Radial Basis Function Artificial Neural Network Research Articles

Radial basis function-artificial neural network (RBF-ANN) for simultaneous fluorescent determination of cysteine enantiomers in mixtures

The determination of chiral compounds is critically important in chemical and pharmaceutical sciences. Cysteine amino acid is one of the important chiral compounds where each enantiomer (L and D) has different effects on fundamental physiological processes. The unique optical properties of nanoparticles make them a suitable probe for the determination of different analytes. In this work, the water-soluble thioglycolic acid (TGA)-capped cadmium-telluride (CdTe) quantum dots (QDs) were applied as optical nanoprobe for the simultaneous determination of cysteine enantiomers. The difference in the kinetics of the interactions between L- and D-cysteine with CdTe QDs is used for multivariate quantitative analysis. Multivariate methods are superior to univariate methods in determining the concentration of each enantiomer in the mixture without the information about the total chiral analyte concentration. As a nonlinear calibration method the radial basis function -artificial neural network (RBF-ANN) model was more successful in predicting L-and D-cysteine concentrations than the linear partial least squares regression (PLS) model.

Performance Assessment for Short-Term Water Demand Forecasting Models on Distinctive Water Uses in Korea

It is crucial to forecast the water demand accurately for supplying water efficiently and stably in a water supply system. In particular, accurately forecasting short-term water demand helps in saving energy and reducing operating costs. With the introduction of the Smart Water Grid (SWG) in a water supply system, the amount of water consumption is obtained in real-time through a smart meter, which can be used for forecasting the short-term water demand. The models widely used for water demand forecasting include Autoregressive Integrated Moving Average, Radial Basis Function-Artificial Neural Network, Quantitative Multi-Model Predictor Plus, and Long Short-Term Memory. However, there is a lack of research on assessing the performance of models and forecasting the short-term water demand in the SWG demonstration plant. Therefore, in this study, the short-term water demand was forecasted for each model using the data collected from a smart meter, and the performance of each model was assessed. The Smart Water Grid Research Group installed a smart meter in block 112 located in YeongJong Island, Incheon, and the actual data used for operating the SWG demonstration plant were adopted. The performance of the model was assessed by using the Residual, Root Mean Square Error, Normalized Root Mean Square Error, Nash–Sutcliffe Efficiency, and Pearson Correlation Coefficient as indices. As a result of water demand forecasting, it is difficult to forecast water demand only by time and water consumption. Therefore, as the short-term water demand forecasting models using only time and the amount of water consumption have limitations in reflecting the characteristics of consumers, a water supply system can be managed more precisely if other factors (weather, customer behavior, etc.) influencing the water demand are applied.

Predicting the mortality risk of acute respiratory distress syndrome: radial basis function artificial neural network model versus logistic regression model.

To predict the mortality of acute respiratory distress syndrome (ARDS) by using a radial basis function (RBF) artificial neural network (ANN) model. This study included 217 patients who were admitted between June 2013 and November 2019. The RBF ANN model and logistic regression (LR) model were based on twelve factors related to ARDS. Statistical indexes were used to determine the value of the prediction in the two models. The sensitivity, specificity and accuracy of the RBF ANN model to predict mortality were 83.6%, 88.5% and 82.5%, respectively. Significant differences were found between the RBF ANN and LR models (P < 0.05). When the RBF ANN model was used to identify ARDS, the area under the ROC curve was 0.854 ± 0.029. LDH, organ failure, SP-D and PaO2/FiO2 were the most important independent variables. The RBF ANN model was more likely to predict the mortality of ARDS than the LR model. In addition, it can extract informative risk factors for ARDS.

Prediction of Signal Power Loss (at Micro-Cell Environments) Using Generalized Adaptive Regression and Radial Basis Function ANN Models Built on Filter for Error Correction

The Prediction of an accurate field signal power is of utmost importance in the design and placement of base station transmitters. This research work has designed and utilized two adaptive neural network models named Generalized Adaptive Regression (GR)-ANN and Radial Basis Function (RBF)-ANN made on vector Non-Linear Median Filter (NLMF) and it has compared their prediction performances with conventional GR-ANN and RBF-ANN. The prediction accuracy of the neural network models has been tested and evaluated using measurement experimental field strength data acquired from the LTE radio network from the line-of-sight (LOS) urban environment named location-1 Non-Line-of-Sight (NLOS) rural environment named location-2. Prediction error, average spread prediction error, and mean squared error have been used for analyzing the performance abilities of the models in the prediction of the measurement data during neural network training. Their performance accuracies have been compared. The GR-ANN and RBF-ANN's superior performances built on vector NLMF over the conventional GR-ANN, and RBF-ANN can be attributed to the high-quality datasets generated through filtering using NLMF. This improves the adaptive models' capability to learn, adaptively respond, and predict the reference propagation loss data's fluctuating pattern during neural network training. A further comparison shows GR-ANN's superiority in performance accuracy built on vector NLMF over RBF-ANN built on vector NLMF. This shows that GR-ANN's capability of solving any function approximation problem is better than RBF-ANN. However, RBF-ANN requires less training time.

A power-efficient and re-configurable analog artificial neural network classifier

This paper presents a power-efficient and re-configurable radial basis function-artificial neural network (RBF-ANN) for real-time pattern classification tasks. We have developed a MATLAB-based behavioral model, which can be employed to facilitate the off-chip learning of the proposed network with a hybrid learning algorithm. Besides, a generic design methodology is presented to ease implementing different scales of neural networks. For the RBF-ANN, an analog tunable Gaussian kernel circuit is used as an activation neuron while a current-mode computation is employed to improve the power efficiency. The proposed network is designed and simulated in 0.18 μm X-FAB CMOS process for a non-linear XOR-pattern classification and voice activity detector (VAD), respectively. It is found that the network's weights obtained using the developed model in MATLAB are well-matched with the Spectre simulation (Virtuoso) results with a maximum relative error of 7.1%. Consequently, the proposed model can be effectively employed for the off-chip training of RBF-ANN. Besides, the preliminary simulation results of the VAD depict that the classification accuracy reaches as large as 95% in a noisy environment of babble with an acoustic signal to noise ratio (SNR) of 10 dB. Meanwhile, the power efficiency of the proposed network gets significantly improved compared to the recent prior arts.

Application of RBF artificial neural networks to precipitation and temperature forecasting in Paraná, Brazil

Precipitation and temperature have an impact on various sectors of society, such as agriculture, power generation, water availability, so it is essential to develop accurate monthly forecasts. The objective of this study is to develop an artificial neural network (ANN) model for monthly temperature and precipitation forecasts for the state of Paraná, Brazil. An important step in the ANN model is the selection of input variables, for which the forward stepwise regression method was used. After identifying the predictor variables for the forecasting model, the Radial Basis Function (RBF) ANN was developed with 50 neurons in the hidden layer and one neuron in the output layer. For the precipitation forecasting models, better performances were obtained for forecasting the data smoothed by the three-month moving average, since noisy data, such as monthly precipitation, are more difficult to be simulated by the neural network. For the temperature forecasts, the ANN model performed well both in the monthly temperature forecast and in the 3-month moving average forecast. This study showed the suitability of forecasting precipitation and temperature with the use of RBF ANNs, especially in the forecast of the monthly temperature.

Application of Artificial Intelligence to Predict Enhanced Oil Recovery Using Silica Nanofluids

The feasibility of approaches to enhanced oil recovery (EOR) in harsh conditions of reservoirs should be evaluated primarily in the laboratory environment to capture possible failures that threaten the performance of an operation, although such experiments are commonly expensive and time-consuming. This work investigated the application of artificial intelligence in allaying such concerns regarding the initial screening of EOR methods. Accordingly, three machine learning algorithms, namely adaptive neuro-fuzzy inference system (ANFIS), multilayer perceptron-artificial neural network (MLP–ANN), and radial basis function-artificial neural network (RBF–ANN), were employed to predict the efficiency of a set of silica nanofluid flooding experiments in carbonate and sandstone core samples. Initially, the optimum structures of the employed models were determined. Then, their performances were compared. The strongest performance was achieved by the ANFIS model, where the results in terms of coefficient of determination and root-mean-square error for training, testing, and entire data points were 0.9954 and 0.3395, 0.9877 and 0.4793, and 0.9939 and 0.3793, respectively. The ANFIS model also has the shortest execution time and the least over-fitting problems, and thus it can be utilized for screening the efficiency of silica-EOR projects.

New methods based on back propagation (BP) and radial basis function (RBF) artificial neural networks (ANNs) for predicting the occurrence of haloketones in tap water

Haloketones (HKs) is one class of disinfection by-products (DBPs) which is genetically toxic and mutagenic. Monitoring HKs in drinking water is important for drinking water safety, yet it is a time-consuming and laborious job. Developing predictive models of HKs to estimate their occurrence in drinking water is a good alternative, but to date no study was available for HKs modeling. This study was to explore the feasibility of linear, log linear regression models, back propagation (BP) as well as radial basis function (RBF) artificial neural networks (ANNs) for predicting HKs occurrence (including dichloropropanone, trichloropropanone and total HKs) in real water supply systems. Results showed that the overall prediction ability of RBF and BP ANNs was better than linear/log linear models. Though the BP ANN showed excellent prediction performance in internal validation (N25 = 98–100%, R2 = 0.99–1.00), it could not well predict HKs occurrence in external validation (N25 = 62–69%, R2 = 0.202–0.848). Prediction ability of RBF ANN in external validation (N25 = 85%, R2 = 0.692–0.909) was quite good, which was comparable to that in internal validation (N25 = 74–88%, R2 = 0.799–0.870). These results demonstrated RBF ANN could well recognized the complex nonlinear relationship between HKs occurrence and the related water quality, and paved a new way for HKs prediction and monitoring in practice.

A Novel Method for Analyzing the Factors Influencing Ground Settlement during Shield Tunnel Construction in Upper-Soft and Lower-Hard Fissured Rock Strata considering the Coupled Hydromechanical Properties

Focusing on the special stratum conditions of upper-soft and lower-hard fissured rock strata, this paper conducts quantitative research and analysis on the factors influencing the ground settlement caused by shield tunnel construction considering the coupled hydromechanical properties and presents a corresponding numerical simulation-artificial neural network-Bayesian network- (NS-ANN-BN-) based method. In this method, with a subway shield tunnel as the engineering context, three numerical models are established, in which the shield tunnel is located in soft strata, the shield tunnel is located in semisoft and semihard strata, or the shield tunnel is located in hard strata. According to the numerical simulation (NS) calculations, the ground settlement values under the three types of strata are 38.96 mm, 10.42 mm, and 3.13 mm, respectively. A radial basis function artificial neural network (RBF-ANN) is used to establish the nonlinear mapping relationship between the stratum parameters and the ground settlement, and the training samples and test samples are generated through NS to train the RBF-ANN. After the training is completed, the accuracy of the neural network meets the requirements. The elastic moduli of coarse sand~gravel sand k3 and moderately weathered rhyolite k4 and the cohesion of moderately weathered rhyolite c4 are selected as the key parameters. A large number of training cases are generated through the RBF-ANN, and the Bayesian network (BN) prior probability is calculated by self-learning. A BN model of ground settlement for shield tunnel construction in the upper-soft and lower-hard fissured rock strata is established. The BN back analysis method is used to quantitatively analyze the influencing factors of the ground settlement. The results show that when the tunnel is located in soft strata, the surface settlement is mainly affected by parameter k3. When the ground settlement increases considerably, the three parameters all have a strong influence. When the tunnel is located in semisoft and semihard strata, the influence of the three parameters on the ground settlement is weak. When the tunnel is located in hard strata, the ground settlement is mainly affected by parameter k4. When the ground settlement greatly increases, parameters k3 and c4 have less influence. When the tunnel is located in strata with different soft-hard ratios, the ground settlement is mainly affected by the elastic moduli of coarse sand~gravel sand and moderately weathered rhyolite. This method can provide a reference for the ground settlement analysis of shield tunnel construction in areas with similar fissured rock strata.

Radial Basis Function Neural Network Model Prediction of Thermo-catalytic Carbon Dioxide Oxidative Coupling of Methane to C2-hydrocarbon

Various anthropogenic activities often result in the emission of carbon dioxide (CO2), which is one of the principal components of greenhouse gases responsible for greenhouse effect. One vital strategy to mitigate the effect of the released CO2 on the environment is through sustainable utilization and conversion to value-added chemicals. This study employs the Radial Basis Function artificial neural network for modeling the prediction of thermo-catalytic CO2 oxidative coupling of methane to C2-hydrocarbons. The various architecture of the Radial Basis Function ANN was developed, trained, and tested using the non-linear relationship between the input parameters (reaction temperature, amount of CaO and MnO in the CaO-MnO/CeO2 catalysts and the CO2/CH4 ratio) and the output parameters (C2 hydrocarbon selectivity and yield). The Radial Basis Function ANN architecture with the topology of 4-20-2, representing the input layer, hidden neurons, and the output layer offers the best performance with a sum of square error (SSE) of 3.9 × 10−24 for training and 0.224 for testing. The R2 of 0.989 and 0.998 obtained for the prediction of the selectivity and the yield of the C2 hydrocarbon is an indication of the robustness of the Radial Basis Function ANN model. The sensitivity analysis revealed that the input parameters significantly influence the model output. However, the reaction temperature has the most significant influence on the model output based on the level of importance.

Predicting Estimated Blood Loss and Transfusions in Gynecologic Surgery Using Artificial Neural Networks

This chapter explores valuating the efficacy of using artificial neural networks (ANNs) for predicting the estimated blood loss (EBL) and also transfusion requirements of myomectomy patients. All 146 myomectomy surgeries performed over a 6-year period from a single site are captured. Records were removed for various reasons, leaving 96 cases. Backpropagation and radial basis function ANN models were developed to predict EBL and perioperative transfusion needs along with a regression model. The single hidden layer backpropagation ANN models performed the best for both prediction problems. EBL was predicted on average within 127.33 ml of measured blood loss, and transfusions were predicted with 71.4% sensitivity and 85.4% specificity. A combined ANN ensemble model using the output of the EBL ANN as an input variable to the transfusion prediction ANN was developed and resulted in 100% sensitivity and 62.9% specificity. The preoperative identification of large EBL or transfusion need can assist caregivers in better planning for possible post-operative morbidity and mortality.

Radial Basis Function Artificial Neural Network for the Investigation of Thyroid Cytological Lesions.

Objective This study investigates the potential of an artificial intelligence (AI) methodology, the radial basis function (RBF) artificial neural network (ANN), in the evaluation of thyroid lesions. Study Design. The study was performed on 447 patients who had both cytological and histological evaluation in agreement. Cytological specimens were prepared using liquid-based cytology, and the histological result was based on subsequent surgical samples. Each specimen was digitized; on these images, nuclear morphology features were measured by the use of an image analysis system. The extracted measurements (41,324 nuclei) were separated into two sets: the training set that was used to create the RBF ANN and the test set that was used to evaluate the RBF performance. The system aimed to predict the histological status as benign or malignant. Results The RBF ANN obtained in the training set has sensitivity 82.5%, specificity 94.6%, and overall accuracy 90.3%, while in the test set, these indices were 81.4%, 90.0%, and 86.9%, respectively. Algorithm was used to classify patients on the basis of the RBF ANN, the overall sensitivity was 95.0%, the specificity was 95.5%, and no statistically significant difference was observed. Conclusion AI techniques and especially ANNs, only in the recent years, have been studied extensively. The proposed approach is promising to avoid misdiagnoses and assists the everyday practice of the cytopathology. The major drawback in this approach is the automation of a procedure to accurately detect and measure cell nuclei from the digitized images.

Application of Artificial Neural Networks to Assess the Mycological State of Bulk Stored Rapeseeds

Artificial neural networks (ANNs) constitute a promising modeling approach that may be used in control systems for postharvest preservation and storage processes. The study investigated the ability of multilayer perceptron and radial-basis function ANNs to predict fungal population levels in bulk stored rapeseeds with various temperatures (T = 12–30 °C) and water activity in seeds (aw = 0.75–0.90). The neural network model input included aw, temperature, and time, whilst the fungal population level was the model output. During the model construction, networks with a different number of hidden layer neurons and different configurations of activation functions in neurons of the hidden and output layers were examined. The best architecture was the multilayer perceptron ANN, in which the hyperbolic tangent function acted as an activation function in the hidden layer neurons, while the linear function was the activation function in the output layer neuron. The developed structure exhibits high prediction accuracy and high generalization capability. The model provided in the research may be readily incorporated into control systems for postharvest rapeseed preservation and storage as a support tool, which based on easily measurable on-line parameters can estimate the risk of fungal development and thus mycotoxin accumulation.

Design and experimental investigation of a GA-based control strategy for a low-speed fin stabilizer

Fin stabilizers are widely used for to reduce ship rolling. However, reducing rolling motion at low ship speeds remains a challenge because of uncertainties in ship dynamics, transient and nonlinear hydrodynamic forces of fin. Also the phase difference between the force and fin angle is highly sensitive to ship speed. Herein, an improved control strategy is proposed to avoid these problems and to enhance the anti-roll effect of fin stabilizers. A prediction algorithm based on the radial base function artificial neural network (RBF-ANN) is first used to forecast ship rolling motion, and then the disturbing moment and roll time series are estimated. Uncertainty of disturbances in roll dynamics are encapsulated in the predictive algorithm. Moreover, an inversion method based on the genetic algorithm can be applied to minimize differences between the disturbing moment and stabilizing moment. A ship model is introduced to verify the proposed control strategy. Forced roll tests were carried out using the ship model to determine the optimal fin profile and maximum control moment. Anti-roll experiments and simulations were performed to verify the improved control strategy.

Robust Chatter Stability Prediction of the Milling Process considering Uncertain Machining Positions

Milling stability is a function of the tool point frequency response functions (FRFs), which vary with the movements of the moving parts within the whole machine tool work volume. The position-dependent tool point FRFs result in uncertain prediction of the stability lobe diagram (SLD) for chatter-free machining parameter selection. Taking the variations of modal parameters to represent the variations of tool point FRFs, this paper introduces the edge theorem to predict the robust milling chatter stability. The application of the edge theorem requires the minimum and maximum modal parameters within the machining space defined by the machining position and machining allowance information. Then, radial basis function artificial neural networks (RBFANNs) are used to predict the position-dependent modal parameters in X and Y directions based on the sample information of machining positions and related modal parameters at the tool point. Moreover, sample machining spaces are determined based on the aforementioned sample positions, and the trained RBFANNs are used to obtain corresponding sample extreme modal parameters. On this basis, RBFANNs for predicting the position and machining allowance-dependent extreme modal parameters can also be trained, and they are combined with the edge theorem and zero exclusion condition to calculate robust pairs of the spindle speed (n) and limiting axial cutting depth (aplim) and then plot the robust SLD (RSLD). A case study was performed on a real three-axial vertical machining center, and the plotted RSLD considering position variations was compared with the traditional SLD. Results of the chatter tests show that the RSLD can provide more reliable (ap, n) pairs to guarantee the milling stability, validating the feasibility of the proposed robust milling chatter stability prediction method.

Ranking of hybrid wavelet-AI models by TOPSIS method for estimation of daily flow discharge

Abstract This research uses the multi-layer perceptron–artificial neural network (MLP-ANN), radial basis function–ANN (RBF-ANN), least square support vector machine (LSSVM), adaptive neuro-fuzzy inference system (ANFIS), M5 model tree (M5T), gene expression programming (GEP), genetic programming (GP) and Bayesian network (BN) with five types of mother wavelet functions (MWFs: coif4, db10, dmey, fk6 and sym7) and selects the best model by the TOPSIS method. The case study is the Navrood watershed in the north of Iran and the considered parameters are daily flow discharge, temperature and precipitation during 1991 to 2018. The derived results show that the best method is the hybrid of the M5T model with sym7 wavelet function. The MWFs were decomposed by discrete wavelet transform (DWT). The combination of AI models and MWFs improves the correlation coefficient of MLP, RBF, LSSVM, ANFIS, GP, GEP, M5T and BN by 8.05%, 4.6%, 8.14%, 8.14%, 22.97%, 7.5%, 5.75% and 10% respectively.

Predictive models of tensile strength and disintegration time for simulated Chinese herbal medicine extracts compound tablets based on artificial neural networks

The tensile strength (TS) and disintegration time (DT) are often used as important indexes to evaluate the quality of tablets. The TS and DT of Chinese herbal medicine compound tablets are affected by the properties of the herbal medicine extract powder. In this study, three predictive models of powder properties-tablet quality were established for simulated herbal medicine compound tablets. The models can be used to predict the TS and DT of tablets according to the powder properties. The models were based on combinations of principal component analysis (PCA) and radial basis function artificial neural network (RBF-ANN), back propagation artificial neural network (BP-ANN) and multiple regression analysis (MRA). The TS and DT prediction accuracy of the three models were ranked as follows: PCA-RBF-ANN > PCA-MRA > PCA-BP-ANN. The PCA-RBF-ANN model had the best predictive performance: the relative error for TS ranged from 1.51% to 6.31%, with a mean relative error of 3.91%; the relative error for DT ranged from 1.18% to 2.84%, with a mean relative error of 2.01%. The results demonstrated that the PCA-RBF-ANN model can be used to predict the quality of tablets and provide a reference for quality control of herbal medicine compound tablets.

An artificial neural network modeling approach for short and long fatigue crack propagation

Fatigue crack growth-based damage modeling approaches have received great interest due to its critical importance in the industry. However, a substantial deficiency of an explicit fatigue damage model to quantify the accurate fatigue crack growth behavior remains due to the complex fatigue crack growth behavior in different length scales. This complexity arises from the fact that fatigue crack growth (FCG) in different length scales depends on many damage controlling parameters. Machine learning-based fatigue damage modeling approaches have received noticeable attention for fatigue crack growth analysis due to their abilities to account for numerous damage parameters simultaneously. In the presented paper, a radial basis function artificial neural network (RBF-ANN) model has been developed to predict the FCG behavior, including the short and long crack regimes. The presented RBF-ANN model has been trained and verified by experimental data sets of Ti-6Al-4V titanium alloy, 2024-T3 and 7075-T6 aluminium alloys. The predictions showed that the RBF-ANN model has a good interpolation capability to predict the nonlinearity of both short and long crack growth behavior. However, the model shows poor extrapolation capability for accurate short crack growth predictions for cases that there are limited data sets in hand. The model effectiveness greatly depends on sufficient available input data.

Estimation of CO2 adsorption in high capacity metal−organic frameworks: Applications to greenhouse gas control

In recent decades, adsorption of high amounts of carbon dioxide (CO2) in metal-organic frameworks (MOFs) has recived attention and is studied broadly. As a main principle, most scientists have accepted that CO2 can be capured by MOFs in order to prevent atmosphere from green-house gas emissions. In the present work, the potential of Particle Swarm Optimization Adaptive Neuro-Fuzzy Inference System (PSO-ANFIS), Differential Evolution-ANFIS (DE-ANFIS), Radial Basis Function Artificial Neural Network (RBF-ANN) and Least Square Support Vector Machine (LSSVM) to estimate CO2 uptake in 13 different MOFs, as a function of the operational pressure (P) supplemented with the property of MOFs was investigated. The inputs of the models are temperature, pressure, surface area and pore volume of MOFs. An extensive databank containing 506 data gathered from the literature was used for models development. The obtained %AARD values for the developed models are 10.05, 36.6, 35.51 and 8.17 for LSSVM, PSO-ANFIS, DE-ANFIS and RBF models, respectively.The sensitivity analysis demonstrated that operational pressure and pore volume of MOFs are the most effective parameters on CO2 adsorbtion by MOFs. It is found that LSSVM model is an outstanding tool for estimating adsorption of CO2 in comparison with other models. The LSSVM model presents a decent method for estimating CO2 adsorption in the studied MOFs, which is straightforward, capable and cost-efficient.

Proposing a modified mechanism for determination of hydrocarbons dynamic viscosity, using artificial neural network

In this study, to have an accurate approximation of dynamic viscosity, radial basis function artificial neural network (RBF-ANN) is employed and developed for normal alkanes. This is done by considering the distinct number of carbons in n-alkanes, certain temperatures, and different pressures. Moreover, in order to train and test the predicting model, a databank of 228 experimental data is gathered from reliable sources in the literature. As a result, training and testing coefficient values are measured 0.99739 and 0.99051; consequently, the robustness and accuracy of RBF-ANN in providing an estimation of n-alkane viscosity is confirmed by graphical analysis and determined indexes.