Estimation of pressuremeter modulus and limit pressure of clayey soils by various artificial neural network models

The main purpose of the present study is to develop some artificial neural network (ANN) models for the prediction of limit pressure (P _L) and pressuremeter modulus (E _M) for clayey soils. Moisture content, plasticity index, and SPT values are used as inputs in the ANN models. To get plausible results, the number of hidden layer neurons in all models is varied between 1 and 5. In addition, both linear and nonlinear activation functions are considered for the neurons in output layers while a nonlinear activation function is employed for the neurons in the hidden layers of all models. Logistic activation function is used as a nonlinear activation function. During the modeling studies, total eight different ANN models are constructed. The ANN models having two outputs produced the worst results, independent from activation function. However, for P _L, the best results are obtained from the feed-forward neural network with five neurons in the hidden layer, and logistic activation function is employed in the output neuron. For E _M, the best model producing the most acceptable results is Elman recurrent network model, which has 4 neurons in the neurons in the hidden layer, and linear activation function is used for the output neuron. Finally, the results show that the ANN models produce the more accurate results than the regression-based models. In the literature, when empirical equations based on regression analysis were used, the best root mean square error (RMSE) values obtained to date for P _L and E _M have been 0.43 and 5.65, respectively. In this study, RMSE values for P _L and E _M were found to be 0.20 and 2.99, respectively, by using ANN models. It was observed that using ANN approach drastically increases the prediction accuracy in terms of RMSE criterion.     

Prediction of feed abrasive value by artificial neural networks and multiple linear regression

In order to evaluate rapid testing methods based on the relationship between feed abrasive value (FAV) and physicochemical properties (particle size, bulk density, dry matter (DM), soluble dry matter, water-holding capacity (WHC), ash, crud protein, neutral detergent fiber (NDF), physically effective NDF and non-fibrous carbohydrates (NFC)), 100 empirical dataset were used. Relationships were investigated using multiple linear regression (MLR) and artificial neural networks (ANNs). The mean relative error was significantly (P?<?0.01) lower for ANN than MLR model. Globally, the non-linear ANN model approach is shown to provide a better prediction of FAV than linear multiple regression.     

Calibrating artificial neural networks by global optimization

Artificial neural networks (ANNs) are used extensively to model unknown or unspecified functional relationships between the input and output of a “black box” system. In order to apply the generic ANN concept to actual system model fitting problems, a key requirement is the training of the chosen (postulated) ANN structure. Such training serves to select the ANN parameters in order to minimize the discrepancy between modeled system output and the training set of observations. We consider the parameterization of ANNs as a potentially multi-modal optimization problem, and then introduce a corresponding global optimization (GO) framework. The practical viability of the GO based ANN training approach is illustrated by finding close numerical approximations of one-dimensional, yet visibly challenging functions. For this purpose, we have implemented a flexible ANN framework and an easily expandable set of test functions in the technical computing system Mathematica. The MathOptimizer Professional global-local optimization software has been used to solve the induced (multi-dimensional) ANN calibration problems.     

Prediction of first lactation 305-day milk yield in Karan Fries dairy cattle using ANN modeling

In this paper, an artificial neural network (ANN) model is proposed to predict the first lactation 305-day milk yield (FLMY305) using partial lactation records pertaining to the Karan Fries (KF) crossbred dairy cattle. A scientifically determined optimum dataset of representative breeding traits of the cattle is used to develop the model.Several training algorithms, viz., (i) gradient descent algorithm with adaptive learning rate; (ii) Fletcher–Reeves conjugate gradient algorithm; (iii) Polak–Ribiére conjugate gradient algorithm; (iv) Powell–Beale conjugate gradient algorithm; (v) Quasi-Newton algorithm with Broyden, Fletcher, Goldfarb, and Shanno (BFGS) update; and (vi) Levenberg–Marquardt algorithm with Bayesian regularization; along with various network architectural parameters, i.e., data partitioning strategy, initial synaptic weights, number of hidden layers, number of neurons in each hidden layer, activation functions, regularization factor, etc., are experimentally investigated to arrive at the best model for predicting the FLMY305.Also, a multiple linear regression (MLR) model is developed for the milk-yield prediction. The performances of ANN and MLR models are compared to assess the relative prediction capability of the former model.It emerges from this study that the performance of ANN model seems to be slightly superior to that of the conventional regression model. Hence, it is recommended that the ANNs can potentially be used as an alternative technique to predict FLMY305 in the KF cattle.     

人工神经网络方法研究含硫芳香衍生物毒性与结构的关系

结合逐步线性回归方法与人工神经网络方法，研究了含硫芳香衍生物对发光细菌毒性的构效关系，充分表明了两个方法的互补，回归方法为网络方法提供变量的物理解释，网络方法建立精确的构效关系模型，人工神经网络方法在非线民生较强的构效关系研究中起到重要的作用，基于交叉检验，本文还提出了防止人工神经网络方法过拟合现象发生的ｒ判据，对于建立较好的预报模型，具有一定的普遍意义。     

基于支持向量机回归的麻醉药毒性的QSPR研究

采用支持向量机回归(SVR)方法研究了39个麻醉药毒性的定量构效关系,基于留一法交叉验证的结果,模型的相关系数为0.970。结果表明,所建SVR模型的精度高于逆传播人工神经网络(BPANN)、多元线性回归(MLR)和偏最小二乘法(PLS)所得的结果。     

Semiparametric ARX neural-network models with an application toforecasting inflation

We examine semiparametric nonlinear autoregressive models with exogenous variables (NLARX) via three classes of artificial neural networks: the first one uses smooth sigmoid activation functions; the second one uses radial basis activation functions; and the third one uses ridgelet activation functions. We provide root mean squared error convergence rates for these ANN estimators of the conditional mean and median functions with stationary β-mixing data. As an empirical application, we compare the forecasting performance of linear and semiparametric NLARX models of US inflation. We find that all of our semiparametric models outperform a benchmark linear model based on various forecast performance measures. In addition, a semiparametric ridgelet NLARX model which includes various lags of historical inflation and the GDP gap is best in terms of both forecast mean squared error and forecast mean absolute deviation error     

Online implementation of an adaptive calibration technique for displacement measurement using LVDT

The paper presents the design and validation of an online intelligent displacement measurement technique with Linear Variable Differential Transformer (LVDT) using Artificial Neural Network (ANN). The objectives of the proposed work are to design a calibration technique using an optimised neural network model such that it a) produces an output which is linear for the full scale of input range, b) makes the output independent of the variations in supply frequency, the physical parameters of the LVDT, and ambient temperature. The output of an LVDT is converted to a DC signal by using a rectifier circuit. The rectified output is further amplified using a differential amplifier. This voltage signal is acquired onto a computer for further processing using an ANN. The optimisation of the ANN is carried out to find the minimum number of hidden layers along with the number of neurones in each layer to give least Mean Square Error (MSE) and Regression (R) nearing to one. This optimisation is done considering various schemes of ANN, training algorithms, and the transfer function of neurones. Once the ANN model is designed, it is subjected to test with both simulated data and experimental validation. The results confirm the successful achievement of the objectives of this paper and thus avoiding the need for repeated calibration.     

A novel hybrid data-driven model for multi-input single-output system simulation

Artificial neural network (ANN)-based data-driven model is an effective and robust tool for multi-input single-output (MISO) system simulation task. However, there are several conundrums which deteriorate the performance of the ANN model. These problems include the hard task of topology design, parameter training, and the balance between simulation accuracy and generalization capability. In order to overcome conundrums mentioned above, a novel hybrid data-driven model named KEK was proposed in this paper. The KEK model was developed by coupling the K-means method for input clustering, ensemble back-propagation (BP) ANN for output estimation, and K-nearest neighbor (KNN) method for output error estimation. A novel calibration method was also proposed for the automatic and global calibration of the KEK model. For the purpose of intercomparison of model performance, the ANN model, KNN model, and proposed KEK model were applied for two applications including the Peak benchmark function simulation and the real-world electricity system daily total load forecasting. The testing results indicated that the KEK model outperformed other two models and showed very good simulation accuracy and generalization capability in the MISO system simulation tasks.

     

Performance of radial basis and LM-feed forward artificial neural networks for predicting daily watershed runoff

This study investigated the effects of upstream stations’ flow records on the performance of artificial neural network (ANN) models for predicting daily watershed runoff. As a comparison, a multiple linear regression (MLR) analysis was also examined using various statistical indices. Five streamflow measuring stations on the Cahaba River, Alabama, were selected as case studies. Two different ANN models, multi layer feed forward neural network using Levenberg–Marquardt learning algorithm (LMFF) and radial basis function (RBF), were introduced in this paper. These models were then used to forecast one day ahead streamflows. The correlation analysis was applied for determining the architecture of each ANN model in terms of input variables. Several statistical criteria (RMSE, MAE and coefficient of correlation) were used to check the model accuracy in comparison with the observed data by means of K-fold cross validation method. Additionally, residual analysis was applied for the model results. The comparison results revealed that using upstream records could significantly increase the accuracy of ANN and MLR models in predicting daily stream flows (by around 30%). The comparison of the prediction accuracy of both ANN models (LMFF and RBF) and linear regression method indicated that the ANN approaches were more accurate than the MLR in predicting streamflow dynamics. The LMFF model was able to improve the average of root mean square error (RMSE_ave) and average of mean absolute percentage error (MAPE_ave) values of the multiple linear regression forecasts by about 18% and 21%, respectively. In spite of the fact that the RBF model acted better for predicting the highest range of flow rate (flood events, RMSE_ave/RBF = 26.8 m³/s vs. RMSE_ave/LMFF = 40.2 m³/s), in general, the results suggested that the LMFF method was somehow superior to the RBF method in predicting watershed runoff (RMSE/LMFF = 18.8 m³/s vs. RMSE/RBF = 19.2 m³/s). Eventually, statistical differences between measured and predicted medians were evaluated using Mann-Whitney test, and differences in variances were evaluated using the Levene's test.     

Comparison of artificial neural network and combined models in estimating spatial distribution of snow depth and snow water equivalent in Samsami basin of Iran

Snow water equivalent (SWE) is a key parameter in hydrological cycle, and information on regional SWE is required for various hydrological and meteorological applications, as well as for hydropower production and flood forecasting. This study compares the snow depth and SWE estimated by multivariate linear regression (MLR), discriminant function analysis, ordinary kriging, ordinary kriging-multivariate linear regression, ordinary kriging-discriminant function analysis, artificial neural network (ANN) and neural network-genetic algorithm (NNGA) models. The analysis was performed in the 5.2 km² area of Samsami basin, located in the southwest of Iran. Statistical criteria were used to measure the models’ performances. The results indicated that NNGA, ANN and MLR methods were able to predict SWE at the desirable level of accuracy. However, the NNGA model with the highest coefficient of determination (R ² = 0.70, P value < 0.05) and minimum root mean square error (RMSE = 0.202 cm) provided the best results among the other models. The lower SWE values were registered in the east of study area and higher SWE values appeared in the west of study area where altitude was higher.     

Modeling glass-forming ability of bulk metallic glasses using computational intelligent techniques

Modeling the glass-forming ability (GFA) of bulk metallic glasses (BMGs) is one of the hot issues ever since bulk metallic glasses (BMGs) are discovered. It is very useful for the development of new BMGs for various engineering applications, if GFA criterion modeled precisely. In this paper, we have proposed support vector regression (SVR), artificial neural network (ANN), general regression neural network (GRNN), and multiple linear regression (MLR) based computational intelligent (CI) techniques that model the maximum section thickness (D_max) parameter for glass forming alloys. For this study, a reasonable large number of BMGs alloys are collected from the current literature of material science. CI models are developed using three thermal characteristics of glass forming alloys i.e., glass transition temperature (T_g), the onset crystallization temperature (T_x), and liquidus temperature (T_l). The R²-values of GRNN, SVR, ANN, and MLR models are computed to be 0.5779, 0.5606, 0.4879, and 0.2611 for 349 BMGs alloys, respectively. We have investigated that GRNN model is performing better than SVR, ANN, and MLR models. The performance of proposed models is compared to the existing physical modeling and statistical modeling based techniques. In this study, we have investigated that proposed CI approaches are more accurate in modeling the experimental D_max than the conventional GFA criteria of BMGs alloys.     

Ability to forecast unsteady aerodynamic forces of flapping airfoils by artificial neural network

The ability of artificial neural networks (ANN) to model the unsteady aerodynamic force coefficients of flapping motion kinematics has been studied. A neural networks model was developed based on multi-layer perception (MLP) networks and the Levenberg–Marquardt optimization algorithm. The flapping kinematics data were divided into two groups for the training and the prediction test of the ANN model. The training phase led to a very satisfactory calibration of the ANN model. The attempt to predict aerodynamic forces both the lift coefficient and drag coefficient showed that the ANN model is able to simulate the unsteady flapping motion kinematics and its corresponding aerodynamic forces. The shape of the simulated force coefficients was found to be similar to that of the numerical results. These encouraging results make it possible to consider interesting and new prospects for the modelling of flapping motion systems, which are highly non-linear systems.     

Use of artificial neural networks for prediction of discharge coefficient of triangular labyrinth side weir in curved channels

Side weirs have been extensively used in hydraulic and environmental engineering applications. The discharge coefficient of the triangular labyrinth side weirs is 1.5-4.5 times higher than that of rectangular side weirs. This study aims to estimate the discharge coefficient (C_d) of triangular labyrinth side weir in curved channel by using artificial neural networks (ANN). In this study, 7963 laboratory test results are used for determining the C_d. The performance of the ANN model is compared with multiple nonlinear and linear regression models. Root mean square errors (RMSE), mean absolute errors (MAE) and correlation coefficient (R) statistics are used as comparing criteria for the evaluation of the models’ performances. Based on the comparisons, it was found that the neural computing technique could be employed successfully in modeling discharge coefficient from the available experimental data. There were good agreements between the measured values and the values obtained using the ANN model. It was found that the ANN model with RMSE of 0.1658 in validation stage is superior in estimation of discharge coefficient than the multiple nonlinear and linear regression models with RMSE of 0.2054 and 0.2926, respectively.     

Semi-quantitative and quantitative analysis of soft drinks using an electronic tongue

A potentiometric electronic tongue with 36 cross-sensibility lipo/polymeric membranes was built and applied for semi-quantitative and quantitative analysis of non-alcoholic beverages. A total of 16 commercial fruit juices (e.g., orange, pineapple, mango and peach) from five different brands were studied. In the semi-quantitative approach, the signal profiles recorded by the device were used together with a stepwise linear discriminant analysis to differentiate four beverage groups with different fruit juice contents: >30%, 14-30%, 6-10% and <4%. The model, with two discriminant functions based on the signals of only four polymeric membranes, explained 99% of the total variability of experimental data and was able to classify the studied samples into the correct group with an overall sensibility and specificity of 100% for the original data, and greater than 93% for the cross-validation procedure.The signals were also used to obtain MLR and PLS calibration models to estimate and predict the concentrations of fructose and glucose in the soft drinks. The linear models established were based on the signals recorded by 16 polymeric membranes and were able to estimate and predict satisfactorily (cross-validation) the concentrations of the two sugars (R² greater than 0.96 and 0.84, respectively).     

Flood flow forecasting using ANN,ANFIS and regression models

Flood prediction is an important for the design, planning and management of water resources systems. This study presents the use of artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), multiple linear regression (MLR) and multiple nonlinear regression (MNLR) for forecasting maximum daily flow at the outlet of the Khosrow Shirin watershed, located in the Fars Province of Iran. Precipitation data from four meteorological stations were used to develop a multilayer perceptron topology model. Input vectors for simulations included the original precipitation data, an area-weighted average precipitation and antecedent flows with one- and two-day time lags. Performances of the models were evaluated with the RMSE and the R ². The results showed that the area-weighted precipitation as an input to ANNs and MNLR and the spatially distributed precipitation input to ANFIS and MLR lead to more accurate predictions (e.g., in ANNs up to 2.0 m³ s^?1 reduction in RMSE). Overall, the MNLR was shown to be superior (R ² = 0.81 and RMSE = 0.145 m³ s^?1) to ANNs, ANFIS and MLR for prediction of maximum daily flow. Furthermore, models including antecedent flow with one- and two-day time lags significantly improve flow prediction. We conclude that nonlinear regression can be applied as a simple method for predicting the maximum daily flow.     

Development of a variable selection method for soft sensor using artificial neural network and nonnegative garrote

This paper developed a new variable selection method for soft sensor applications using the nonnegative garrote (NNG) and artificial neural network (ANN). The proposed method employs the ANN to generate a well-trained network, and then uses the NNG to conduct the accurate shrinkage of input weights of the ANN. This paper took Bayesian information criterion as the model evaluation criterion, and the optimal garrote parameter s was determined by v-fold cross-validation. The performance of the proposed algorithm was compared to existing state-of-art variable selection methods. Two artificial dataset examples and a real industrial application for air separation process were applied to demonstrate the performance of the methods. The experimental results showed that the proposed method presented better model accuracy with fewer variables selected, compared to other state-of-art methods.     

前向傅立叶神经网络系统逼近理论及学习算法

定义了傅立叶神经元与傅立叶神经网络,将一组傅立叶基三角函数作为神经网络各隐层单元的激合函数,设计出一类单输入单输出三层前向傅立叶神经网络与双输入单输出四层前向傅立叶神经网络,以及奇、偶傅立叶神经网络,基于三角函数逼近论,讨论了前向傅立叶神经网络的三角插值机理及系统逼近理论,且有严格的数学理论基础,给出了前向傅立叶神经网络学习算法,通过学习,它们分别能逼近于给定的傅立叶函数到预定的精度。仿真实验表明,该学习算法效率高,具有极为重要的理论价值和应用背景。     

Estimation of chemical oxygen demand by ultraviolet spectroscopic profiling and artificial neural networks

A simple method based on the mathematical treatment of spectral absorbance profiles in conjunction with artificial neural networks (ANNs) is demonstrated for rapidly estimating chemical oxygen demand (COD) values of wastewater samples. In order to improve spectroscopic analysis and ANN training time as well as to reduce the storage space of the trained ANN algorithm, it is necessary to decrease the ANN input vector size by extracting unique characteristics from the raw input pattern. Key features from the spectral absorbance pattern were therefore selected to obtain the spectral absorbance profile, reducing the ANN input vector from 160 to 10 selected inputs. The results indicate that the COD values obtained from the selected absorbance profiles agreed well with those obtained from the entire absorbance pattern. The spectral absorbance profile technique was also compared to COD values estimated by a multiple linear regression (MLR) model to validate whether ANNs were better and more robust models for rapid COD analysis. It was found that the ANN model predicted COD values closer to standard COD values than the MLR model.