying the proposed method to forecast speed also support the benefits of the proposed method against alternative prediction methods. [ABSTRACT FROM AUTHOR]

Thermal conductivity of nanofluids depends on several parameters including temperature, concentration, and size of nanoparticles. Most of the proposed models utilized concentration and temperature as influential factors in their modeling. In this study, group method of data handling (GMDH) artificial neural networks is applied in order to model the dependency of thermal conductivity on the mentioned factors. Firstly, temperature and concentration considered as inputs and a model is represented. Afterwards, the size of nanoparticles is added to the input variables and the results are compared. Based on obtained results, GMDH is an appropriate method to predict thermal conductivity of the nanofluids. In addition, it is necessary to consider size of nanoparticles in order to have a more precise model. [ABSTRACT FROM AUTHOR]

CO2 emission depends on several parameters. Due to environmental issues, it is necessary to find influential factors on CO2 emission as one of the most critical greenhouse gases. Type of utilized fuels and their share in total primary energy consumption, Gross Domestic Product (GDP) as an indicator for economic activities and the share of renewable energies play key role in the amount of CO2 emission. In the present study, Group method of data handling (GMDH) is applied in order to model CO2 emission as a function of consumption of various fuels, renewable energies and GDP. Obtained data showed that GMDH is an appropriate approach to predict CO2 emission. Comparing between actual data and GMDH output indicates that the R -squared value for the proposed model is equal to 0.998 which shows its high accuracy. In addition, it is observed that the highest absolute error by using GMDH artificial neural network is lower than 4%. The absolute relative error for more than 66% of data is lower than 1% which is another criterion demonstrating acceptable accuracy of the proposed model. [ABSTRACT FROM AUTHOR]

The brain activity observed on EEG electrodes is influenced by volume conduction and functional connectivity of a person performing a task. When the task is a biometric test the EEG signals represent the unique “brain print”, which is defined by the functional connectivity that is represented by the interactions between electrodes, whilst the conduction components cause trivial correlations. Orthogonalization using autoregressive modeling minimizes the conduction components, and then the residuals are related to features correlated with the functional connectivity. However, the orthogonalization can be unreliable for high-dimensional EEG data. We have found that the dimensionality can be significantly reduced if the baselines required for estimating the residuals can be modeled by using relevant electrodes. In our approach, the required models are learnt by a Group Method of Data Handling (GMDH) algorithm which we have made capable of discovering reliable models from multidimensional EEG data. In our experiments on the EEG-MMI benchmark data which include 109 participants, the proposed method has correctly identified all the subjects and provided a statistically significant (p<0.01) improvement of the identification accuracy. The experiments have shown that the proposed GMDH method can learn new features from multi-electrode EEG data, which are capable to improve the accuracy of biometric identification. [ABSTRACT FROM AUTHOR]

Existence of debris structures inevitably ascends the rate of scour process around bridge piers and flow area not only lead into remarkable deviation of flow but also increase the velocity around bridge piers. A myriad of experimental and field studies to understand effective parameters on the scour depth with debris effects were conducted. To reach permissible values of the scour depth for the practical uses, relationships extracted in previous investigations suffer from lack of generalization for experimental data ranges. In this way, neuro-fuzzy group method of data handling (NF-GMDH)-based self-organized models is applied to evaluate the pier scour depth. In this study, NF-GMDH network is implemented using evolutionary algorithms listed particle swarm optimization (PSO), gravitational search algorithm (GSA), and genetic algorithm (GA). In all, 243 experimental datasets including a wide range of input and output parameters to develop the proposed models were compiled from various literature. The efficiency of NF-GMDH networks for training and testing stages was perused. NF-GMDH-PSO model provided the scour depth with more precise predictions (root mean squared error (RMSE) = 0.388 and scatter index (SI) = 0.343) in comparison with NF-GMDH-GA (RMSE = 0.402 and SI = 0.361) and NF-GMDH-GSA (RMSE = 0.456 and SI = 0.407) networks. In addition, blockage ratio (ΔA) was taken into account as the most sumptuous parameter with utmost level of effectiveness using the sensitivity analysis. [ABSTRACT FROM AUTHOR]

Purpose: Machine learning classification algorithms (classifiers) for prediction of treatment response are becoming more popular in radiotherapy literature. General Machine learning literature provides evidence in favor of some classifier families (random forest, support vector machine, gradient boosting) in terms of classification performance. The purpose of this study is to compare such classifiers specifically for (chemo)radiotherapy datasets and to estimate their average discriminative performance for radiation treatment outcome prediction. Methods: We collected 12 datasets (3496 patients) from prior studies on post‐(chemo)radiotherapy toxicity, survival, or tumor control with clinical, dosimetric, or blood biomarker features from multiple institutions and for different tumor sites, that is, (non‐)small‐cell lung cancer, head and neck cancer, and meningioma. Six common classification algorithms with built‐in feature selection (decision tree, random forest, neural network, support vector machine, elastic net logistic regression, LogitBoost) were applied on each dataset using the popular open‐source R package caret. The R code and documentation for the analysis are available online ( https://github.com/timodeist/classifier_selection_code). All classifiers were run on each dataset in a 100‐repeated nested fivefold cross‐validation with hyperparameter tuning. Performance metrics (AUC, calibration slope and intercept, accuracy, Cohen's kappa, and Brier score) were computed. We ranked classifiers by AUC to determine which classifier is likely to also perform well in future studies. We simulated the benefit for potential investigators to select a certain classifier for a new dataset based on our study (pre‐selection based on other datasets) or estimating the best classifier for a dataset (set‐specific selection based on information from the new dataset) compared with uninformed classifier selection (random selection). Results: Random forest (best in 6/12 datasets) and elastic net logistic regression (best in 4/12 datasets) showed the overall best discrimination, but there was no single best classifier across datasets. Both classifiers had a median AUC rank of 2. Preselection and set‐specific selection yielded a significant average AUC improvement of 0.02 and 0.02 over random selection with an average AUC rank improvement of 0.42 and 0.66, respectively. Conclusion: Random forest and elastic net logistic regression yield higher discriminative performance in (chemo)radiotherapy outcome and toxicity prediction than other studied classifiers. Thus, one of these two classifiers should be the first choice for investigators when building classification models or to benchmark one's own modeling results against. Our results also show that an informed preselection of classifiers based on existing datasets can improve discrimination over random selection. [ABSTRACT FROM AUTHOR]

Relative permittivities, refractive indices, and densities of the various binary systems containing three primary diols (1,3-propanediol, 1,4-butanediol, and 1,5-pentanediol) and three similar structurally related aliphatic ketones (dimethyl-, diethyl-, and methyl ethyl-ketones) were measured and analyzed over the whole composition range at T = 298.15 K and p = 101.3 kPa. Various approaches were used to coherent data analysis and accomplish the purpose of the study. The formulations of the Kumbharkhane et al. and the Winkelmann-Quitzsch are required for a coherent interpretation and understanding of these binary systems. The experimental data of the binary systems and pure liquids were used to calculate the excess parameters, namely excess permittivity, excess free energy, excess molar volume, and excess refractive index. In this study, a Group Method of Data Handling (GMDH) type neural network was used to correlate the permittivity data. The proposed model gives excellent agreement with the experimental data. The model is shown to be appropriate for predicting the permittivity data. [ABSTRACT FROM AUTHOR]

Neural network-based methods such as deep neural networks show great efficiency for a wide range of applications. In this paper, a deep learning-based hybrid approach to forecast the yearly revenue passenger kilometers time series of Australia's major domestic airlines is proposed. The essence of the approach is to use a resilient error backpropagation algorithm with dropout for "tuning" the polynomial neural network, obtained as a result of a multi-layered GMDH algorithm. The article compares the performance of the suggested algorithm on the time series with other popular forecasting methods: deep belief network, multi-layered GMDH algorithm, Box-Jenkins method and the ANFIS model. The minimum reached MAE of the proposed algorithm was approximately 25% lower than the minimum MAE of the next best method - GMDH, thus indicating that the practical application of the algorithm can give good results compared with other well-known methods. [ABSTRACT FROM AUTHOR]

Analysis of slope stability failures, as one of the complex natural hazards, is one of the important research issues in the field of civil engineering. Present paper adopts and investigates four soft computing-based techniques for this problem: Patient Rule-Induction Method (PRIM), M5' algorithm, Group Method of data Handling (GMDH) and Multivariate Adaptive Regression Splines (MARS). A comprehensive database consisting of 168 case histories is used to calibrate and test the developed models. Six predictive variables including slope height, slope angle, bulk density, cohesion, angle of internal friction, and pore water pressure ratio were considered to generate new models. The results of test studies are used for feasibility, effectiveness and practicality comparison of techniques with each other, and with the other available well-known methods in the literature. Results show that all methods not only are feasible but also result in better performance than previously developed soft computing based predictive models and tools. It is shown that M5' and PRIM algorithms are the most effective and practical prediction models. [ABSTRACT FROM AUTHOR]

Virtual metrology (VM) is drawing more and more attention in the recent research of wafer to wafer control for semiconductor manufacturing. Although many different approaches for VM have been proposed, the adaptiveness of these approaches in feature selection and model complexity selection is still less discussed and most of the current researches rely on the summary statistics of the trace signals. In this work, an adaptive methodology based on the group method of data handling (GMDH) type polynomial neural networks is proposed to address these issues. In the proposed methodology, the processes for model selection and feature selection are fully automatic, and enhanced model performance can be achieved by employing two new types of features. To show the effectiveness of the propose methodology, the dataset from prognostics and health management (PHM) data challenge 2016 is employed to predict the material removal rate for the chemical-mechanical planarization process in semiconductor fabrication. The validation results report improved accuracy in comparison with several candidate methods, and the successful application of the proposed method suggests that the proposed method can be an effective tool for the virtual metrology in semiconductor manufacturing. [ABSTRACT FROM AUTHOR]

Real-time prediction of tidal level is of great significance for activities of human beings in the fields of marine and coastal engineering. However, the disturbance factors of tidal level are very intricate, which deteriorate the tidal prediction accuracy. To improve the accuracy of real-time tidal-level prediction, a modular real-time tidal-level prediction approach is proposed based on the grey group method of data handling (Grey-GMDH) neural network. The modular model is composed of astronomical tide parts caused by celestial bodies’ movement and the nonastronomical tide parts caused by various meteorological and other environmental factors. The GMDH is a polynomial network that is commonly used in prediction and pattern recognition. However, GMDH is sensitive to nondeterministic time series, which would result in low accuracy of prediction. In this study, the grey prediction theory is introduced into the GMDH prediction model to alleviate the unfavorable effects of uncertainty caused by various environmental factors and the adverse effects caused thereby on the prediction accuracy. In this study of tidal prediction, the Grey-GMDH model is used to predict the nonastronomical tide parts, whereas the conventional harmonic analysis model is used to predict the astronomical tide parts. The final prediction result is achieved by combining the estimation outputs of the harmonious analysis model and the Grey-GMDH model. Measured tidal-level data of San Diego tidal station is selected as the testing database. Simulation and experimental results confirm that the proposed approach can achieve real-time predictions for tidal level with high accuracy, satisfactory convergence and stability. [ABSTRACT FROM AUTHOR]

In the present study group method of data handling (GMDH) type of artificial neural networks are used to model deviation angle ( θ), total pressure loss coefficient ( ω), and performance loss coefficient ( ξ) in wet steam turbines. These parameters are modeled with respect to four input variables, i.e., stagnation pressure ( P ), stagnation temperature ( T ), back pressure ( P ), and inflow angle ( β). The required input and output data to train the neural networks has been taken from numerical simulations. An AUSM-Van Leer hybrid scheme is used to solve two-phase transonic steam flow numerically. Based on results of the paper, GMDH-type neural networks can successfully model and predict deviation angle, total pressure loss coefficient, and performance loss coefficient in wet steam turbines. Absolute fraction of variance ( R ) and root-mean-squared error related to total pressure loss coefficient ( ω) are equal to 0.992 and 0.002, respectively. Thus GMDH models have enough accuracy for turbomachinery applications. [ABSTRACT FROM AUTHOR]

Several efforts have been made to describe cars by adjectives, however there is no particular work exploring adjectives describing yacht hulls which motivates this study. First, a novel design schema is developed for representing yacht hulls in 3D, which is parametric based and includes several geometric parameters quantifying the hull models. Three surveys are then conducted to learn the relationship between hulls and hull adjectives. In the first survey, yacht models with different geometries are shown to participants to form the hull adjective dictionary. Next, geometric parameters having no impact on the hull adjectives are eliminated via the second survey. Hull adjectives are then matched with yacht hull models via the third survey. The models shown in the third survey are obtained by performing sampling using the Taguchi experimental method. Finally, GMDH-type neural network (GMDH) is applied to the data sets obtained from the third survey to determine the relationships between the hull adjectives and the geometric parameters. GMDH provides mathematical models for each adjective consisting of geometric parameters with coefficients. With the outcomes of this work, we expect that communication between designers and customers can be easier, and adjective based design variations of yacht hulls can be achieved in a shorter amount of time. [ABSTRACT FROM AUTHOR]

Global sensitivity analysis (GSA) is a very useful tool to evaluate the influence of input variables in the whole distribution range. Sobol' method is the most commonly used among variance-based methods, which are efficient and popular GSA techniques. High dimensional model representation (HDMR) is a popular way to compute Sobol' indices, however, its drawbacks cannot be ignored. We show that modified GMDH-NN algorithm can calculate coefficients of metamodel efficiently, so this paper aims at combining it with HDMR and proposes GMDH-HDMR method. The new method shows higher precision and faster convergent rate. Several numerical and engineering examples are used to confirm its advantages. [ABSTRACT FROM AUTHOR]

As transport sector takes a big share of the whole energy consumption in China, it is crucial to predict its energy demand. To forecast China's transport energy demand, group method of data handling ( GMDH) was introduced. The model can help policymakers' select influential variables and build prediction models automatically. Furthermore, it can reduce the negative impact of the noise in the Chinese statistical data. To produce comparable results, four of the six data sets used in this paper contain the same variables as in previously published research. Artificial neural networks ( ANN), GMDH, multiple linear regression ( MLR), and support vector machine ( SVM) models were trained using fivefold cross-validation. The performance of these models was measured in terms of coefficient of determination and root mean square error. Results showed that GMDH achieved better performance than the other models. Finally, projections were made with two scenarios. Both of the projected results showed that the energy demands peak in certain years and then decrease gradually. This study suggests that GDP is not the essential variable, while urbanization rate is an important variable to forecast the transport energy demand in China. It also suggests that Chinese government needs to prepare for the development and deployment of transport energy. [ABSTRACT FROM AUTHOR]

Data dimension reduction is an important step for customer classification modeling, and feature selection has been a research focus of the data dimension reduction field. This study introduces the group method of data handling (GMDH), puts forward a GMDH-based semi-supervised feature selection (GMDH-SSFS) algorithm, and applies it to customer feature selection. The algorithm can utilize a few samples with class labels L , and a large number of samples without class labels U simultaneously. What is more, it considers the relationship between features and class labels, and that between features during feature selection. The GMDH-SSFS model mainly consists of three stages: 1) Train N basic classification models based on the dataset L with class labels; 2) Label samples selectively in the dataset U without class labels, and add them to L ; 3) Train the GMDH neural network based on the new training set L , and select the optimal feature subset F S . Based on an empirical analysis of four customer classification datasets, results suggest that the features selected by the GMDH-SSFS model have a good explainability. Meanwhile, the customer classification performance of the classification model trained by the selected feature subset is superior to that of the models trained by the commonly used Laplacian score (an unsupervised feature selection algorithm), Fisher score (a supervised feature selection algorithm), and the FW-SemiFS and S3VM-FS (two semi-supervised feature selection algorithms). [ABSTRACT FROM AUTHOR]

In this communication, four different generalized methods have been developed to estimate the normal boiling points of pure chemical compounds by using multilayer perceptron (MLP) and radial basis function (RBF) neural networks, least square support vector machine (LSSVM) and group method of data handling (GMDH). In order to develop the models, experimental data of 563 pure compounds were gathered from literature sources. The collected data includes data points from 13 different groups including: paraffins; cycloparaffins; monooleffins and dioleffins; cyclooleffins and actylens; benzene derivatives; condensed ring aromatics and derivatives; acids, alcohols, and phenols and aldehydes; amines and nitrogen containing compounds; esters; ethers, ketones; halogenated hydrocarbons; and sulfur containing hydrocarbons. The prediction results using the proposed models are compared to three of the previously developed methods for estimating the normal boiling point using statistical and graphical error analyses. Comparisons show that all of the proposed models are more reliable and accurate than the available methods. Average absolute percent relative errors of the proposed MLP, RBF, LSSVM and GMDH are 3.41%, 2.65%, and 3.11% and 3.78%, respectively. The developed method based on RBF is selected as the most accurate predictive model, while the GMDH model has the advantage of estimating normal boiling point through a simple mathematical correlation without any need to computers. To find out the outliers and applicability domain of the proposed models and prove that our models are statistically valid, Leverage approach was used. The results indicate that only small percent of the experimental dataset are located out of the applicability domain of the developed models. [ABSTRACT FROM AUTHOR]

High mountain systems are predicted to be especially vulnerable to the impact of climate change, with the climatically-constrained tree limit rapidly shifted upslope. In turn, the impact of upward treeline migration on mountain-dwelling bird species is expected to significantly reduce habitat suitability. We developed the first projection of the expected climate-driven rise of the whole treeline (19,256 km) of the Italian Alps. The study area extends over 20,700 km 2 , ranging over 550 km in longitude and 320 km in latitude. We then investigated how much the expected treeline rise will induce a) shrinking and shifting of the elevation range and b) loss in suitable habitat for the flagship species rock ptarmigan, an alpine bird species dwelling above the treeline and, similarly to many other alpine species, highly vulnerable to treeline rise. We also investigated the potential gain in suitable habitat for rock ptarmigan due to the climate-driven upshift in the uppermost thermal limit. At lower altitudes (1500–1600 m a.s.l.), the average expected upshift in the current treeline resulted in 195, 274 and 354 m over the short (2010–2039), medium (2040–2069) and long term (2070–2099) respectively. Above 2400 m a.s.l., it was less than 30 m even in the long term. Overall, during the three climate periods the extent of suitable habitat for rock ptarmigan above the current treeline is projected to decrease by 28.12%, 38.43% and 49.11% respectively. In contrast, the expected gain in suitable habitat due to the shift in the uppermost thermal limit will be severely restrained by the limited surface extension in the top portion of the Italian Alps. The presented approach can promote similar studies elsewhere in the globe, providing a regional perspective to the projection of climate change impact on bird species dwelling above the treeline. [ABSTRACT FROM AUTHOR]

A precise model of a counter-flow indirect dew-point evaporative cooler was developed using the group method of data handling-type neural network while the network was trained by extracted data from a validated numerical model. After validating the model, it was employed in a multi-objective optimization problem that implements the non-dominated sorting genetic algorithm-II method. The system was optimized in diverse climatic conditions. In this regard, Yazd, Masjed-Soleiman and Ahvaz were chosen as representatives of cities with hot, hot semi-humid and hot-humid climates in Iran. In each city, optimum values of channel length, channel gap, inlet air velocity and return to intake air ratio were found so that these decision variables maximize the average coefficient of performance and minimize the specific area of the cooler, simultaneously. The results indicated that the developed model can predict the supply air temperature accurately with less than 1 °C error and due to its quick calculation process it is possible to optimize the design based on hourly climate data without any needs to very fast processors. Moreover, using the optimization, the coefficient of performance and specific area for the system designed to be used in Yazd were improved 36.3% and 30.9%, respectively. This figure at Masjed-Soleiman and Ahvaz was 16% and 7.92% improvement in the specific area at the cost of 2.63% and 2.19% reduction in the coefficient of performance, respectively. These improvements allowed the system to reach its full potential and making dew-point evaporative coolers as a suitable cooling system in diverse climatic conditions. [ABSTRACT FROM AUTHOR]

Estimation of natural gas viscosity is essential for accurate analysis of gas reserves, reservoir simulation and optimum gas consumption. The general method for calculation of gas viscosity is to conduct experimental tests, however, these tests are normally time consuming and expensive as well as sometimes even impossible at some specific pressure and temperature conditions. In this study, a group method of data handling (GMDH)-type neural network was utilized to predict the viscosity of pure hydrocarbon and gas mixtures containing heavy components and impurities such as carbon dioxide, helium and nitrogen by using more than 3800 data points. First, the data sets were divided into three parts based on their density. Next, a model was developed for each part as a function of molecular weight, pseudo reduced temperature, pseudo reduced pressure and density. The proposed models were compared to 13 well-known models by performing graphical and statistical error analyses. The results indicate that the average absolute percent relative error of the proposed GMDH models is 3.45% and the standard deviation from experimental data is 0.0566. Error distribution curves indicate that the proposed models are able to accurately estimate natural gas viscosity over a wide range of pressure and temperature conditions as no significant error trend is observed in the predictions. Finally, the results of relevancy factor analysis showed that the mixture density has the largest impact on viscosity compared to the other input parameters. [ABSTRACT FROM AUTHOR]

In this article, a novel approach based on game theory is presented for multi-objective optimal synthesis of four-bar mechanisms. The multi-objective optimization problem is modelled as a Stackelberg game. The more important objective function, tracking error, is considered as the leader, and the other objective function, deviation of the transmission angle from 90° (TA), is considered as the follower. In a new approach, a group method of data handling (GMDH)-type neural network is also utilized to construct an approximate model for the rational reaction set (RRS) of the follower. Using the proposed game-theoretic approach, the multi-objective optimal synthesis of a four-bar mechanism is then cast into a single-objective optimal synthesis using the leader variables and the obtained RRS of the follower. The superiority of using the synergy game-theoretic method of Stackelberg with a GMDH-type neural network is demonstrated for two case studies on the synthesis of four-bar mechanisms. [ABSTRACT FROM AUTHOR]

The PSO – based GMDH network model forecasting method is composed. On the basis of the introduction for two methods, PSO and GMDH, the optimized model, method and operation flow of the PSO – based GMDH network are basically introduced. Accordingly on this basis, preciseness of GMDH network forecasting and PSO – based GMDH network forecasting is verified by adapting forecasting volume of Shenzhen import and export trade; the Shenzhen import and export trade is fitting forecasted by single GMDH network and PSO – based GMDH network respectively. The simulation experiment reaches a conclusion that the PSO – based GMDH network is able to acquire better forecasting result compared with single GMDH network. [ABSTRACT FROM AUTHOR]

In this research, the group method of data handling (GMDH) networks is applied for estimating the significant process variables of a commercial scale thermal cracking (visbreaking) unit. This model can predict the fuel oil viscosity, severity and yield of products i.e. fuel oil, gasoline and light gasses by using a grand polynomial correlation which is a function of flow rate, viscosity and initial boiling point of feed, furnace outlet temperature, and steam flow rate. To this fifty data points research, are obtained from the target plant during a life cycle about 422 days. Then, the GMDH network uses 70% of these data points for self-training while using the remained ones for the validation step. The results show that the developed network can precisely estimate the fuel oil product properties during the life of the process. Moreover, it is confirmed that the proposed model is capable of predicting severity, gas, gasoline and fuel oil product yields, and fuel oil viscosity with the average absolute deviation (AAD%) of 0.462%, 0.448%, 0.458%, 0.051%, and 0.016%, respectively. Moreover, the root mean square error (RMSE %) of the mentioned parameters are 0.717%, 0.709%, 0.716%, 0.078% and 0.025%, respectively. [ABSTRACT FROM AUTHOR]

The velocity at limit of deposition, namely, the velocity below which the sediments start to form stationary deposits on the pipe invert, plays a key role in designing an effective storm sewer system. In fact, an accurate evaluation of the aforesaid velocity permits to prevent the formation of sediment deposits in the pipe, and, consequently, a decreasing of the hydraulic capacity of the same pipe. Nowadays, different methods based on artificial intelligence are applied to analyze and solve problems of scientific and practical interest, among which the analysis of sediment transport mechanism in clean storm sewer networks. In this study, neuro-fuzzy based group method of data handling (NF-GMDH), an adaptive learning network, has been utilized to predict the velocity at limit of deposition in partially-filled circular storm sewer networks under noncohesive bed load sediment transport and clean pipe conditions. The NF-GMDH network has been developed using the particle swarm optimization (PSO). Four different dimensionless groups have been used as input parameters to evaluate the dimensionless velocity at limit of deposition (or, equivalently, the densimetric particle Froude number at limit of deposition) through the NF-GMDH-PSO model. A published experimental data sets were collected from the literature to train and test the adaptive learning network used in this study. The performances of training and testing stages for NFGMDH-PSO have been evaluated using specific statistical indexes. The results showed that NF-GMDH-PSO model is able to give more accurate predictions of the velocity at limit of deposition compared with those obtained using semiempirical equations. [ABSTRACT FROM AUTHOR]

Prediction of pavement condition is one of the most important issues in pavement management systems. In this paper, capabilities of artificial neural networks (ANNs) and group method of data handling (GMDH) methods in predicting flexible pavement conditions were analysed in three levels: in 1 year, in 2 years (short term) and in the pavement life cycle (long term). For this purpose, three effective groups on pavement condition including traffic conditions, environmental changes and pavement structures were studied and nine effective variables were selected as input variables. International roughness index (IRI) was also used as the indicator of pavement performance. Various ANN structures and GMDH models in partial description configurations of 1st, 2nd, 3rd and 4th polynomials were formed and examined. Results indicate that while ANN models predict future condition of pavement with high accuracy in the short and long terms, GMDH models do not have accepted accuracy. [ABSTRACT FROM AUTHOR]

To determine the minimum velocity required to prevent sedimentation, six different models were proposed to estimate the densimetric Froude number (Fr). The dimensionless parameters of the models were applied along with a combination of the group method of data handling (GMDH) and the multi-target genetic algorithm. Therefore, an evolutionary design of the generalized GMDH was developed using a genetic algorithm with a specific coding scheme so as not to restrict connectivity configurations to abutting layers only. In addition, a new preserving mechanism by the multi-target genetic algorithm was utilized for the Pareto optimization of GMDH. The results indicated that the most accurate model was the one that used the volumetric concentration of sediment (CV), relative hydraulic radius (d/R), dimensionless particle number (Dgr) and overall sediment friction factor (λs) in estimating Fr. Furthermore, the comparison between the proposed method and traditional equations indicated that GMDH is more accurate than existing equations. [ABSTRACT FROM AUTHOR]

In this study a newly developed thin-walled structure with the combination of circular and square sections is investigated in term of crashworthiness. The results of the experimental tests are utilized to validate the Abaqus/Explicit™ finite element simulations and analysis of the crush phenomenon. Three polynomial metamodels based on the evolved group method of data handling (GMDH) neural networks are employed to simply represent the specific energy absorption (SEA), the initial peak crushing load (P1) and the secondary peak crushing load (P2) with respect to the geometrical variables. The training and testing data are extracted from the finite element analysis. The modified genetic algorithm NSGA-II, is used in multi-objective optimisation of the specific energy absorption, primary and secondary peak crushing load according to the geometrical variables. Finally, in each optimisation process, the optimal section energy absorptions are compared with the results of the finite element analysis. The nearest to ideal point and TOPSIS optimisation methods are applied to choose the optimal points. [ABSTRACT FROM AUTHOR]

GMDH, which stands for Group Method Data Handling, is an evolutionary type of neural network. It has received much attention in the supercomputing research community because of its ability to optimize its internal structure for maximum prediction accuracy. GMDH works by evolving itself from a basic network, expanding its number of neurons and hidden layer until no further performance gain can be obtained. Earlier on, the authors proposed a novel strategy that extends existing GMDH neural network techniques. The new strategy, called residual-feedback, retains and reuses past prediction errors as part of the multivariate sample data that provides relevant multivariate inputs to the GMDH neural networks. This is important because the strength of GMDH, like any neural network, is in predicting outcomes from multivariate data, and it is very noise-tolerant. GMDH is a well-known ensemble type of prediction method that is capable of modeling highly non-linear relations. Maximum accuracy is often achieved by using only the minimum amount of network neurons and simplest layered structure. This paper contributes to the technical design of implementing GMDH on GPU memory where all the weight computations run on parallel GPU memory blocks. It is a first step towards developing complex neural network architecture on GPU with the capability of evolving and expanding its structure to minimally sufficient for obtaining the maximum prediction accuracy based on the given input data. [ABSTRACT FROM AUTHOR]

In this paper, the control theory is applied to assist the estimation of state of health (SoH) which is a key parameter to battery management. Battery can be treated as a system, and the internal state, e.g. SoH, can be observed through certain system output data. Based on the philosophy of human health and athletic ability estimation, variables from a specific process, which is a constant current charge subprocess, are obtained to depict battery SoH. These variables are selected according to the differential geometric analysis of battery terminal voltage curves. Moreover, the relationship between the differential geometric properties and battery SoH is modelled by the group method of data handling (GMDH) polynomial neural network. Thus, battery SoH can be estimated by GMDH with inputs of voltage curve properties. Experiments have been conducted on different types of Li-ion battery, and the results show that the proposed method is valid for SoH estimation. [ABSTRACT FROM AUTHOR]

A model was presented to determine product air properties of dew-point indirect evaporative coolers with cross flow heat exchanger, M-cycle CrFIEC. In this regard, the most powerful statistical method known as the group method of data handling-type neural network (GMDH) was employed. Then the developed GMDH model was implemented for multi-objective optimization of a prototype CrFIEC and the average annual values of coefficient of performance (COP) and cooling capacity (CC) were maximized, simultaneously, while working to air ratio (WAR) and inlet air velocity were decision variables of optimization. Accordingly, features of the proposed system were optimized at twelve diverse climates of the world based on Koppen–Geiger's classification. Results implied that the optimized inlet air velocity for all climates varied between 1.796 and 1.957 m.s −1 , while the optimum WAR was 0.318 for “A” class cities. Moreover, the mean values of the COP and CC were improved 8.1% and 6.9%, respectively. [ABSTRACT FROM AUTHOR]

The author utilized neuro-fuzzy based group method of data handling (NF-GMDH) to predict the local scour depth around pile groups under clear-water conditions. They collected the datasets from literature. To predict the local scour by using NF-GMDH, nine dimensional parameters were considered to define a functional relationship between input and output variables. The results of NF- GMDH networks were compared with that of the empirical equations. However, the collected datasets for pile group scouring, the method of implementing the empirical formula to calculate scour depth, and using the equation of Sheppard et al. (2004) suggested for single pier to predict local scouring around pile groups merits this discussion. Here, we will establish that a part of applied data and also some of the implemented equations were not related to pile group scour. The empirical formulations were not employed correctly too and all the conclusions and results of the paper are disbelieving. Finally, we will discuss on the wide use of various artificial intelligent methods. [ABSTRACT FROM AUTHOR]

Application of polarity scales and artificial neural network for direct modeling of liquid-liquid separation process was investigated. A simple add-in, named FeedGen, was developed for reproducing the feed data and expanding the liquid-liquid equilibrium pattern. It was concluded that solvatochromic polarity scales method cannot be used as a wide-range approach for direct modeling liquid-liquid equilibrium systems and is only applicable for limited set of data. In comparison, artificial neural networks reproduce features of these systems, satisfactorily well. Multilayered back propagation and GMDH type neural networks were compared in modeling the liquid-liquid ternary systems. It was shown that well-trained networks even could reproduce the outlier data, at different compositions and/or temperatures, acceptably. [ABSTRACT FROM AUTHOR]

The group method of data handling (GMDH) technique was used to predict heat transfer and friction characteristics in heat exchanger tubes equipped with wire-rod bundles. Nusselt number and friction factor were determined as functions of wire-rod bundle geometric parameters and Reynolds number. The performance of the developed GMDH-type neural networks was found to be superior in comparison with the proposed empirical correlations. For optimization, the genetic algorithm-based multi-objective optimization was applied. [ABSTRACT FROM AUTHOR]