Error Diagram Research Articles

A Bayesian regularization radial basis neural network novel procedure for the fractional economic and environmental system

The motive of current work is to design a novel radial basis Bayesian regularization neural network (RB-BRNN) for solving the nonlinear fractional economic and environmental system (FEES). A radial basis activation function in the hidden layers is applied by taking 20 numbers of neurons. The mathematical FEES is presented in three classes, named as cost of control accomplishment, manufacturing elements competence and technical exclusion’s diagnostics cost. A reference dataset is obtained using the Adams numerical results to reduce the mean square error (MSE) by taking the data for training 70%, while 15% is used for both testing and validation. The negligible absolute error values and comparison of the solutions develop the worth of computing RB-BRNN in order to solve the nonlinear dynamics of the FEES. Error diagrams, regression values, and the MSE performances are implemented to assess the precision of the designed solver.

Machine Learning as a Tool for Auxiliary Diagnosis of Osteoporosis

By making predictions from the model created with machine learning, specifically supervised learning, this essay focuses on the auxiliary diagnosis of osteoporosis. The chosen dataset includes highly relevant indexes that determine the diagnosis of osteoporosis. After doing the feature selection and one-hot encoding to preprocess the dataset, we then split the dataset into validation and training sets to avoid overfitting. Then, to train the model for prediction, we used the neuron network, chose ReLU and Sigmoid functions as activation functions, and changed the number of neurons and epochs to find the best-fit model. Through further measurement, evaluation, and application, including plotting the binary cross entropy error diagram and analyzing the classification report, the model is examined as highly accurate and desirable. With an appreciable degree of accuracy, this model for auxiliary diagnosis is able to prevent disease development or deterioration by detecting early symptoms and vulnerable populations, reduce the probability for doctors to misdiagnose, and improve the efficiency and quality of the osteoporosis diagnosis, therefore enhancing patient experiences.

Correlation between Strain Rate and Seismicity in Different Tectonic Settings

Abstract Geodetic strain rate characterizes present-day crustal deformation and therefore may be used as a spatial predictor for earthquakes. However, the reported correlation between strain rates and seismicity varies significantly in different places. Here, we systematically study the correlation between strain rate, seismicity, and seismic moment in six regions representing typical plate boundary zones, diffuse plate boundary regions, and continental interiors. We quantify the strain rate–seismicity correlation using a method similar to the Molchan error diagram and area skill scores. We find that the correlation between strain rate and seismicity varies with different tectonic settings that can be characterized by the mean strain rates. Strong correlations are found in typical plate boundary zones where strain rates are high and concentrated at major fault zones, whereas poor or no correlations are found in stable continental interiors with low strain rates. The correlation between strain rate and seismicity is also time dependent: It is stronger in seismically active periods but weaker during periods of relative quiescence. These temporal variations can be useful for hazard assessment.

Assessing Earthquake Forecasting Performance Based on Annual Mobile Geomagnetic Observations in Southwest China

There have been reports about anomalies in mobile geomagnetic data before earthquakes; however, whether it can be used as an indicator for identifying potential earthquake areas was not be explored. In this study, we propose two parameters for earthquake forecasting based on annual mobile geomagnetic observation data. The spatial horizontal and three components’ changes are calculated in each year and then used to forecast moderate–large earthquakes (M ≥ 5.0) in southwest China in the subsequent period. It is found that earthquakes are more likely to occur in low H- or F-value regions. We statistically assess their forecasting performance by using Molchan’s error diagram, and the results indicate that there is considerable precursory information in the spatial H and F values. It is concluded that mobile geomagnetic observations might be useful in middle-term earthquake forecasts in the study area. We discuss the physical mechanisms of H and F values to explain their reasonability. The methodology proposed in this study could be helpful in finding out the optimal solution for annual mobile geomagnetic measurements for middle-term earthquake forecasting.

Water Temperature Changes Related to Strong Earthquakes: The Case of the Jinjia Well, Southwest China

Systematic measurements of water temperature are lacking but useful in understanding the relationship between water temperature and earthquakes. Based on the water temperature data, geological structure, borehole structure, and temperature gradient in the Jinjia well, Southwest China, we systematically analysed the water temperature changes related to earthquakes. The water temperature of the Jinjia well recorded the coseismic changes caused by the Wenchuan M7.9 and Panzhihua M6.1 earthquakes in 2008. We also found abnormal changes in the water temperature, after which moderate to strong earthquakes occurred in the surrounding region. The preseismic abnormal changes of the Jinjia well were rising-recovery (rising to a high value and continuing for a period of time before decreasing or quickly recovering), with the range of 0.007–0.07 °C. The maximum change (0.07 °C) occurred before the M7.9 Wenchuan earthquake in 2008. According to the Molchan error diagram, the most likely time for an earthquake to occur is within approximately 4 months after the water temperature exceeds the threshold temperature. In the Jinjia well, the installation depth of the temperature sensor affected the correlation between the temperature changes and earthquakes with a seismic energy density above 10−3 J·m−3. The shorter the distance between the sensor and the fault, the higher the probability of water temperature changes related to earthquakes.

Accuracy requirements for the road friction coefficient estimation of a friction-adaptive automatic emergency steer assist (ESA)

The number of traffic accidents resulting in personal injury and property damage is increasingly being reduced by effective advanced driver assistance systems (ADAS). Nevertheless, many traffic accidents still cannot be prevented today because they are due to wet, snow- and ice-covered roads. For this reason, the Institute of Automotive Engineering (IAE) of the Technical University of Braunschweig is investigating the road friction coefficient sensitivity and adaptation of advanced driver assistance systems (ADAS) currently in series production from 2018 to 2021 as part of the ‘Road Condition Cloud’ research project funded by the German Research Foundation (DFG) to increase driving safety, particularly on wet, snow- and ice-covered roads. In this article, the road friction coefficient sensitivity and adaptation of an automatic emergency steer assist is simulatively investigated. This assist overrides the driver to automatically execute an evasive maneuver. The driving maneuver used is a standardized obstacle-avoidance maneuver that is simulatively repeated on a dry, wet, snow- and ice-covered road. The road friction coefficient sensitivity shows that this test is already failed on a wet road because the simulated vehicle does not pass the second lane without errors. Subsequently, a road friction coefficient adaptation of the emergency steer assist is investigated. This adaptation varies the maximum lateral acceleration of the evasive trajectory depending on an estimated value of the road friction coefficient in order not to exceed the maximum adhesion coefficient of the wheels during the evasive maneuver. Ideally, the estimated value matches the true road friction coefficient so that the second lane is passed without errors even on a wet, snow- and ice-covered road. In contrast, an existing difference determines whether the second lane is reached. Finally, the necessary accuracy requirements of the road friction coefficient estimation are determined in an novel estimation error diagram. A road friction coefficient adaptation increases the driving safety of driver advanced assistance systems (ADAS) that are in series production today and future highly automated driving functions (HAF) and is necessary for automated driving because the driver is not present as a fallback level. The described results were presented before in [1].

Statistical evaluation of earthquake forecast efficiency using earthquake-catalog and fault slip rate in the Sichuan-Yunnan region, China

Epicenter locations are generally adjacent to active faults and past seismicity regions. Past earthquake catalogs and the geometry of the active faults can provide key prior knowledge concerning earthquake forecasts. In this study, we first introduce two straightforward dedicated models, the proximity-to-past-earthquakes (PPE) and proximity-to-mapped-faults (PMF) models, to fit the seismicity in the Sichuan-Yunnan region, China. The hybrid proximity-to-known-sources (PKS) model with the optimized model parameters is then used to estimate the probability of earthquake occurrence. Second, to compare the PKS forecast efficiency to those of different models, retrospective tests are applied to a dataset located in the Sichuan-Yunnan region. The results show that the probability maps derived from PPE, PMF, and PKS have non-uniform Poisson distribution features and that there is forecasting significance for past cases of moderate earthquakes in the test region. Finally, using Molchan error diagram tests, we find that the hybrid PKS model performs better than the other models in the testing region. The unsatisfactory performance of the PMF model for earthquake forecasting may lie both in the incompleteness of the fault database and the lack of consideration of co-seismic ruptures. Therefore, one of the three models can be used as a base model for comparing and evaluating earthquake forecast strategies.

Coarse-graining research of the thermal infrared anomalies before earthquakes in the Sichuan area on Google Earth engine

Seismo-induced Thermal infrared (TIR) anomalies has been proposed as a significant precursor of earthquakes. Several methods have been proposed to detect Thermal infrared anomalies that may be associated with earthquakes. However, there is no comparison of the influence for Thermal infrared extraction methods with a long time statistical analysis. To quantify the effects of various techniques used in Thermal infrared anomaly extraction, in this paper, we offer a complete workflow of their comparative impacts. This study was divided into three parts: anomaly detection, statistical analysis, and tectonic factor research. For anomaly detection, daily continuous nighttime surface temperature (ConLST) data was obtained from the Google Earth Engine (GEE) platform, and each different anomaly detection method was used to detect Thermal infrared outliers in the Sichuan region (27°-37°N, 97°-107°E). During statistical analysis, The heated core model was applied to explore Thermal infrared anomalies which is to filter anomalies unrelated to earthquakes by setting time-space-intensity conditions. The 3D error diagram offers scores to assume the best parameter set using training-test-validation steps. In the final part, we considered information on stresses, active faults, and seismic zones to determine the optimal parameters for extracting the Thermal infrared anomalies. The Kalman filter method detected the highest seismic anomaly frequency without considerating the heating core condition. The Autoencoder and Isolation Forest methods obtain the optimal alert type and parameter set to determine if the anomaly is likely earthquake-related. The RST method performs optimally in the final part of the workflow when it considers physical factors such as active faults, seismic zones, and stresses. However, The six methods we have chosen are not sufficient to contain the entire Thermal infrared anomaly extraction. The consideration of tectonic factors in the research remains poorly developed, as statistical methods were not employed to explore the role of constructive factors. Nevertheless, it is a significant factor in comparing anomaly extraction methods and precursor studies.

A New 3-D Error Diagram for a More Balanced Assessment of Binary Alarms for Predicting Earthquakes: Application to TIR Anomalies in Sichuan Area, China

A New 3-D Error Diagram for a More Balanced Assessment of Binary Alarms for Predicting Earthquakes: Application to TIR Anomalies in Sichuan Area, China

Application of 3D Error Diagram in Thermal Infrared Earthquake Prediction: Qinghai–Tibet Plateau

Earthquakes are the most dangerous natural disasters, and scholars try to predict them to protect lives and property. Recently, a long-term statistical analysis based on a “heating core” filter was applied to explore thermal anomalies related to earthquakes; however, some gaps are still present. Specifically, (1) whether there are differences in thermal anomalies generated by earthquakes of different magnitudes has not yet been discussed; and (2) thermal anomalies in high-spatial-resolution data are often distributed in spots, which is not convenient for statistics of thermal anomalies. To address these issues, in this study, we applied high-spatial-resolution thermal infrared data to explore the performance of the “heating core” for earthquake prediction at different magnitudes (i.e., 3, 3.5, 4, 4.5, and 5). The specific steps were as follows: first, the resampling and moving-window methods were applied to reduce the spatial resolution of the dataset and extract the suspected thermal anomalies; second, the “heating core” filter was used to eliminate thermal noise unrelated to the seismic activity in order to identify potential thermal anomalies; third, the time–distance–magnitude (TDM) windows were used to establish the correspondence between earthquakes and thermal anomalies; finally, the new 3D error diagram (false discovery rate, false negative rate, and space–time correlation window) and the significance test method were applied to investigate the performance under each minimum magnitude with training data, and the robustness was validated using a test dataset. The results show that the following: (1) there is no obvious difference in the thermal anomalies produced by earthquakes of different magnitudes under the conditions of a “heating core”, and (2) the best model with a “heating core” can predict earthquakes effectively within 200 km and within 20 days of thermal anomalies’ appearance. The binary prediction model with a “heating core” based on thermal infrared anomalies can provide some reference for earthquake prediction.

How Useful Are Strain Rates for Estimating the Long-Term Spatial Distribution of Earthquakes?

Strain rates have been included in multiplicative hybrid modelling of the long-term spatial distribution of earthquakes in New Zealand (NZ) since 2017. Previous modelling has shown a strain rate model to be the most informative input to explain earthquake locations over a fitting period from 1987 to 2006 and a testing period from 2012 to 2015. In the present study, three different shear strain rate models have been included separately as covariates in NZ multiplicative hybrid models, along with other covariates based on known fault locations, their associated slip rates, and proximity to the plate interface. Although the strain rate models differ in their details, there are similarities in their contributions to the performance of hybrid models in terms of information gain per earthquake (IGPE). The inclusion of each strain rate model improves the performance of hybrid models during the previously adopted fitting and testing periods. However, the hybrid models, including strain rates, perform poorly in a reverse testing period from 1951 to 1986. Molchan error diagrams show that the correlations of the strain rate models with earthquake locations are lower over the reverse testing period than from 1987 onwards. Smoothed scatter plots of the strain rate covariates associated with target earthquakes versus time confirm the relatively low correlations before 1987. Moreover, these analyses show that other covariates of the multiplicative models, such as proximity to the plate interface and proximity to mapped faults, were better correlated with earthquake locations prior to 1987. These results suggest that strain rate models based on only a few decades of available geodetic data from a limited network of GNSS stations may not be good indicators of where earthquakes occur over a long time frame.

Study of water resources parameters using artificial intelligence techniques and learning algorithms: a survey

Qualitative analysis of water resources is one of the most widely used topics in water resources research today. Researchers use various analysis methods of water parameters to achieve the desired goals in this field. This research uses artificial intelligence (AI), learning machine (LM), data mining, and mathematical techniques to simulate water behavior and estimate its parametric changes. The proposed model used in this study was a Self-adaptive Extreme learning machine (SAELM) to estimate hydrogeological parameters of the Meghan wetland located in Markazi province in Iran. In addition, SAELM simulation results were compared to Least square support vector machine (LSSVM), Multiple linear regression (MLR), and Adaptive Neuro-fuzzy inference system (ANFIS) models. The simulated parameters were Electrical Conductivity (EC), Total Dissolved Solids (TDS), Groundwater Level (GWL), and salinity. This information was related to sampling for 175 months in the study area. Finally, after simulation operation, four models were introduced as superior models. Mentioned exceptional models were SAELM in GWL modeling, SAELM in modeling the EC, MLR in salinity simulation, and LSSVM in the simulation of TDS parameters. Moreover, by five approaches, the models' performance was evaluated. Suggested strategies were performance evaluation by statistical indicators, Wilson score method uncertainty analysis (WSMUA), response & correlation plots, discrepancy ratio charts, and distribution error diagrams. Based on statistical indicators, the SAELMGWL model was the most accurate model with RMSE, MAPE, and R2 indices equal to 0.1496, 0.0043, and 0.9933, respectively. The ANFIS model had the worst results in simulation.

Analisis Kesalahan Ejaan Pada Teks Eksposisi Siswa Kelas V Sekolah Dasar Persatuan Umat Islam Haurgeulis

The importance of using good and correct language rules needs to be trained and applied from an early age in elementary schools and madrasah Ibtidaiyah thus there are no errors or mistakes in language. Elementary school students are guided to be able to understand spelling rules following the General Guidelines for Indonesian Spelling (PUEBI) in language skills, one of which is writing skills. They can provide information in their writings correctly thus the readers can understand the message or opinion conveyed easily.Researchers focus on two scopes, namely; the mistakes of fifth graders of SD PUI Haurgeulis In using capital letters, the punctuation marks and commas, the use of words in expository essays, and their understanding of Indonesian spelling.This study is used the descriptive qualitative method. For the data collection, researchers conducted observations, interviews, and documentation. At the data analysis stage, the researchers reduce the data, encode, present, and finally find conclusions from the processed data. The result of this study indicates that students quite understand spelling in Indonesian properly and correctly. The students' errors in the use of spelling are as follows; as many as 156 capital letter errors occupy the number 67%, as many as 26 punctuation errors occupy the number 22%, then the last as many as 51 errors in word usage occupy the number 11%, and all included in the overall percentage error diagram contained in the essays of class students V SD PUI Haurgeulis.

Analisis Kesalahan Ejaan Pada Teks Eksposisi Siswa Kelas V Sekolah Dasar Persatuan Umat Islam Haurgeulis

The importance of using good and correct language rules needs to be trained and applied from an early age in elementary schools and madrasah Ibtidaiyah thus there are no errors or mistakes in language. Elementary school students are guided to be able to understand spelling rules following the General Guidelines for Indonesian Spelling (PUEBI) in language skills, one of which is writing skills. They can provide information in their writings correctly thus the readers can understand the message or opinion conveyed easily.Researchers focus on two scopes, namely; the mistakes of fifth graders of SD PUI Haurgeulis In using capital letters, the punctuation marks and commas, the use of words in expository essays, and their understanding of Indonesian spelling.This study is used the descriptive qualitative method. For the data collection, researchers conducted observations, interviews, and documentation. At the data analysis stage, the researchers reduce the data, encode, present, and finally find conclusions from the processed data. The result of this study indicates that students quite understand spelling in Indonesian properly and correctly. The students' errors in the use of spelling are as follows; as many as 156 capital letter errors occupy the number 67%, as many as 26 punctuation errors occupy the number 22%, then the last as many as 51 errors in word usage occupy the number 11%, and all included in the overall percentage error diagram contained in the essays of class students V SD PUI Haurgeulis.

RST Analysis of Anomalous TIR Sequences in Relation with Earthquakes Occurred in Turkey in the Period 2004–2015

The paper provides, for the first time, a long-term (>10 years) analysis of anomalous transients in Earth’s emitted radiation over Turkey and neighbouring regions. The RST (Robust Satellite Techniques) approach is used to identify Significant Sequences of Thermal Anomalies (SSTAs) over about 12 years (May 2004 to October 2015) of night-time MSG-SEVIRI satellite images. The correlation analysis is performed with earthquakes with M ≥ 4, which occurred in the investigated period/region within a pre-defined space-time volume around SSTA occurrences. It confirms, also for Turkey, the possibility to qualify SSTAs among the candidate parameters of a multi-parametric system for time-Dependent Assessment of Seismic Hazard (t-DASH). After analysing about 4000 images (about 400 million of single satellite records), just 155 SSTAs (about 4 every 100 images) were isolated; 115 (74% out of the total) resulted in earthquake-related (false-positive rate 26%). Results of the error diagram confirms a non-casual correlation between RST-based SSTAs and earthquake occurrences, with probability gain values up to 2.2 in comparison with the random guess. The analysis, separately performed on Turkish areas characterized by different faults and earthquakes densities, demonstrates the SSTA correlation with a dynamic seismicity more than with static tectonic settings.

Efficiency of earthquake forecast models based on earth tidal correlation with background seismicity along the Tonga\u2013Kermadec trench

The correlation between Earth’s tides and background seismicity has been suggested to become stronger before great earthquakes and weaker after. However, previous studies have only retrospectively analyzed this correlation after individual large earthquakes; it thus remains vague (i) whether such variations might be expected preceding future large earthquakes, and (ii) the strength of the tidal correlation during interseismic periods. Therefore, we retrospectively investigated whether significant temporal variations of the tidal correlation precede large interplate earthquakes along the Tonga–Kermadec trench, where Mw 7-class earthquakes frequently occurred from 1977 to 31 December 2020. We evaluated a forecast model based on the temporal variations of the tidal correlation via Molchan’s error diagram, using the tidal correlation value itself as well as its rate of change as threshold values. For Mw ≥ 7.0 earthquakes, this model was as ineffective as random guessing. For Mw ≥ 6.5, 6.0, or 5.5 earthquakes, the forecast model performed better than random guessing in some cases, but even the best forecast only had a probability gain of about 1.7. Therefore, the practicality of this model alone is poor, at least in this region. These results suggest that changes of the tidal correlation are not reliable indicators of large earthquakes along the Tonga–Kermadec trench.Graphical

Bifurcation Analysis and Synchronous Patterns between Field Coupled Neurons with Time Delay

Neurons encode and transmit signals through chemical synaptic or electrical synaptic connections in the actual nervous system. Exploring the biophysical properties of coupling channels is of great significance for further understanding the rhythm transitions of neural network electrical activity patterns and preventing neurological diseases. From the perspective of biophysics, the activation of magnetic field coupling is the result of the continuous release and propagation of intracellular and extracellular ions, which is very similar to the activation of chemical synaptic coupling through the continuous release of neurotransmitters. In this article, an induction coil is used to connect two HR neurons to stimulate the effect of magnetic field coupling. It is inevitable that time delays can affect the coupling process in the transmission of information, and it should be considered in the coupled model. Firstly, the firing characteristics and bifurcation modes of two coupled HR neurons are studied by using one parameter and two parameters bifurcation. With the increase of propagation delay and coupling gain, the chaotic state of neurons disappears and the high‐period window decreases due to the influence of energy transfer between neurons. Then, the synchronization patterns of two HR neurons with different stimulation are analyzed by error diagrams and time series diagrams. It is confirmed that the synchronous pattern has certain regularity and is related not only to the neurons with large stimulation current but also to the time delay and coupling gain. The research conclusions of this article will provide the corresponding theoretical basis for medical experiments.

DAMPAK PANDEMI COVID-19 TERHADAP KESALAHAN BERBAHASA PADA TEKS ILMIAH MAHASISWA IAIN BONE

The study aims to describe the error of Indonesian done the student at covid-19 pandemic. This research is a descriptive type. The source of the data in this study are the student of IAIN Bone. The instruments used in this research include observation sheets, reading, and note-taking techniques. Analytical techniques used in analyzing data-error language i.e. qualitative data analysis techniques. The results of this research show that there were errors in using Indonesian, which include standard words, phonological, morphological, syntactic, and percentage of the language error diagram. The advice of this research, the lecturer or the teacher can use the results of the analysis on language errors made by students as reflection of learning.

Investigation of sand production prediction shortcomings in terms of numerical uncertainties and experimental simplifications

Sand production is one of the main research topics in the petroleum industry. This problematic phenomenon is related to the mechanical and hydrodynamic behavior and reservoir specifications. Sand production often leads to equipment damage and significant losses. This is usually studied by experimental and numerical methods. This study first gives a brief overview of the methods used to predict sand production in terms of experimental tests, numerical simulation, and field data. The main objective of this research is to highlight the shortcomings of these methods. In addition, experimental hollow cylinder test data and widely used continues numerical simulation are used to investigate these shortcomings. This study is performed by scrutinizing the most important and basic parameters in numerical modeling including two constitutive models (Mohr-Coulomb elastic-perfectly plastic and Mohr-Coulomb cohesion softening/friction hardening failure criteria) and various element sizes and shapes. Since most studies use continuum approaches, it was decided to use a finite difference program. Further, to reduce the undesirable influencing factors the fracture energy regularization method was implemented to diminish mesh dependency related to energy dissipation. In addition, a mesh size sensitivity analysis was performed to show the effects of size, shape and pattern of mesh on the results and cumulative probability distribution versus absolute relative error diagrams were applied to compare the accuracy of the models. After all, the best model of prediction was selected to simulate a real sand production in an oil well with 50° inclination and 6 SPF in North Sea Reservoir. Review of experimental papers shows that these tests usually have several hypotheses for simplification. Rock strength, stress state, fluid flow properties, test duration, and sample dimensions are the most important parameters in sand production tests. Researchers usually focus on only one or two of these parameters, which may lead to many errors in contrast to reality. In addition, numerical methods have some deficiencies such as mesh size problems, lack of critical-state-based constitutive models, sanding criteria, and lack of sufficient research for the calibration procedure in the DEM model. A small change in both the numerical simulation input data and the experimental procedure leads to different results. Indeed, the experimental test of sand production with multiple hypotheses can qualitatively simulate the steps and shape of well or perforation failure not the exact sand production rate. Also, numerical simulation results are very sensitive due to uncertainties and errors of the model and input data. It has been shown that the results are highly dependent on every simple parameter such as the shape of the elements. The differences between experimental results and numerical modeling in only one perforation can be 2 to 10 times. Despite all errors and uncertainties in both the laboratory and modeling studies, the simulation of a real sand production in North Sea Reservoir with same sized element was relatively acceptable. This level of accuracy of the model can be very helpful in subsequent decision making and sand control management.

A well-trained feed-forward perceptron Artificial Neural Network (ANN) for prediction the dynamic viscosity of Al2O3–MWCNT (40:60)-Oil SAE50 hybrid nano-lubricant at different volume fraction of nanoparticles, temperatures, and shear rates

In this study, the influence of volume fraction of nanoparticles (φ) and temperature on dynamic viscosity (μnf) of Al2O3 –MWCNT (40:60) - Oil SAE50 hybrid nano-lubricant was analyzed. For this reason, μnf of a new hybrid nano-lubricant has derived for 174 various experiments through a series of experimental tests including a combination of different φ, temperatures and shear rates (γ̇). A well trained Artificial Neural Network (ANN) is created using the trainbr/trainlm algorithm and showed an MSE value of 3.58 along 0.999 as correlation coefficient for prediction of μnf. Variant Error diagrams and error histograms proved the appropriateness of the ANN as a tool for determining the μnf and the capability of the used training algorithms. In this analysis, the most effective factor on the μnf is the temperature and a decrease in temperature value has an impressive growth of μnf value for all φ. The results show that the φ has a negligible effect on the output parameter (μnf) especially in higher temperatures in a manner that by enhancing the φ, the μnfwill increase for all temperatures, while this enhance is more noticeable in lower temperatures. For example, enhancing the φ from 0 to 1%, almost will not change the μnf while this change of φ causes around 40% increase of μnf in T = 60 °C. Also, γ̇has a non-uniform influence on the μnf, in a sense that in lower γ̇, the μnf has much higher values for different combinations of temperature and φ; on the other hand, by increasing the γ̇, the μnfhas much lower values with narrower bandwidth for various temperatures and φ.