A comparison between ANN based methods of critical clearing time estimation

Photoelectric factor, formation true resistivity, and formation water saturation are three functional parameters of a hydrocarbon reservoir that could provide invaluable data for reservoir characterization and formation evaluation. The present study proposes an improved strategy for making a quantitative formulation between conventional well log data and the mentionewd parameters. At the first stage of this study, three architectures of artificial neural networks, including generalized regression neural network, radial basis neural network, and Bayesian regulation backpropagation neural network, were employed to predict the aforementioned parameters from conventional well log data. Consequently, a committee neural network was constructed by virtue of hybrid genetic algorithm-pattern search technique. The propounded committee neural network combines the results of generalized regression neural network, radial basis neural network, and Bayesian regulation backpropagation neural network to improve the accuracy of final prediction. It assigns a weight factor to each of the individual artificial neural networks indicating its contribution in overall prediction. A set of data points was used for model construction and another set was employed to assess the model performance. The results showed that integration of artificial neural networks using the concept of committee machine could improve the precision of target prediction, although each of the artificial neural networks has performed adequately for prediction of photoelectric factor and formation true resistivity. The values obtained for formation water saturation are not as accurate as results obtained for photoelectric factor and formation true resistivity, although the correlation coefficient between measured and predicted values for formation water saturation is higher.

In this study, the thermoluminescence (TL) glow curve test results performed with eleven different dose values were used as training data, and its attempted to estimate the test results of the curves performed at four different doses using artificial intelligence methods. While the dose values of the data used for training were 10, 20, 50, 100, 150, 220, 400, 500, 600, 700, and 900 Gy, the selected dose values of the data for the testing were 40, 276, 320, and 800 Gy. The success of the experimental and artificial neural network results was determined according to the mean squared error (RMSE), regression error (R2), root squared error (RSE), and mean absolute error (MAE) criteria. Studies have been carried out on seven different neural network types. These networks are adaptive network-based fuzzy inference system (ANFIS), general regression neural network (GRNN), radial basis neural network (RBNN), cascade-forward backprop neural network (CFBNN), Elman backprop neural network (EBNN), feed-forward backprop neural network (FFBNN), and layer recurrent neural network (LRNN). This study concluded that the neural network with the Elman backpropagation network type demonstrated the best network performance. In this network, the training success rate is 80.8%, while the testing success rate is 87.95%.

Leveraging hybrid machine learning and data fusion for accurate mapping of malaria cases using meteorological variables in western India

<abstract><p>The training of artificial neural networks (ANNs) with rectified linear unit (ReLU) activation via gradient descent (GD) type optimization schemes is nowadays a common industrially relevant procedure. GD type optimization schemes can be regarded as temporal discretization methods for the gradient flow (GF) differential equations associated to the considered optimization problem and, in view of this, it seems to be a natural direction of research to <italic>first aim to develop a mathematical convergence theory for time-continuous GF differential equations</italic> and, thereafter, to aim to extend such a time-continuous convergence theory to implementable time-discrete GD type optimization methods. In this article we establish two basic results for GF differential equations in the training of fully-connected feedforward ANNs with one hidden layer and ReLU activation. In the first main result of this article we establish in the training of such ANNs under the assumption that the probability distribution of the input data of the considered supervised learning problem is absolutely continuous with a bounded density function that every GF differential equation admits for every initial value a solution which is also unique among a suitable class of solutions. In the second main result of this article we prove in the training of such ANNs under the assumption that the target function and the density function of the probability distribution of the input data are piecewise polynomial that every non-divergent GF trajectory converges with an appropriate rate of convergence to a critical point and that the risk of the non-divergent GF trajectory converges with rate 1 to the risk of the critical point. We establish this result by proving that the considered risk function is <italic>semialgebraic</italic> and, consequently, satisfies the <italic>Kurdyka-Łojasiewicz inequality</italic>, which allows us to show convergence of every non-divergent GF trajectory.</p></abstract>

Pan evapotranspiration (E) is an important physical parameter in agricultural water resources research. Many climatic factors affect E, and one of the essential challenges is to model or predict E utilizing limited climatic parameters. In this study, the performance of four different artificial neural network (ANN) algorithms i.e., multiple hidden layer back propagation (MBP), generalized regression neural network (GRNN), probabilistic neural networks (PNN), and wavelet neural network (WNN) and one empirical model namely Stephens–Stewart (SS) were employed to predict monthly E. Long-term climatic data (i.e., 1961–2013) was used for the validation of the proposed model in the Henan province of China. It was found that different models had diverse prediction accuracies in various geographical locations, MBP model outperformed other models over almost all stations (maximum R2 = 0.96), and the WNN model was the best over two sites, the accuracies of the five models ranked as MBP, WNN, GRNN, PNN, and SS. The performances of WNN and GRNN were almost the same, five-input ANN models provided better accuracy than the two-input (solar radiation (Ro) and air temperature (T)) SS empirical model (R2 = 0.80). Similarly. the two-input ANN models (maximum R2 = 0.83) also generally performed better than the two-input (Ro and T) SS empirical model. The study could reveal that the above ANN models can be used to predict E successfully in hydrological modeling over Henan Province.

Artificial intelligent provides diverse solutions for the complex problems in agriculture research. The study aimed to use three models of artificial neural networks (Feed Forward Neural Network (FFNN), Generalized Regression Neural Network (GRNN) and Radial-Basis Neural Network (RBNN)) in the field of wheat yield prediction. 27-year data for the period (1986-2012) were utilized to improve the models and four-year data (2013 and 2016) were used to estimate the models, to compare their outputs with the measured data. Prediction data was not entered in the process of building neural network models. The results showed that the optimal configuration of the FFNN model consists of 40 neurons in the hidden layer (8-40-1). The Tan Sigmoid activation function was used in both the hidden layer and the output layer using all of these models (anterior neural feeding network and the regression neural network and radial base neural network) in the 4-year wheat yield forecast field for production (2013-2016) by applying 8 input parameters that were result of NMMS (8.6%, 7.6% and 15.7% resp.), To find that FFNN and GRNN provide the best result from BRNN because while the information set was large or in a wide range, then the range data ranges from -1 to +1 (normalization data) , GRNN gives better outcomes after the information or sample data were in large range.

The applicability of artificial neural networks (ANNs) and the adaptive neuro-fuzzy inference system (ANFIS) for determination of mean velocity and discharge of natural streams is investigated. The 2,184 field data obtained from four different sites on the Sarimsakli and Sosun streams in central Turkey were used in the study. ANNs and ANFIS models use the inputs, water surface velocity and water surface slope, to estimate the mean velocity and discharges of natural streams. The accuracies of both models were compared with the multiple-linear regression (MLR) model. The comparison results showed that the ANFIS model performed better than the ANNs and regression models for estimating mean velocity and discharge. The ANN model also showed better accuracy than the MLR model. The root mean square errors (RMSE) and mean absolute relative errors (MARE) of the MLR model were reduced by 88 and 91 % using the ANFIS model in estimating discharges, respectively. It is found that the optimal ANFIS model with RMSE of 0,063, MARE of 3,47 and determination coefficient (R2) of 0,996 in the test period is superior in estimation of discharge than the MLR model with RMSE of 0,532, MARE of 38,9 and R2 of 0,776, respectively. The study reveals that the ANFIS technique can be successfully used for estimating the mean velocity and discharge of natural streams by using only the inputs of water surface velocity and water surface slope.

Artificial neural networks (ANN) based pattern recognition for steady state (SSA), transient (TSA) and dynamic security assessment (DSA) of the power systems is presented. Conventional methods for security assessment take lot of time to assess the security of power systems when all contingencies are considered. Artificial neural networks based pattern recognition is used to solve SSA, TSA and DSA and its effectiveness against conventional methods is presented. In addition contingency ranking and generator severity ranking is used to measure the severity of various contingencies which allows an operator to take preventive control (generator rescheduling) or to be ready for corrective actions. Direct methods are fast compared to numerical methods but proper choice of Lyapunov function is difficult. ANN based PR for SSA, TSA and DSA effectiveness is compared with other conventional methods like pattern recognition which confirms that ANN not only gives accurate results but also is adaptive to the topology changes of the power system. In addition contingency ranking and generator severity ranking has been addressed which allows the operator to take preventive control actions like generator rescheduling.

Brushless DC (BLDC) motors are the most popular motors used by the industry because they are easy to control. BLDC motors are generally controlled by artificial controls such as Fuzzy Logic Controller (FLC), Artificial Neural Network (ANN), and Adaptive Neuro-Fuzzy Inference System (ANFIS). However, the performance of the BLDC control system in previous studies was compared separately with their respective parameters, making it difficult to evaluate comprehensively. Therefore, in order to investigate the characteristic performance of Fuzzy, ANN, and ANFIS, this article provides a comparison of these artificial controls. Two scenarios of the dynamic tests are conducted to investigate control performance under constant torque-various speed and constant speed-various torque. By dynamic testing, characteristics of Fuzzy, ANN, and ANFIS can be observed as real applications. The testing parameters are: Settling Time, Overshoot and Overdamp (in the graph and average value), and then statistic performance are: Integral Square Error (ISE), Integral Absolute Error (IAE), Integral Time Absolute Error (ITAE), and Mean Absolute Error (MAE). The test result in scenario 1 showed that the ANN has a better performance compared to other controllers with the MAE, IAE, ITAE, and ISE value of 31.3003; 105.6280; 208.0630; and 5,7289 e4, respectively. However, in scenario 2, ANN only has a better performance compared to other controllers on just a few parameters. In scenario 2, ANN is indeed able to maintain speed but it has a more ripple value than ANFIS. Even so, the ripple that occurs in ANN does not have too much value compared to the setpoint. Therefore, the MAE value of the ANN is smaller than the ANFIS (18.8937 of ANN and 28.4685 of ANFIS).

BACKGROUND: Currently, artificial intelligence in the form of artificial neural networks is being actively implemented in a number of areas of our lives, including medicine. In particular, in otorhinolaryngology, artificial neural networks are used to analyze images obtained during endoscopic examinations of patients (e.g., videolaryngoscopy) [1–3]. The interpretation of laryngoscopic images often presents significant difficulties for practicing physicians, which reduces the frequency of detection of precancerous laryngeal diseases and contributes to the increase in the number of patients with stage III–IV laryngeal cancer [4, 5]. This underscores the significance of prompt performance and accurate interpretation of the findings of endoscopic examinations of patients with laryngeal disorders. Artificial neural networks can be employed to analyze the results of videolaryngoscopy, furnishing the physician with supplementary information that can enhance diagnostic accuracy and diminish the probability of error [6, 7]. AIM: The study aims to develop and train an artificial neural network for recognizing characteristic features of laryngeal neoplasms and variants of laryngeal normality. MATERIALS AND METHODS: The study was conducted under the grant of the Moscow Center for Innovative Technologies in Healthcare (grant No. 2112-1/22) entitled “Using Neural Networks (Artificial Intelligence Algorithms) for Control and Improving the Quality of Diagnosis and Treatment of Diseases of Laryngeal and Ear Structures through Digital Technologies”.The following methods were used during the course of the study: data collection for the creation of a photobank (dataset) of medical images obtained during videolaryngoscopy; data partitioning for the formation of datasets for individual nosologies and groups of diseases; the method of consilium; analysis of the accuracy of recognition and classification of digital endoscopic images; and training of classification neural networks. Consequently, a dataset comprising 1,471 laryngeal images in digital formats (JPEG, BMP) was assembled, labelled, and uploaded for the purpose of training the artificial neural network. Of the total number of images, 410 were classified as pertaining to laryngeal formation, while 1061 were classified as variants of normality. Subsequently, the neural network was trained and tested to identify the signs of normal and laryngeal masses. RESULTS: The results of the testing of the artificial neural network indicated the formation of an inaccuracy matrix, the calculation of the value of recognition accuracy, the calculation of the quality indicators of the model performance, and the construction of the ROC curve. The developed and trained artificial neural network demonstrated an accuracy of 86% in recognizing the signs of laryngeal masses and norms. CONCLUSIONS: This study demonstrates that a trained artificial neural network can successfully distinguish between signs of normal and laryngeal masses in endoscopic photographs. With further training of the neural network and achievement of high accuracy, this technology can be used in clinical practice as an assistant in the interpretation of laryngoscopic images and early diagnosis of laryngeal masses. It can also be employed to control and improve the quality of diagnosis and treatment of diseases of the throat, nose, and ears by primary care physicians.

Artificial neural network approaches for prediction of backwater through arched bridge constrictions

In 2014, the relevant research data from the Ministry of Environmental Protection and the Ministry of Land and Resources showed that the total exceedance rate of soil heavy metal pollution in China had reached 16.1%, and in the construction of ecological civilization in the 13th Five-Year Plan, China has made the prevention and control of soil heavy metal pollution as the focus of prevention and control. Therefore, in this paper, four neural optimization network models, that is, radial basis neural network (RBFNN), generalized regression neural network (GRNN), wavelet neural network (WNN), and fuzzy neural network (FNN), are simulated and created to measure and correlate the soil heavy metal content in a city in northwest China and a city in central China from the actual situation in China. The simulations were conducted. Finally, by analyzing the comparison of predicted and true values of these four models on the test data of two sets of experimental data, the distribution of predicted differences to true values, and the calculation results of three error indicators, we found that WNN has the best prediction performance when using RBFNN, GRNN, WNN, and FNN for soil heavy metal content prediction.

This paper introduces an adaptive terminal voltage regulation of a standalone self excited induction generator using flexible AC transmission systems (FACTS). FACTS in the form of static VAR compensator (SVC) is introduced. SVC is used to regulate the terminal voltage of self excited induction generator-based (SEIG) wind generator working with variable speed and load. Since, the wind generator operates over a wide range of operating conditions; the terminal voltage of the induction generator is not regulated. This terminal voltage is controlled by adapting the value of the excitation capacitance of SVC using artificial neural networks (ANN) and adaptive neuro-fuzzy inference systems (ANFIS). Changing the excitation capacitance is performed by controlling the firing angle of SVC under different operating conditions to control the terminal voltage. A mathematical model of SEIG with variable load and speed along with SVC is developed and simulated in MATLAB to get the excitation capacitance required for voltage control. Simulation results are used to train both ANN and ANFIS for on-line prediction of the suitable firing angles required to control the terminal voltage of the system under these operating conditions. Results signify the supremacy of ANFIS over ANN in terms of performance measures.

Public transportation trip flow modeling with generalized regression neural networks

Nowadays, The Indian stock market is very promising and every trader wants to take advantage of this market. So, prediction plays an important role to predict the value of Nifty 50 in the stock market. Nifty 50 comes under the futures and options (F&O) segment in the market. Machine learning tools are used for better prediction purposes. In this paper, we have presented four neural network models (Feedforward neural network, generalized regression neural network, radial basis neural network, and exact radial basis neural network) and all are based on machine learning. The research work proposed four model to predict the accuracy of Nifty 50 value by comparing it with a minimum error rate. The data set samples of last nine years, Jan, 2013 to June, 2021 collected from the Yahoo Finance URL, has been used in order to carried out the research work. Total four features as initial opening value, day high, day low, and total volumes traded on that particular day are considered as input parameters and the closing value of the day taken as an output parameter for the Nifty 50 value of Stock Market. The experimental results reveals that the best model to predict the Nifty 50 stock market is radial basis neural network model provides 98.17% accuracy in contrast to the rest of the three models.