Search

One of the respiratory disorders is obstructive sleep apnea (OSA). OSA occurs when a person sleeps. OSA causes breathing to stop momentarily due to obstruction in the airways. In this condition, people with OSA will be deprived of oxygen, sleep awake and short of breath. Diagnosis of OSA by a doctor can be done by confirming the patient's complaints during sleep, sleep patterns, and other symptoms that point to OSA. Another way of diagnosing OSA is a polysomnography (PSG) examination in the laboratory to analyze apnea and hypopnea. However, this examination tends to be high cost and time consuming. An alternative diagnostic tool is an electrocardiogram (ECG) examination referring to changes in the mechanism of ECG-derived respiration (EDR). So digital ECG signal analysis is a potential tool for OSA detection. Therefore, in this study, it is proposed to classify OSA based on ECG signals using wavelets and statistical parameters. Statistical parameters include mean, variance, skewness kurtosis entropy calculated on the signal decomposition results. The validation performance of the proposed method is carried out using a support vector machine, k-nearest neighbor (k-NN), and ensemble classifier. The proposed method produces the highest accuracy of 89.2% using a bagged tree where all features are used as predictors. From this study, it is hoped that ECG signal analysis can be used to complete clinical diagnosis in detecting OSA.

Uncertainties in power system studies are typically managed by Monte Carlo methods or by applying some worst case assumptions. As the number of uncertainties increases, there is a need for methods that can estimate statistical parameters from a limited number of calculations. This paper utilizes a method called the Unscented Transform together with Cornish-Fisher expansion to estimate the 2%-value of switching overvoltages using only about one tenth the number of calculations as a Monte Carlo method, with similar accuracy. The uncertainties considered are the energizing instants of the three phases. The method is illustrated through EMT simulations in PSCAD and it is shown to provide a good approximation of the 2%-value in most of the studied cases.

Design of bridge piers and abutments is significantly impacted by hydrodynamic processes that cause scouring of the foundation. Although, many empirical formulae are available in the literature to estimate the depth of scouring, but they suffer from several limitations. A major limitation of empirical formulae is that they are largely applicable to the hydraulic conditions for which they have been derived. In this research, a deep neural network (DNN) has been developed and applied to predict the depth of scour around bridge piers and abutments. The practicality of the proposed model has been demonstrated using the experimental data sets consisting of 211 data points. The novelty of the DNN model applied herein lies in the use of Adam Optimizer for optimizing the parameters of the DNN model. The performance of the DNN model was evaluated for each parameter set using statistical indicators such as the coefficient of determination, root mean square error, and mean absolute error. A regression equation based upon the available data set has also been proposed. Based upon the values of the statistical parameters, the DNN model has been found to be significantly better than the regression model. The model proposed herein performs better than the regression model. A distinct practical advantage of the model proposed herein is that it eliminates the need of hit and trial procedure to determine the optimal parameter set for the model.

There is a direct link between the extent of formation damage and the filtration volume of the drilling fluids in hydrocarbon reservoirs. The filtration volume could be diminished by adding different additives to the drilling fluids. Recently, nanoparticles have been extensively used for enhancing the filtration characteristics of the drilling fluids. However, there is no reliable model for investigating the influence of this class of additives on the performance of drilling fluids. Hence in this study, two powerful tools ELM (Extreme Learning Machine) and PSO-LSSVM (Particle Swarm Optimization-Least Square Support Vector Machine) are applied to determine the effect of various nanoparticles on the filtration volume. The assessment of the models is carried out by computing the statistical parameters and it was found that ELM has a greater ability to predict the filtration volumes, while PSO-LSSVM performs satisfactorily too. The model predictions and experimental results are in excellent agreement as suggested by the values of root mean squared error (RMSE = 0.2459), coefficient of determination (R2 = 0.999), and mean relative error (MRE = 2.028%) for the dataset. The statistical analysis showed that the suggested model can predict the filtration volume with great accuracy. Moreover, through sensitivity analysis of the input parameters, it was found that for a specified nanoparticle, the filtration volume is highly influenced by nanoparticle concentration and it is the essential variable for the optimization process.

There are numerous correlations and thermodynamic models for predicting the natural gas hydrate formation condition but still the lack of a simple and unifying general model that addresses a broad ranges of gas mixture is highly felt. This study was aimed to develop a user-friendly universal correlation based on hybrid group method of data handling (GMDH) for prediction of hydrate formation temperature of a wide range of natural gas mixtures including sweet and sour gas. To establish the hybrid GMDH, the total experimental data of 343 were obtained from open articles. The selection of input variables was based on the hydrate structure formed by each gas species. The modeling resulted in a strong algorithm since the squared correlation coefficient (R2) and root mean square error (RMSE) were 0.9721 and 1.2152, respectively. In comparison to some conventional correlation, this model represents not only the outstanding statistical parameters but also its absolute superiority over others. In particular, the result was encouraging for sour gases concentrated at H2S to the extent that the model outstrips all available thermodynamic models and correlations. Leverage statistical approach was applied on datasets to the discovery of the defected and doubtful experimental data and suitability of the model. According to this algorithm, approximately all the data points were in the proper range of the model and the proposed hybrid GMDH model was statistically reliable.

Gas release and its dispersion is a major concern in chemical industries. In order to manage and mitigate the risk of gas dispersion and its consequences, it is necessary to predict gas dispersion behavior and its concentration at various locations upon emission. Therefore, models and commercial packages such as Phast and ALOHA have been developed. Computational fluid dynamics (CFD) can be a useful tool to simulate gas dispersion in complex areas and conditions. The validation of the models requires the employment of the experimental data from filed and wind tunnel experiments. It appears that the use of the experimental data to validate the CFD method that only includes certain monitor points and not the entire domain can lead to unreliable results for the intended areas of concern. In this work, some of the trials of the Kit Fox field experiment, which provided a wide-range database for gas dispersion, were simulated by CFD. Various scenarios were considered with different mesh sizes, physical conditions, and types of release. The results of the simulations were surveyed in the whole domain. The data matching each scenario was varied by the influence of the dominant displacement force (wind or diffusivity). Furthermore, the statistical parameters suggested for the heavy gas dispersion showed a dependency on the lower band of gas concentration. Therefore, they should be used with precaution. Finally, the results and computation cost of the simulation could be affected by the chosen scenario, the location of the intended points, and the release type.

The quality of cement-treated soil columns is normally assured based on the unconfined compressive strength qu of core samples. qu of core samples varies spatially and the statistical parameters of qu (i.e., mean µqu, variance [Formula: see text], and autocorrelation distance θqu) are adopted in quality assurance procedures. The statistical parameters of qu evaluated from the core sample strengths have a statistical uncertainty depending on the statistical sample size. The present study investigates the influence of the statistical sample size on the evaluation of overall strength of a cement-treated soil column. A probabilistic framework in which a Bayesian inference analysis and a finite element method analysis are incorporated is used to calculate the overall strength while simultaneously considering the statistical uncertainty and spatial variability of core strength. The probabilistic framework is briefly described, and a parametric analysis is performed to investigate the influence of the statistical sample size on the evaluation of the overall strength of a full-scale column. The numerical results show that the sample size and spatial correlation influence the variability of the overall strength, and the influence can be reasonably described using an equivalent number of independent data.

Joint roughness is one of the most important issues in the hydromechanical behavior of rock mass. Therefore, the joint roughness coefficient (JRC) estimation is of paramount importance in geomechanics engineering applications. Studies show that the application of statistical parameters alone may not produce a sufficiently reliable estimation of the JRC values. Therefore, alternative data-driven methods are proposed to assess the JRC values. In this study, Gaussian process (GP), K-star, random forest (RF), and extreme gradient boosting (XGBoost) models are employed, and their performance and accuracy are compared with those of benchmark regression formula (i.e. Z2, Rp, and SDi) for the JRC estimation. To analyze the models’ performance, 112 rock joint profile datasets having eight common statistical parameters (Rave, Rmax, SDh, iave, SDi, Z2, Rp, and SF) and one output variable (JRC) are utilized, of which 89 and 23 datasets are used for training and validation of models, respectively. The interpretability of the developed XGBoost model is presented in terms of feature importance ranking, partial dependence plots (PDPs), feature interaction, and local interpretable model-agnostic explanations (LIME) techniques. Analyses of results show that machine learning models demonstrate higher accuracy and precision for estimating JRC values compared with the benchmark empirical equations, indicating the generalization ability of the data-driven models in better estimation accuracy.

Accurate measurement of acoustic velocities of sedimentary rocks is essential for prediction of rock elastic constants and well failure analysis during drilling operations. Direct measurement by advanced logging tools such as dipole sonic imager is not always possible. For older wells, such data are not available in most cases. Therefore, it is an alternate way to develop a reliable correlation to estimate the shear wave velocity from existing log and/or core data. The objective of this research is to investigate the nature of dependency of different reservoir parameters on the shear wave velocity (Vs) of clastic sedimentary rocks, and to identify the parameter/variable which shows the highest level of dependency. In the study, data-driven connectionist models are developed using machine learning approach of least square support vector machine (LSSVM). The coupled simulated annealing (CSA) approach is utilized to optimize the tuning and kernel parameters in the model development. The performance of the simulation-based model is evaluated using statistical parameters. It is found that the most dependency predictor variable is the compressional wave velocity, followed by the rock porosity, bulk density and shale volume in turn. A new correlation is developed to estimate Vs, which captures the most influential parameters of sedimentary rocks. The new correlation is verified and compared with existing models using measured data of sandstone, and it exhibits a minimal error and high correlation coefficient (R2 = 0.96). The hybridized LSSVM-CSA connectionist model development strategy can be applied for further analysis to predict rock mechanical properties. Additionally, the improved correlation of Vs can be adopted to estimate rock elastic constants and conduct wellbore failure analysis for safe drilling and field development decisions, reducing the exploration costs.

For a Maxwell-Boltzmann gas (MB) it is known that T (temperature) is a statistical parameter related to the average energy. It appears in f(ei) = C exp(-ei/T) so T has the same units as ei, a single particle energy. If T increases, ei increases identically if ei/T is treated as constant. Thinking in terms of ei=pp/2m, this means the momentum spread (i.e. variance of the Gaussian increases) and one expects entropy to increase In (1) we argued that exp(-ei/T) for an MB gas and exp(ipx) for a quantum free particle (constant p), follow from the same statistical rule P(a1)P(a2)=P(a1+a2), but ei is a scalar and p a vector. Furthermore exp(ipx) is associated with spatial invariance and the generator of translations d/dx. In this note, we try to argue that a constant p may act as a statistical parameter just as T, although in this case hbar/p has the behaviour of a length i.e. the wavelength. If p increases (just like T is increased), the wavelength decreases meaning there are more peaks in a fixed length or more entropy, we argue. Thus there seems to be a statistical mechanical similarity to increasing T for an MB gas and to increasing p for a single free quantum particle. The association of x and p in exp(ipx) has implications, not only for the resolution of x space, but the increased entropy suggested by more peaks of cos(px). In addition, this means more peak places for impulses to occur. Thus a large p not only represents a large impulse, but is associated with more peak points for this impulse to be delivered and more entropy. In (2) we argued that the humps of cos(px) encode information about the impulse/force used to create p and which may be delivered if p hits an object. Thus there is a somewhat unusual relationship between p and x that one does not find in Newtonian mechanics, but has its roots in special relativity i.e. in the Lorentz invariant -Et+px. We suggest that just like exp(-V(x)/T) in an MB gas means that for a large force=-dV/dx, exp(-V/T) changes rapidly in x, a large p, associated with a large force should also imply that the humps in exp(ipx) rise (and fall) sharply, thus leading to sharp peaks. Thus sharp peaks are indicative of high internal force and increased entropy for a free particle exp(ipx), we argue.

A new image measurement method for obtaining time-mean velocity field is proposed. The so-called time-averaged contrast is a statistical parameter of image data. Its characteristics are examined in detail with a simple mathematical model for particle images. It is found that the variance of image data gives the time-averaged contrast in time. Numerical simulation shows the possibility of practical measurement.

This article provides an overview of the most popular discrete probability distributions. Both univariate and multivariate distributions are discussed. The distributions covered in this article are: Bernoulli, binomial, geometric, hypergeometric, multinomial, negative binomial, Poisson, and discrete uniform.

Background The ability to combine with the high-temperature applications even in less sunlight distinguishes vacuum tube solar collectors (VTSCs) from other collectors. Loading nanoparticles can lead to effectiveness enhancement. In this numerical study, using regression-based methods the thermal behavior of VTSCs filled with SiO2/EG-water was evaluated. Methods For this purpose, using the statistical parameters of R-square and margin of deviation (MOD), the appropriate number of neurons for the artificial neural network (ANN) was determined. Findings The results showed that using ANN for the prediction of outlet temperature was successful. Considering R2 > 0.99 and MOD According to the output temperature predicted by ANN, the instantaneous/overall efficiencies were calculated with a maximum error of 7% and 0.298%. Moreover, the approved ANN for instantaneous efficiency has R2 > 0.886 while this figure for overall efficiency was greater than 0.9999.

We have developed a massive-parallel, multi-purpose Monte Carlo (MC) code for simulation of light propagation in complex structures modelled with e.g. magnetic resonance images. The code is designed to execute parallel threads on a Linux-based cluster of computers equipped with multiple graphical processing units (GPU) utilizing NVidia CUDA technology. We show steps one can take to implements such code itself. Furthermore, we provide methodology of building a MRI-based head model and populating it with realistic optical properties at excitation and fluorescence emission wavelengths during inflow of fluorescence agent (indocyanine green – ICG). The proposed code provides following original features: (i) Simulation of fluorescence light propagation in media with spatial distribution of multiple different fluorophores characterized by concentration, quantum yield and fluorescence lifetime. (ii) The fluorescence light tracking does not need extra photon tracking and works in parallel with tracking photons at the excitation wavelength, introducing execution time overhead of 0.02% only. (iii) Calculation of high-resolution spatial distributions of sensitivity factors mapping voxels absorption change to parameters measured on a model surface: statistical parameters (moments) of the distribution of time of flight of photons. (iv) Random number generators states are preserved between runs to greatly improve calculation time of the sensitivity factors. (v) Simulation of fluorescence lifetime wide field imaging in diffusively scattering media. The code is designed to handle big models, divided into e.g. 200 million voxels or more, which other methods struggle to handle. Simulations on a human head model with 0.3 mm voxel size require 2 GB of a GPU memory only. This is supported by developed non-standard floating-point data storage format. The proposed code is cross-validated with field-leading MC and finite element methods on the same hardware environment for varying model sizes and temporal resolutions. Tests revealed competitive execution time and high temporal resolution of boundary data for high spatial resolution of MRI-based head model.

The main aims of this study are related to present nonlinear analysis and prediction model for evaluating and predicting the performance of composite castellated steel beam (CCSB) under fire and static load. This study includes two parts, including parametric study and the prediction models. The beam size, concrete thickness, temperature, and beam length are considered as the independent variables in the parametric study. Among considered independent variables in this study, the increasing concrete thickness has a negligible positive effect on the load carrying capacity. In addition, gene expression programming (GEP), three regression models such as multiple linear regression (MLR), principal component regression (PCR), and multiple Ln equation regression (MLnER), the combination of GEP and MLR, and the combination of GEP, MLnER, and MLR are used to predict the load carrying capacity of the castellated beam. The maximum positive and negative errors, mean of absolute percentage error (MAPE), and statistical parameters such as the coefficient of determination, root mean square error (RMSE), normalized square error (NMSE), and fractional bias are utilized to evaluate and compare the performance of the models. According to the results of these parameters, the two best models specify. In addition, a distribution error table is used to specify the best model. Based on the results of this table and statistical parameters, the combination of GEP and MLR is considered as the best model for predicting the load carrying capacity of CCSBs.

Demand for solar energy is increasing due to its clean nature in contrast to conventional fossil fuel sources and lowering of the cost harvesting solar energy. Consequently, it’s important to assess the spatio-temporal distribution and future projection of global horizontal irradiance (GHI) under future climate scenarios. However, due to the absence of high-quality ground observations, whether related to the measuring site accessibility or the associated high cost of equipment, it’s generally difficult to get GHI at the desired spatial interval. Empirical calibrated models may be used for estimating GHI using other local meteorological parameters available at finer spatial interval. The present study compared the performance of four popular empirical models including a newly proposed MND model with an intention to reduce model complexity. The models are calibrated and validated over nineteen locations spread over four climatic zones of India. The results reveal that the MND model performs more efficiently than the other three models. Statistical parameters also confirm the accuracy level of MND. Four sets of common coefficients are generated for projection of daily GHI in any location of the respective four zones. Finally, temperature and rainfall data sets projected by the CMIP5 models, corresponding to 23 locations across the West Bengal State, are used to produce GHI for four future periods under four Representative Concentration Pathway scenarios. Simulated results support the view of having less GHI availability in the near future. In general, the whole State might experience a deficit in annual mean daily GHI by ≥1 MJ m-2day−1.

In practical timber engineering, various problems widely exist in the current reliability assessment for the bearing capacity of components. Improving the current assessment standards of timber components has important guiding significance for their design and repairing optimization. Considering the long-term load effect and the latest code GB50005-2017 of timber structures with a new resistance coefficient, a superior limit state function (LSF) of timber components with bearing capacity was established. Using this realistic LSF, the reliability index values β were discussed and analyzed by two versions of Chinese codes (GB50068-2001 and GB50068-2018) with different load partial coefficients γL and three design reference periods (DRPs) with different statistical parameters. Furthermore, the four-level reliability assessment standardization with bearing capacity was improved based on superior LSF, different load partial coefficients and three DRPs. The results showed that the load partial coefficients γL and DRPs significantly impact the reliability index values β. By contrast, the impact load partial coefficients and DRPs on the limits of four-level assessment (k) is less significant than that on the reliability index values β. The practical four-level assessment standardization is improved based on the target reliability index [β] and superior level principles. The reasonableness and superiority of the four-level reliability assessment standardization were verified by calculating the 28 different load cases, 3 different DRPs and 26 kinds of ratios k of resistance to load effect. To meet the requirements of the minimum reliability index values β, this study suggests that the bearing capacity design values of R/γ0S are set to 1.0, 0.93, and 0.87 as the limits of au/bu, bu/cu, and cu/du for main timber components, while values of R/γ0S are set to 1.0, 0.87, and 0.82 as the limits for general timber components.

Site-specific seismic hazard analysis is crucial for designing earthquake resistance structures, particularly in seismically active regions. Shear wave velocity (VS) is a key parameter in such analysis, although the economy and other factors restrict its direct field measurement in many cases. Various VS-SPT-N correlations are routinely incorporated in seismic hazard analysis to estimate the value of VS. However, many uncertainties question the reliability of these estimated VS values. This paper comes up with a statistical approach to take care of such uncertainties involved in VS calculations. The measured SPT-N values from all the critical boreholes were converted into statistical parameters and passed through various correlations to estimate VS at different depths. The effect of different soil layers in the boreholes on the VS estimation was also taken into account. Further, the average shear wave velocity of the top 30 m soil cover (VS30) is estimated after accounting for various epistemic and aleatoric uncertainties. The scattering nature of the VS values estimated using different VS-N correlations was reduced significantly with the application of the methodology. Study results further clearly demonstrated the potential of the approach to eliminate various uncertainties involved in the estimation of VS30 using general and soil-specific correlations.

Malaria is a major public health concern, affecting over 3.2 billion people in 91 countries. The advent of digital microscopy and Machine learning with the aim of automating Plasmodium falciparum diagnosis extensively depends on the extracted image features. The color of the cells, plasma, and stained artifacts influence the topological, geometrical, and statistical parameters being used to extract image features. During microscopic image acquisition, custom adjustments to the condenser and color temperature controls often have an influence on the extracted statistical features. But, our human visual system sub-consciously adjusts the color and retains the originality in a different lighting environment. Despite the use of appropriate image preprocessing, findings from the literature indicate that statistical feature variations exist, allowing the risk of P. falciparum misinterpretation. In order to eliminate this pervasive variation, the current work focuses on preprocessing the extracted statistical features rather than the prepossessing of the source image. It begins with the augmentation of series images for a microscopic field by inducing illumination variations during the microscopic image acquisition stage. A set of such image series is analyzed using a Nonlinear Regression Model to generalize the relationship between microscopic images acquired with variable ambient brightness and a specific feature. The projection point of the centroid feature onto the brightness parameter is identified in the model and it is denoted as the optimum brightness factor (OBF). Using the model, the feature correction factor (CF) is calculated from the rate of change of feature values over the interval OBF, and the brightness of the test image is processed. The present work has investigated OBF for selected image textural features, namely Contrast, Homogeneity, Entropy, Energy, and Correlation individually from its co-occurrence matrices. For performance analysis, the best state-of-the-art method uses selected texture as a subset feature to evaluate the effectiveness of P. falciparum malaria classification. Then, the impact of proposed feature processing is evaluated on 274 blood smear images with and without Feature Correction (FC). As a result, the "p" value is less than .05, which leads to the result that it is highly significant and the classification accuracy and F-score of P. falciparum malaria are increased.

The excess sediment load in canals generally causes the silting problem. The vortex chamber type silt excluders are used to extract the excess sediments from the canals to increase its discharge carrying capacity. The silt removing efficiency of silt excluder is generally calculated using the available empirical equations. The prediction results of the existing empirical equations were not found satisfactory. To improve the prediction results, a new model was developed using the artificial neural network (ANN). The experimental data were trained to developed the ANN model. The performance of developed ANN model was evaluated using two different statistical parameters MSE and R. These performance parameters suggest that the accuracy of developed ANN model improved significantly than that of other available empirical equations. The R value was found to be equal to 0.9863 which is quite closer to 1. In addition to this, the removal efficiency predicted using the ANN model lies within the error band of ± 20% which is more accurate than that predicted by existing empirical relationships in which the estimated removal efficiency lies within the error band on ± 40%.

In this paper, we use the correlation between the average wind speed and the elevation above sea level to present a regression model for calculating the average wind speed and evaluating the wind potential in the southern region of Ecuador. After obtaining the regression model, an adjustment factor based on the topographic slope has been included, mainly since the wind speed could vary largely as it blows across the lower slope regions or intermediate hills of mountains. Once the wind speed was obtained, both at 10 m and 100 m, the wind power density was calculated, which includes the impact of wind speed and air density. Finally, the model accuracy was obtained by comparing other free access data sources including actual data from meteorological stations, using statistical parameters to quantify the error. According to the results obtained, we find that wind speed has a good correlation with the terrain elevation of the southern region of Ecuador. The simulated wind speed compared to the actual data has errors between 7.75% and 16.89%, which indicates that the model can predict with > 83% accuracy. In addition, both the root means square error and the standard deviations have around 1 m/s of error.

In this paper, an improved fractal interpolation model is proposed to reconstruct the surface topography of composite hole wall. This model adopts the maximum positive deviations and maximum negative deviations between the measured values and trend values to determine the contraction factors. Hole profiles in 24 directions are measured. Fractal parameters are calculated to evaluate the measured surface profiles. The maximum and minimum fractal dimension of the hole wall are 1.36 and 1.07, whereas the maximum and minimum fractal roughness are 4.05 × 10−5 and 4.36 × 10−10 m, respectively. Based on the two-dimensional evaluation results, three-dimensional surface topographies in five typical angles (0°, 45°, 90°, 135°, and 165°) are reconstructed using the improved model. Fractal parameter Ds and statistical parameters Sa, Sq, and Sz are used to evaluate the reconstructed surfaces. Average error of Ds, Sa, Sq, and Sz between the measured surfaces and the reconstructed surfaces are 1.53%, 3.60%, 5.60%, and 9.47%, respectively. Compared with the model in published literature, the proposed model has equal reconstruction effect in relatively smooth surface and is more advanced in relatively rough surface. Comparative results prove that the proposed model for calculating contraction factors is more reasonable.

Digital elevation models (DEMs) enable extraction of stream networks, delineation of watersheds and determination of geomorphological characteristics. A widely used method for stream network extraction is to specify a threshold area required to initiate a channel. This is achieved by applying a threshold area value (As) in GIS software which displays the accumulated flow to each cell. In this study, the effect of the assigned As on the direct runoff hydrographs was analyzed. Of using different threshold values varying in a wide range, stream network extraction and watershed delineation were performed, and then stream orders, main channel lengths and related morphometric parameters were computed. The geomorphological instantaneous unit hydrograph (GIUH) theory was adopted to obtain the hydrological response of the watershed and three direct runoff hydrographs were considered for validation. Statistical parameters and cumulative density functions of both observed and simulated hydrographs were computed and uncertainty analysis was performed. The best performing value of As with respect to the stream order and main channel length was determined using hesitant probabilistic fuzzy linguistic sets for different runoff hydrographs and criteria considered. It was found that the As value affected the stream order as expected and a stream order of maximum 3 was adequate for estimation of the runoff hydrograph with acceptable accuracy without unreasonably increasing the computational effort.

The size of a fracture within a rock mass can be obtained using borehole sampling data or exposed surfaces. This paper aims at building a method to estimate the fracture size, without the presupposed size distribution, based on full three-dimensional geometric parameters (shape, orientation and position). In this study, the rock fracture was considered as an elliptical plane, and each set of fractures had the same aspect ratio. The statistical parameters of fracture size were derived, from sample (sub fracture group) to population (parent fracture group), based on multiple borehole samples. Parent fracture group simulations were realized using MATLAB, and the codes were designed by the authors. Moreover, in-situ time domain electromagnetic methods (TEM) and borehole induced polarization methods (BPM) were used to validate the Monte Carlo simulation. The results revealed that the statistical rules of Monte Carlo simulation of the parent fracture group are similar to those of the in-situ detection.

Ambulatory electrocardiogram ( ECG ) recordings from patients undergoing severe physical stress are corrupted by large muscle artifacts ( EMG ) and other noise sources, such as baseline drifts and currents induced by motion artifacts and electromechanical devices. A simple real-time algorithm has been developed which is suitable for on-line detection of the QRS complexes. The algorithm calculates several statistical parameters of the ECG signal which are used to adapt the threshold to baseline changes in the signal, thereby increasing detection sensitivity.

The present study was conducted in Baitarani basin up to Anandapur gauging station of Odisha covering an area of 8603.7 km2. Pre-processing of basin from digital elevation model (DEM) was done using HEC-Geo-HMS extension and spatial analyst tool in ArcGIS. These pre-processed files were then imported to HEC-HMS for simulating runoff. In this study, runoff simulation was done using two methods, viz., composite and distributed curve number (CN) approaches. SCS curve number method was used for computation of runoff volume, SCS UH method for direct runoff, constant- monthly varying base flow method for base flow and Muskingum method for flow routing. The model was calibrated and validated using both composite and distributed CN approaches. Data from 1st January, 2007 to 31st December, 2013 were used for calibration and 1st January, 2014 to 31st December, 2016 were used for validation. During the calibration period of composite CN approach, the statistical parameters like Nash-Sutcliffe efficiency (NSE), Coefficient of determination (R2), Percent bias (PBIAS) and RMSE-observations standard deviation ratio (RSR) were found to be 0.51, 0.63, 12.82 and 0.7, respectively and during the validation period they were found to be 0.53, 0.54, -19.73 and 0.7, respectively. In case of distributed CN approach, the statistical parameters like NSE, R2, PBIAS and RSR were found to be 0.62, 0.63, -8.64 and 0.6, respectively during the calibration period and 0.67, 0.66, -2.25 and 0.6, respectively during the validation period. The study indicated that distributed CN approach is more accurate than composite CN approach in simulation of runoff using HEC-HMS model.

Artificial Neural Network (ANN) architecture contains three main (input, hidden and output) layers. The connections are established between layers through weights and bias. The various simulators are available to implement ANN. But, a knowledge on the numerical investigation and application of ANN for arbitrary values related by a nonlinear function is essential for the better understanding of a nature-inspired algorithm. Hence, the present manuscript provides the mathematical implementation of an algorithm for known values of independent and dependent variables, with and without bias. The predictability of ANN was assessed by a statistical parameter, mean squared error (MSE). The MSE by ANN algorithm was found to be higher (0.008) without bias than with bias for arbitrary values of independent and dependent variables. Hence, it could be concluded that the bias reduces error and enhances the predictability .

This article displays an application of the statistical method moti- vated by Bruno de Finetti's operational subjective theory of probability. We use exchangeable forecasting distributions based on mixtures of linear com- binations of exponential power (EP) distributions to forecast the sequence of daily rates of return from the Dow-Jones index of stock prices over a 20 year period. The operational subjective statistical method for comparing distributions is quite different from that commonly used in data analysis, because it rejects the basic tenets underlying the practice of hypothesis test- ing. In its place, proper scoring rules for forecast distributions are used to assess the values of various forecasting strategies. Using a logarithmic scoring rule, we find that a mixture linear combination of EP distributions scores markedly better than does a simple mixture over the EP family, which scores much better than does a simple Normal mixture. Surprisingly, a mix- ture over a linear combination of three Normal distributions also makes a substantial improvement over a simple Normal mixture, although it does not quite match the performance of even the simple EP mixture. All sub- stantive forecasting improvements become most marked after extreme tail phenomena were actually observed in the sequence, in particular after the abrupt drop in market prices in October, 1987. However, the improvements continue to be apparent over the long haul of 1985-2006 which has seen a number of extreme price changes. This result is supported by an analysis of the Negentropies embedded in the forecasting distributions, and a proper scoring analysis of these Negentropies as well.

In this study, the detection of wear faults in spur gears was examined using vibration analysis, statistical process control method, and statistical parameters. For this purpose, a closed-loop test rig with a power transmission system was established. Defect-free gears were attached to the test assembly, and the system was operated at a specific torsional load and number of cycles until the gears were worn. Vibration amplitudes at vertical and horizontal directions, received via sensors on the bearings, were transferred to the computer with a digital-analog converter. The control charts were plotted by sampling 30 data points per hour. Upper and lower control limits were determined by using the data obtained from the defect-free gears. The gears are worn in the process due to the effect of applied torque and the operation conditions suitable for the formation of defects. As a result, the vibration amplitudes were increased. The accuracy and convergence of the statistical process control method were verified by the statistical parameters root mean square, kurtosis value, skewness value, crest factor, and peak-to-peak values. It was emphasized that great convergence and accuracy between the statistical process control results and statistical parameters results are achieved. The present study showed that the detection of abrasion of a robust gear could be graphically demonstrated through a real-time experimental study. The statistical process control method is convenient and easily applicable, which allows constructing a real-time early warning system detecting malfunctions at the start.

Over the years, many organizations across the globe have conducted various studies pertaining to air pollution and its ill effects. The results of these studies substantially conclude that a plethora of people succumbs to the adversities caused by the ever-increasing air pollutants. In this investigation, M5P, random forest (RF)- and Gaussian process (GP)-based approaches are used to predict the tropospheric ozone for Amritsar, Punjab state of India, metropolitan area. The models proposed were based on ten input parameters viz. particulate matter PM2.5, particulate matter PM10, sulphur dioxide (SO2), nitrogen dioxide (NO2), nitric oxide (NO), ammonia (NH3), temperature (T), solar radiation (SR), wind direction (WD) and wind speed (WS), while the tropospheric ozone (O3) was an output parameter. Three most popular statistical parameters such as correlation coefficient (CC), mean absolute error (MAE) and root mean square error (RMSE) were used for the assessment of the developed models. In comparison, it was found that better results were achieved with random forest-based model with CC value as 0.8850, MAE value as 0.0593 and RMSE value as 0.0772 for testing stage. The suggested models are expected to save cost of instrument, cost of labour work, time and contribute to greater accuracy. A result of sensitivity investigation concludes that the solar radiation is the most influencing parameter in estimating the actual values of O3 based on the current data set.

Based on the previously obtained results of the Data Mining - based Classification and Regression Trees (C&RT) technique application to industrial Ni-based superalloys, multiple regression models were developed to describe quantitatively the chemical composition effects on the alloys tensile strength. The regression models obtained were verified for adequacy in three ways, contrary to the conventional approach requiring only several inadequacy variance values calculations. Namely, the following verification methods were applied: traditional R2 coefficient calculations; comparisons of computer and experimental frequency distributions of the quality indexes; Monte-Carlo simulated and experimental data based scatter plots comparing. It was emphasized that, according to the general statistic principle, close coincidence of the Monte-Carlo simulated and real frequency distributions of any measured characteristic values means full formal (statistical) identity of the real and simulated objects. Hence, in addition, coincidence of the corresponding scatter plots statistical parameters should be considered as a sign of the physical identity of real and modeled regression dependencies. All the applied verification methods show the excellent results that leads to conclusion about high workability of the obtained models in practical and theoretical applications. An additional general advantage of the models was noted: their physically interpretable structure, that provides the opportunity to determine and analyze the effects of individual chemical elements and their interactions under real industrial conditions. Most of the obtained results and the formulated conclusions, especially related to the chemical elements individual effects are in good accordance with the known experimental and theoretic data for polycrystalline Ni-based superalloys. Meantime, some unexpected features, particularly, for the interactions of Nb, Ti, Cu with each other and grain boundaries were revealed, showing necessity of further in dept investigations.

Purpose The resistance of steel plate shear walls (SPSW) under explosive loads is evaluated using nonlinear FE analysis and surrogate methods. This study uses the conventional weapons effect program (CONWEP) model for the explosive load and the Johnson-Cook model for the steel plate. Based on the Taguchi method, 25 samples out of 100 samples are selected for a parametric study where we predict the damaged zones and the maximum deflection of SPSWs under explosive loads. Then, this study uses a multiple linear regression (MLR), multiple Ln equation regression (MLnER), gene expression programming (GEP), adaptive network-based fuzzy inference (ANFIS) and an ensemble model to predict the maximum detection of SPSWs. Several statistical parameters and error terms are used to evaluate the accuracy of the different surrogate models. The results show that the cross-section in the y-direction and the plate thickness have the most significant effects on the maximum deflection of SPSWs. The results also show that the maximum deflection is related to the scaled distance, i.e. for a value of 0.383. The ensemble model performs better than all other models for predicting the maximum deflection of SPSWs under explosive loads. Design/methodology/approach The SPSW under explosive loads is evaluated using nonlinear FE analysis and surrogate methods. This study uses the CONWEP model for the explosive load and the Johnson-Cook model for the steel plate. Based on the Taguchi method, 25 samples out of 100 samples are selected for a parametric study where we predict the damaged zones and the maximum deflection of SPSWs under explosive loads. Then, this study uses a MLR, MLnER, GEP, ANFIS and an ensemble model to predict the maximum detection of SPSWs. Several statistical parameters and error terms are used to evaluate the accuracy of the different surrogate models. The results show that the cross-section in the y-direction and the plate thickness have the most significant effects on the maximum deflection of SPSWs. The results also show that the maximum deflection is related to the scaled distance, i.e. for a value of 0.383. The ensemble model performs better than all other models for predicting the maximum deflection of SPSWs under explosive loads. Findings The resistance of SPSW under explosive loads is evaluated using nonlinear FE analysis and surrogate methods. This study uses the CONWEP model for the explosive load and the Johnson-Cook model for the steel plate. Based on the Taguchi method, 25 samples out of 100 samples are selected for a parametric study where we predict the damaged zones and the maximum deflection of SPSWs under explosive loads. Then, this study uses a MLR, MLnER, GEP, ANFIS and an ensemble model to predict the maximum detection of SPSWs. Several statistical parameters and error terms are used to evaluate the accuracy of the different surrogate models. The results show that the cross-section in the y-direction and the plate thickness have the most significant effects on the maximum deflection of SPSWs. The results also show that the maximum deflection is related to the scaled distance, i.e. for a value of 0.383. The ensemble model performs better than all other models for predicting the maximum deflection of SPSWs under explosive loads. Originality/value The resistance of SPSW under explosive loads is evaluated using nonlinear FE analysis and surrogate methods. This study uses the CONWEP model for the explosive load and the Johnson-Cook model for the steel plate. Based on the Taguchi method, 25 samples out of 100 samples are selected for a parametric study where we predict the damaged zones and the maximum deflection of SPSWs under explosive loads. Then, this study uses a MLR, MLnER, GEP, ANFIS and an ensemble model to predict the maximum detection of SPSWs. Several statistical parameters and error terms are used to evaluate the accuracy of the different surrogate models. The results show that the cross-section in the y-direction and the plate thickness have the most significant effects on the maximum deflection of SPSWs. The results also show that the maximum deflection is related to the scaled distance, i.e. for a value of 0.383. The ensemble model performs better than all other models for predicting the maximum deflection of SPSWs under explosive loads.

Permeability is a vital parameter in reservoir engineering that affects production directly. Since this parameter's significance is obvious, finding a way for accurate determination of permeability is essential as well. In this paper, the permeability of two notable carbonate reservoirs (Ilam and Sarvak) in the southwest of Iran was predicted by several different methods, and the level of accuracy in all models was compared. For this purpose, Multi-Layer Perceptron Neural Network (MLP), Radial Basis Function Neural Network (RBF), Support Vector Regression (SVR), decision tree (DT), and random forest (RF) methods were chosen. The full set of real well-logging data was investigated by random forest, and five of them were selected as the potent variables. Depth, Computed gamma-ray log (CGR), Spectral gamma-ray log (SGR), Neutron porosity log (NPHI), and density log (RHOB) were considered efficacious variables and used as input data, while permeability was considered output. It should be noted that permeability values are derived from core analysis. Statistical parameters like the coefficient of determination ( ), root mean square error (RMSE) and standard deviation (SD) were determined for the train, test, and total sets. Based on statistical and graphical results, the SVM and DT models perform more accurately than others. RMSE, SD and R2values of SVM and DT models are 0.38, 1.63, 0.97 and 0.44, 2.89, and 0.96 respectively. The results of the best-proposed models of this paper were then compared with the outcome of the empirical equation for permeability prediction. The comparison indicates that artificial intelligence methods perform more accurately than traditional methods for permeability estimation, such as proposed equations. Doi: 10.28991/HEF-2021-02-02-01 Full Text: PDF