MSE Criterion Research Articles

Aircraft Accident and Crash Images Processing with Machine Learning

The aviation industry is in constant need of innovations in terms of safety and operational efficiency. In this context, low-light image enhancement technologies play an important role in a numerous areas of disciplines, from night flights to accident and collision investigations. Machine learning, deep learning methods and traditional methods not only provide the aviation industry with an effective image processing and improvement capacity in low light conditions, but also reveal important information by analysing the data of low-light images of crashed and destroyed aircraft. Within the scope of the study, traditional methods, deep learning method and machine learning are combined in order to enhance and process low-light ambient images of crashed and destroyed aircraft. By using Swish and Tanh activation functions together in the deep learning model, the performance of the neural networks used in the process of improving low-light environment images was improved and the image quality was increased. The enhanced images were evaluated and compared using PSNR and MSE as objective quality assessment measures. According to the PSNR and MSE criteria, the numerical results obtained from the image enhancement studies of the deep learning model were calculated as 29.85 and 100.44, respectively. The results introduce that the deep learning model provides better image enhancement than traditional methods. In conclusion, improvement of low-light image and processing is an important technological advancement in the aviation industry, enabling safer and more efficient operations. The successful of machine learning include deep learning and traditional methods shows that the aviation industry will achieve a safer and innovative structure in the future.

Using the Bayesian method to estimate and comparison the regression of the exponential and gamma survival (Simulation)

Parametric regression models It is one of the oldest and most common regression models and can be defined as one of the statistical methods that is used to describe and estimate the relationship between a dependent random variable and explanatory random variables. These models have types, including quantitative models, of their linear and non-linear types, and qualitative models that The dependent variable is a binary response variable. These models are characterized by the fact that all cases that are studied are assumed to be normally distributed and measurable, and that the regression function determines the parameters that cannot be changed except by changing the number of variables included in the study, relying on probability distributions, which are the exponential distribution and the Gamma, we will obtain parametric regression models, which are the exponential regression model, and the gamma regression model, relying on the Cox regression model to be used in forming these models, which are models that require the presence of information and hypotheses about the distribution of the population used in the test that is appropriate for the units or data, as well as the variables that enter. The test or experiment on which the survival function is based, in this thesis, it was proposed to estimate the parameters of these models using the Bayesian method. The simulation method was used to generate data that follows parametric survival regression models according to various factors. The simulation results showed that the third model of the exponential probability distribution of the survival function shows the lowest value according to the MSE criterion. This indicates that Increasing the sample size typically reduces the standard mean error (MSE), which is used as an indicator of the differences between expected and actual values in statistical estimates. Simply put, the larger the sample size, the more accurate the statistical predictions are and the lower the standard deviation from the actual values, indicating that larger samples often contribute to improving the accuracy of statistical estimates.

On some two parameter estimators for the linear regression models with correlated predictors: simulation and application

Regression analysis is widely used to predict the response variable utilizing one or more predictor variables. In many fields of study, the predictors are highly correlated causing multicollinearity problem that severely affects the efficiency of ordinary least square (OLS) estimators by significantly inflating their variances. To solve the multicollinearity problem, various one and two parameter ridge estimators are available in literature. In this article, a class of modified two parameter Lipovetsky–Conklin ridge estimators is proposed based on eigen values of X ′ X matrix that provide an automatic dealing option for treating different levels of multicollinearity. An extensive simulations study followed by real life example is used to evaluate the performance of proposed estimators based on MSE criterion. In most of the simulation conditions, our proposed estimators outperformed the existing estimators.

PER CAPITA CONSUMPTION ESTIMATION IN SURABAYA USING ENSEMBLE MODEL APPROACH

The categorization of the Low-Income Community category is based on the poverty indicators in the Multidimensional Poverty Index, including the dimensions of health, education, and living standards. The Proxy Means Test (PMT) can estimate household income or consumption by taking into account household conditions that are readily observable and cannot be manipulated. This method offers the advantage of being capable of determining both the poverty level of a household and the household's characteristics based on asset ownership and socio-demographic conditions. This study aims to estimate per capita consumption using OLS, Robust, Quantile, LASSO, and Ensemble methods. The application of these methods is intended to address various issues, including the presence of outlier data, multicollinearity, and uncertainties. The results indicate that none of the four methods used achieved the highest accuracy based on the MSE, MAE, and sMAPE criteria. Consequently, employing an ensemble model becomes essential to accommodate the element of uncertainty present in these four models. The application of the ensemble method is not only as a comparison between the models, but also as a means to capture the uncertainty contained in each model

Expectation Parameters in the Poisson Mixture Regression Model for Latent Class by Applying Genetic Algorithm and Maximization Algorithm

In a Poisson mixture regression model for latent class, observations come from different sub-sources or classes, and the observed data are assumed to be generated by a specific (finite) mixture of unobserved or latent classes. The problem lies in the optimal assignment of observations to their respective classes. This requires sophisticated methods for estimating the parameters in the model. Usually, the model parameters are estimated by the conventional EM algorithm. The research aims to compare the EM algorithm and the genetic algorithm GA. Using simulation, the two algorithms were compared based on the MSE criterion, with different sample sizes (n = 50, 90, 120) and three scenarios (S1, S2, S3) for default values of the parameters. The results showed the superiority of the GA genetic algorithm over the EM algorithm, as the GA genetic algorithm gave the lowest MSE values. Paper type: Research paper

A two-parameter estimator for correlated regressors in gamma regression model

Gamma Modified Two Parameter (GMTP) is a novel biased two-parameter estimator proposed to address the effects of multicollinearity in Generalized Linear Models (GLMs). An expansion of the linear regression model's Modified Two Parameters (MTP) is the newly suggested estimator. The performance of the GMTP estimator over the maximum likelihood estimator (MLE), gamma ridge estimator (GRE), gamma Liu estimator (GLE), and gamma Liu-type estimator (GLTE) reviewed in this article are theoretically compared, and the estimator's properties is discussed. A simulation study that examine the effects of the dispersion parameter, sample size, explanatory variables, and degree of correlation are used to examine the superiority of the GMTP with four different biasing parameters over the MLE, GRE, GLE, and GLTE with regard to the estimated MSE criterion. The GMTP estimator with biasing parameters and outperforms the MLE, GRE, GLE, and GLTE, according to simulation research. More research can be done to see how well the GMTP estimator performs in comparison to other estimators that were not examined in this study. 2 k 4 k

Machine learning prediction in distortion behavior of unsymmetric laminates under hygrothermal environment

This paper deals with the effects of curing process and hygrothermal environment on the distortion behaviors of continuous carbon fiber reinforced polyamide 6 (CF/PA6) unsymmetric laminates. To accurately characterize the shape of CF/PA6 unsymmetric laminates in the water absorption process, the 3D model reconstruction with different water content is carried by combining 3D scanner and secondary development in Abaqus. A full-field displacement comparison method is proposed to calculate the equivalent thermal/moisture expansion coefficient, and the effectiveness of numerical simulation is verified. The dataset with 2816 instances is further constructed through finite element method. Through grid search and five-fold cross validation, the ANN model is trained and validated according to R 2 and MSE criterion. The well-trained ANN model builds the mapping relationship between lay-up design parameters, hygrothermal environment and the distortion parameters of unsymmetric laminates.

A new approach for estimating variance of a population employing information obtained from a stratified random sampling

In this article, we suggest an enhanced estimator for the estimation of finite population variance using twofold auxiliary variable under stratified random sampling. The numerical expressions for the bias and MSE are determined up to the first order of approximation. In order to effectively validate the theoretical findings, three actual data sets are included. Additionally, the application of the suggested estimators is demonstrated using a simulation study. Results of an empirical comparison among the suggested and existing estimators were investigated. To determine how good the suggested estimator, in comparison to the preliminary estimators, the MSE criterion is used. The suggested estimator has a smaller MSE and better PRE than existing estimators, according to numerical results utilizing actual data sets and a simulation analysis.

A Tarso model for studying the level of the Cuiabá river

The Cuiabá River registers cyclical occurrences of floods and droughts over the years, according to the hydrological periods, thus characterizing a non-linear behavior. The prediction of the level of the Cuiabá river is important to help institutions such as the Civil Defense of the state of Mato Grosso and many other institutions that are concerned with the prevention and mitigation of natural disasters. Thus, this study considered the nonlinear Threshold Autoregressive Self-Excking Open-loop (TARSO) model with 2 regimes, with a Bayesian approach. We tested models to which values of the linimetric quota (riverwater level in millimeters) with and without rainfall (mm) were associated. All models were compared using the lowest DIC, MAPE and MSE criterion, and the TARSO (2; 1, 0, 3, 1, 1) model performed best according to these criteria. Finally, the selected model was shown to produce reliable predictions.

A simulation study: An enhanced generalized class of estimators for estimation of population proportion using twofold auxiliary attribute

The article introduces a novel class of estimators designed for estimating finite population proportions. These estimators utilize dual auxiliary attributes and are applicable under simple random sampling. The proposed class of estimators includes various members with distinct characteristics. The article provides numerical terminologies for the bias and MSE of the estimators, acquire up to first order of approximation. Four actual data sets are used. Additionally, a simulation study is accompanied to perceive the presentations of estimators. The MSE criterion is used to assess how well the proposed estimator performed as likened to the preliminary estimators. The simulation analysis revealed that, in contrast to other examined estimators, the suggested class of estimators provided better results. The empirical investigation offers evidence to substantiate the findings of the argument. Theoretical research also displays that the suggested class of estimators outperforms its competitors.

PERBANDINGAN MODEL ARIMA DENGAN MODEL NONPARAMETRIK POLINOMIAL LOKAL DAN SPLINE TRUNCATED UNTUK PERAMALAN HARGA MINYAK MENTAH WEST TEXAS INTERMEDIATE (WTI) DILENGKAPI GUI R

Crude oil as one of the most important natural resources experiences price fluctuations from time to time, even the spot price of West Texas Intermediate (WTI) world crude oil on 20th April 2020 reached -36,98 USD/barrel due to the Covid-19 pandemic. WTI oil price data was modeled using the ARIMA method, local polynomial, and spline truncated nonparametric regression then compared and obtained the best model and formed R Graphical User Interface (GUI). The ARIMA model and nonparametric time series models can be used to model time series data, but in the ARIMA model there are assumptions that must be fulfilled. Nonparametric time series models, which include local polynomial model and truncated spline do not need to fulfill these assumptions. The ARIMA model obtained did not fulfilled the assumptions of normality and residual homoscedasticity, so the modeling was stopped and modeling was only carried out using nonparametric regression methods. Based on the minimum MSE criteria, the best nonparametric model was obtained, namely nonparametric truncated spline model with degrees 3 and 3 knot points which was categorized as a strong model based on R-squared in sample value and having a very good forecasting ability based on MAPE out sample value.

Use of a Convolutional Neural Network for Predicting Fuel Consumption of an Agricultural Tractor

The energy crisis and depleting fossil fuel resources have always been the focus of researchers. Fuel consumption of agricultural tractors is not an exception. Researchers have used different methods to predict fuel consumption. With the development of artificial intelligence in the last decade, all re-searchers’ attention has been directed towards it. Deep learning is a subset of machine learning, which was inspired by the data processing patterns in the human brain. The deep learning method has been used in research due to the advantages of high accuracy and generalization. So far, no research has used this method to predict fuel consumption. In this research, field experiments were carried out in sandy clay loam and clay soils to model the temporal fuel consumption and specific fuel consumption of an agricultural tractor using a convolutional neural network (CNN), while having some parameters such as the soil type, soil conditions, tool parameters, and operation pa-rameters. The experiments were conducted within each soil texture in a factorial manner based on the randomized complete block design (RCBD) with three replicates. For each soil texture, various moisture levels (8–17% for dry and 18–40% for moist soils), tractor forward speeds (1.2, 1.6, 1.8, and 2.2 km h−1), working depths (30 and 50 cm), the number of passes (2 and 6), and tire inflation pressure (20 and 25 psi) were selected, and cone index, dynamic load, and moisture content were measured in each experimental section. The designed networks used to predict the instant fuel consumption were of a CNN type. The results indicated that the network developed based on the Sgdm algorithm outperformed the others, and thus it was selected for modeling purposes. The network was evaluated based on R2 and MSE criteria. For the temporal fuel consumption, the best results were obtained while using 8-510-510-1 architecture with R2 = 0.9729 and MSE = 0.0049. The 8-100-95-1 architecture also led to the best prediction of the specific fuel consumption with R2 of 0.9737 and MSE of 0.0054. The high prediction accuracy and low error in this research compared to previous studies indicate the superiority of this method in order to predict fuel consumption. It was also observed from the results that the input parameters, which include soil, tool, and operational parameters, are all effective on fuel consumption. Proper management of some parameters, such as working depth, tire inflation pressure, and forward speed, can help to optimize fuel consumption.

Simultaneous bandwidths determination for DK-HAC estimators and long-run variance estimation in nonparametric settings

We consider the derivation of data-dependent simultaneous bandwidths for double kernel heteroscedasticity and autocorrelation consistent (DK-HAC) estimators. In addition to the usual smoothing over lagged autocovariances for classical HAC estimators, the DK-HAC estimator also applies smoothing over the time direction. We obtain the optimal bandwidths that jointly minimize the global asymptotic MSE criterion and discuss the tradeoff between bias and variance with respect to smoothing over lagged autocovariances and over time. Unlike the MSE results of Andrews, we establish how nonstationarity affects the bias-variance tradeoff. We use the plug-in approach to construct data-dependent bandwidths for the DK-HAC estimators and compare them with the DK-HAC estimators from Casini that use data-dependent bandwidths obtained from a sequential MSE criterion. The former performs better in terms of size control, especially with stationary and close to stationary data. Finally, we consider long-run variance (LRV) estimation under the assumption that the series is a function of a nonparametric estimator rather than of a semiparametric estimator that enjoys the usual rate of convergence. Thus, we also establish the validity of consistent LRV estimation in nonparametric parameter estimation settings.

A Novel Unbiased Deep Learning Approach (DL-Net) in Feature Space for Converting Gray to Color Image

Gray to Color conversion causes difficulties because of the nature of its intrinsic multi-modality. Despite recent significant advancements in this domain by numerous learning-based approaches, there still have two drawbacks: i) implausible color assignment and ii) contextual ambiguity. Recently deep learning models are being used for colorization as they outperform others. In a training image, desaturated color components are greater than saturated color components due to the larger background areas (clouds, pavement, dirt, walls, etc.) compared to the focused objects. This imbalanced feature representation biases the learning model in favor of major features. However, small regions with specific colors are the region of interest. To solve this problem, we proposed the Deep Localization Network (DL-Net) by modifying the mean squared error backpropagation algorithm. We compute chromatic component-based Local Losses (LLs) which are the primary component of the proposed DL-Net. The LL employs priority on rare semantic components of the original image features. It works to improve diverse-range dependency modeling in an effort to reduce contextual ambiguity and color leakage that promotes the production of more plausible coloring. With a number of current methodologies, we contrast our proposed approach. The experimental findings demonstrate that our proposed method produces good colorization of images and outperforms other methods in terms of SSIM, MSE, and PSNR quality criteria.

Image Segmentation Using Haar Wavelet Transform and Artificial Network for Identification of Ant Nest Pattern

Ant nest is a powerful medicinal plant to treat various diseases such as heart disease, tumors, cancer, hemorrhoids, tuberculosis, rheumatism, ulcers and prostate disorders. The many benefits generated cause the ant nest to have a selling value in the community, so it is not uncommon to trigger ant nest forgery. This study aims to identify the image of an ant nest by testing the accuracy of the backpropagation network and haar wavelet. Before the identification process with the backpropagation method is carried out, first the process of taking the characteristics of the ant nest is carried out which will later be used as test data input in the identification process. The output of the network will be compared with the target to get the error output. Then these errors are propagated again to increase the network weight to minimize errors. This research resulted in an ant nest identification application. The backpropagation ANN architecture for the training data used is 0.95 momentum, 0.01 target error with MSE criteria, the maximum number of training iterations (epochs) is set at 5000, the learning rate is 0.1 and the number of hidden layers is 20 by using wavelet haar feature extraction level 3 and the backpropagation momentum method can be used. used to identify ant nest images with 100% accuracy.

Random Ensemble MARS: Model Selection in Multivariate Adaptive Regression Splines Using Random Forest Approach

Multivariate Adaptive Regression Splines (MARS) is a supervised learning model in machine learning, not obtained by an ensemble learning method. Ensemble learning methods are gathered from samples comprising hundreds or thousands of learners that serve the common purpose of improving the stability and accuracy of machine learning algorithms. This study presented REMARS (Random Ensemble MARS), a new MARS model selection approach obtained using the Random Forest (RF) algorithm. 200 training and test data set generated via the Bagging method were analysed in the MARS analysis engine. At the end of the analysis, two different MARS model sets were created, one yielding the smallest Mean Square Error for the test data (Test MSE) and the other yielding the smallest Generalised Cross-Validation (GCV) value. The best model was estimated for both Test MSE and GCV criteria by examining the error of measurement criteria, variable importance averages, and frequencies of the knot values for each model. Eventually, a new model was obtained via the ensemble learning method, i.e., REMARS, that yields result as good as the MARS model obtained from the original data set. The MARS model, which works better in the larger data set, provides more reliable results with smaller data sets utilising the proposed method.

Forecasting the variability of stock index returns with the multifractal random walk model for realized volatilities

We adapt the multifractal random walk model by Bacry et al. (2001) to realized volatilities (denoted RV-MRW) and take stock of recent theoretical insights on this model in Duchon et al. (2012) to derive forecasts of financial volatility. Moreover, we propose a new extension of the binomial Markov-switching multifractal (BMSM) model by Calvet and Fisher (2001) to the RV framework. We compare the predictive ability of the two against 10 classical and multifractal volatility models. Forecasting performance is evaluated out-of-sample based on the empirical MSE, MAE, and QLIKE criteria as well as using model confidence sets following the methodology of Hansen et al. (2011). Overall, our empirical study for 14 international stock market indices has a clear message: The RV-MRW is the best model throughout under the MAE criterion, i.e., for all indices and forecast horizons between one day and 100 days, with uniform results for forecast evaluations against both realized volatilities and squared returns or during tranquil/turbulent market periods. Based on the evaluation of MSE and QLIKE forecast errors, the RV-MRW, RV-BMSM, and RV-ARFIMA provide the most accurate forecasts during our tranquil sample from 2016–2018, where we can observe a transition from RV-MRW dominating long-term forecasts to RV-BMSM and RV-ARFIMA dominating in the short term. The new RV-BMSM takes the lead in phases of more turbulent market dynamics (sample 2010–2012), when it appears throughout in the 90% model confidence set at horizons ≤10 days and for 13 out of 14 indices at 20 days. These results are very promising if we consider that this is the first empirical application of the RV-MRW and RV-BMSM. Moreover, whereas RV-ARFIMA forecasts are often a time-consuming task, the RV-MRW stands out due to its fast execution and straightforward implementation.

Forecasting future climate boundary maps (2021–2060) using exponential smoothing method and GIS

Future-oriented forecasts have an important place in making forward-looking decisions and planning. At the beginning of these studies is the monitoring and detection of climate change. The climate is very variable. Therefore, by making predictions about the climate, preliminary information about how and to what extent the climate will change can be obtained, and accordingly, necessary precautions can be taken quickly. This study aims to produce predictive climate boundary maps using Geographic Information Systems (GIS), in which climate classification methods and time series methods are evaluated to monitor and determine the changes caused by the climate in 13 selected provinces in Turkey. The triple exponential smoothing method and the Erinc climate classification method were discussed. The data were obtained from the General Directorate of Meteorology (GDM) between 1930 and 2020, and each year's precipitation efficiency index (Im) of the Erinc climate classification method was calculated. It is divided into two classes for forecasting and testing current indices: test Im indices (1930–2014) and forecast test Im indices (2015–2020). MAD, MSE, and MAPE criteria were calculated to determine whether the Im estimates were meaningful. However, the accuracy of the estimates was ensured by considering the MAPE criteria for this study. After this stage, the analyses were performed again with test Im indices (1930–2020) and forecast Im indices (2021–2060), and Im indices predictions for the future were made. Finally, the obtained forecast indices were subjected to GIS interpolation analyses (Kriging and IDW), and future climate boundary maps were produced. Thanks to the outputs obtained from the study, how the climate classes of any region will be in the future and to what extent they will change will be provided by evaluating the climate classification and time series methods together. It will contribute to different studies in this field with its innovative analysis approach.

The Use of the Regression Tree and the Support Vector Machine in the Classification of the Iraqi Stock Exchange for the Period 2019-2020

The financial markets are one of the sectors whose data is characterized by continuous movement in most of the times and it is constantly changing, so it is difficult to predict its trends , and this leads to the need of methods , means and techniques for making decisions, and that pushes investors and analysts in the financial markets to use various and different methods in order to reach at predicting the movement of the direction of the financial markets. In order to reach the goal of making decisions in different investments, where the algorithm of the support vector machine and the CART regression tree algorithm are used to classify the stock data in order to determine the trend of the stock if it is a rising stock or a descending stock .The aim of the research is to classify the financial stock data using five variables where the data of the Iraqi Islamic Bank for investment and development was used where the results showed the accuracy of the algorithm, the support vector machine and the CART algorithm, and their performance was good. Also, the results showed that the Support Vector Machines algorithm is the best when compared with the CART algorithm, using the Classification Error and MSE criteria

Weibull Reliability Estimation of (3+1) Cascade Model

In this paper presents the R reliability mathematical formula of (3+1) Weibull Cascade model. The reliability of the model is expressed by Weibull random variables, which are stress and strength distributions. The reliability model was estimated by six dissimilar methods (ML, Mo, LS, WLS, Rg and Pr) and simulation was performed using MATLAB 2012 program to compare the results of the reliability model estimates using the MSE criterion, the results indicated that the best estimator among the six estimators was ML.