<span>Dust is a common cause of health risks and also a cause of climate change, one of the most threatening problems to humans. In the recent decade, climate change in Iraq, typified by increased droughts and deserts, has generated numerous environmental issues. This study forecasts dust in five central Iraqi districts using machine learning and five regression algorithm supervised learning system framework. It was assessed using an Iraqi meteorological organization and seismology (IMOS) dataset. Simulation results show that the gradient boosting regressor (GBR) has a mean square error of 8.345 and a total accuracy ratio of 91.65%. Moreover, the results show that the decision tree (DT), where the mean square error is 8.965, comes in second place with a gross ratio of 91%. Furthermore, Bayesian ridge (BR), linear regressor (LR), and stochastic gradient descent (SGD), with mean square error and with accuracy ratios of 84.365%, 84.363%, and 79%. As a result, the performance precision of these regression models yields. The interaction framework was designed to be a straightforward tool for working with this paradigm. This model is a valuable tool for establishing strategies to counter the swiftness of climate change in the area under study.</span>
This paper aims to introduce a concept of an equilibrium point of a dynamical system which will call it almost global asymptotically stable. We also propose and analyze a prey-predator model with a suggested function growth in prey species. Firstly the existence and local stability of all its equilibria are studied. After that the model is extended to an optimal control problem to obtain an optimal harvesting strategy. The discrete time version of Pontryagin's maximum principle is applied to solve the optimality problem. The characterization of the optimal harvesting variable and the adjoint variables are derived. Finally these theoretical results are demonstrated with numerical simulations.
Artificial Neural networks (ANN) are powerful and effective tools in time-series applications. The first aim of this paper is to diagnose better and more efficient ANN models (Back Propagation, Radial Basis Function Neural networks (RBF), and Recurrent neural networks) in solving the linear and nonlinear time-series behavior. The second aim is dealing with finding accurate estimators as the convergence sometimes is stack in the local minima. It is one of the problems that can bias the test of the robustness of the ANN in time series forecasting. To determine the best or the optimal ANN models, forecast Skill (SS) employed to measure the efficiency of the performance of ANN models. The mean square error and
... Show MoreAbstract
The method binery logistic regression and linear discrimint function of the most important statistical methods used in the classification and prediction when the data of the kind of binery (0,1) you can not use the normal regression therefore resort to binary logistic regression and linear discriminant function in the case of two group in the case of a Multicollinearity problem between the data (the data containing high correlation) It became not possible to use binary logistic regression and linear discriminant function, to solve this problem, we resort to Partial least square regression.
In this, search th
... Show MoreThis article aims to explore the importance of estimating the a semiparametric regression function ,where we suggest a new estimator beside the other combined estimators and then we make a comparison among them by using simulation technique . Through the simulation results we find that the suggest estimator is the best with the first and second models ,wherealse for the third model we find Burman and Chaudhuri (B&C) is best.
The purpose of this article is to improve and minimize noise from the signal by studying wavelet transforms and showing how to use the most effective ones for processing and analysis. As both the Discrete Wavelet Transformation method was used, we will outline some transformation techniques along with the methodology for applying them to remove noise from the signal. Proceeds based on the threshold value and the threshold functions Lifting Transformation, Wavelet Transformation, and Packet Discrete Wavelet Transformation. Using AMSE, A comparison was made between them , and the best was selected. When the aforementioned techniques were applied to actual data that was represented by each of the prices, it became evident that the lift
... Show MoreSolar energy usage in Iraq is facing many issues; one of those is the accumulation “of the dust on the surface of the solar module which” would highly lower its efficiency. The present work study the effect of dust accumulation” on installing fixed solar modules with different inclined angles 15o, 33o, 45o, 60o. Evaluation of the solar modules performance under different circumstance conditions such as rain, wind and humidity are considered in study of dust effect on solar module performance. The results show that the lowest output average efficiencies of solar modules occurs at 15o horizontally inclined angle are 7.4% , 6.7% , 8.0% , 8.1%, and 8.4% for the cor
... Show MoreThe influence of solar activity on the predicted ionospheric temperature parameters (electron Te, Ion Ti and neutral particle Tn) have been investigated over ionospheric Iraqi region by data generated using International Reference Ionosphere (IRI) and Madrigal models, the models result have been compared during the minimum and the maximum of solar cycle 24 for the years 2009 and 2016 respectively and for an altitudes ranged from 200-1000 km. The region under consideration spans over (latitude 29.1-37.2oN; longitude 38.9-47.7oE) within Iraq territory, the purpose of this paper is to determine the affection of the solar activity represented by the (sunspot number and solar flux) on the annual behavio
... Show MoreAbstract
Multivariate GARCH Models take several forms , the most important DCC dynamic conditional correlation, and CCC constant conditional correlation , The Purpose of this research is the Comparison for both Models.Using three financial time series which is a series of daily Iraqi dinar exchange rate indollar, Global daily Oil price in dollar and Global daily gold price in dollarfor the period from 01/01/2014 till 01/01/2016, Where it has been transferred to the three time series returns to get the Stationarity, some tests were conducted including Ljung-Box , JarqueBera , Multivariate ARCH to Returns Series and Residuals Series for both models In Comparison
... Show More