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 the absolute mean square error were also used to measure the accuracy of the estimation for methods used. The important result obtained in this paper is that the optimal neural network was the Backpropagation (BP) and Recurrent neural networks (RNN) to solve time series, whether linear, semilinear, or non-linear. Besides, the result proved that the inefficiency and inaccuracy (failure) of RBF in solving nonlinear time series. However, RBF shows good efficiency in the case of linear or semi-linear time series only. It overcomes the problem of local minimum. The results showed improvements in the modern methods for time series forecasting.
This research represents a practical attempt applied to calibrate and verify a hydraulic model for the Blue Nile River. The calibration procedures are performed using the observed data for a previous period and comparing them with the calibration results while verification requirements are achieved with the application of the observed data for another future period and comparing them with the verification results. The study objective covered a relationship of the river terrain with the distance between the assumed points of the dam failures along the river length. The computed model values and the observed data should conform to the theoretical analysis and the overall verification performance of the model by comparing it with anothe
... Show MoreThis paper is interested in certain subclasses of univalent and bi-univalent functions concerning to shell- like curves connected with k-Fibonacci numbers involving modified Sigmoid activation function θ(t)=2/(1+e^(-t) ) ,t ≥0 in unit disk |z|<1 . For estimating of the initial coefficients |c_2 | , |c_3 |, Fekete-Szego ̈ inequality and the second Hankel determinant have been investigated for the functions in our classes.
This prospective study investigates the prevalence of methicillin-resistant S.aureus (MRSA)
in burn unit of Al-Kindy Iraqi hospital, their susceptibility to antibiotics and bactericidal effect of near
infrared light from high powered 1064nm Nd: YAG laser and green light 532nm from SHG Nd: YAG laser
using various energy densities on these bacteria. Twenty four clinical isolates of S.aureus out of sixty
four examined patients with sever burn ulcers.MRSA was associated with 50% of S.aureus infections
.Results of antimicrobial susceptibility revealed that MRSA were multidrug resistant. After laser treatment
of non MRSA with Nd:YAG with wavelength of 1.064nm, 4mm beam diameter, energy density of
0.636 kh/cm2 and 180sec ex
A series of coumarin derivatives linked to amino acid ester side chains were synthesized and evaluated of their antibacterial and antifungal activity. The coumarin derivatives was alkylated by the ethyl bromoacetate and then using potassium carbonate to get alkylated hymecromone. Conventional solution method for amide bond formation was used as a coupling method between the carboxy-protected amino acids with acetic acid side chain of coumarin derivatives. The DCC/ HOBt coupling reagents were used for peptide bond formation. The proposed analogues were successfully synthesized and their structural formulas were consistent with the proposed struct
... Show MoreAcinetobacter baumannii (A. baumannii) is a major opportunistic nosocomial pathogen, mostly resistant to several groups of antibiotics. Colistin is now used as a last-line treatment for isolates that are highly resistant. The purpose of this study is to identify the importance of LptD; which is involved in the translocation of LPS from the inner membrane to the outer membrane in compartment with LptA and LptC of A. baumannii and its indispensable role as a virulence factor, and the efficiency of colistin as a monotherapy. In the current research, two isolates of A.baumannii were used, the local isolate HHR1 isolated from urine sample and the global strain ATCC 17904, and three antibiot
... Show MoreThis study showed that the lens in baloot muluki fish Chondrostoma regium is transparent, spherical shape, and solid in textures, while in the tree frog Hyla arborea savignyi, freshwater turtles Clemmys caspia caspia, white–eared bulbul Pycnonotus leucotis and brown rat Rattus norvegicus are transparent, soft and biconvex, it is very soft in white–eared bulbul. There are many significant differences have been recorded between the average weight lens and the total concentration of the protein in the lens all studied animals. Electrical migration process for lens proteins showed that there is one bundle of crystalline –? and one bundle also crystalline–? in all studied species, either crystalline–? may represent one bundle character
... Show MoreThis research aims to study the important of the effect of analysis of covariance manner for one of important of design for multifactor experiments, which called split-blocks experiments design (SBED) to deal the problem of extended measurements for a covariate variable or independent variable (X) with data of response variable or dependent variable Y in agricultural experiments that contribute to mislead the result when analyze data of Y only. Although analysis of covariance with discussed in experiments with common deign, but it is not found information that it is discussed with split-Blocks experiments design (SBED) to get rid of the impact a covariance variable. As part application actual field experiment conducted, begun at
... Show MoreSupport vector machines (SVMs) are supervised learning models that analyze data for classification or regression. For classification, SVM is widely used by selecting an optimal hyperplane that separates two classes. SVM has very good accuracy and extremally robust comparing with some other classification methods such as logistics linear regression, random forest, k-nearest neighbor and naïve model. However, working with large datasets can cause many problems such as time-consuming and inefficient results. In this paper, the SVM has been modified by using a stochastic Gradient descent process. The modified method, stochastic gradient descent SVM (SGD-SVM), checked by using two simulation datasets. Since the classification of different ca
... Show MoreSummary The aim of this study is the evaluation the resistance of S. marcescence obtained from soil and water to metals chlorides (Zn+2, Hg+2, Fe+2, Al+3, and Pb+2). Four isolates, identified as Serratia marcescence and S. marcescena (S4) were selected for this study according to their resistance to five heavy metals. The ability of S. marcescena (S4) to grow in different concentrations of metals chloride (200-1200 µg/ml) was tested, the highest concentration that S. marcescence (S4) tolerate was 1000 µg/ml for Zn+2, Hg+2, Fe+2, AL+3, pb+2 and 300 µg/ml for Hg+2 through 24 hrs incubation at 37 Co. The effects of temperature and pH on bacteria growth during 72 hrs were also studied. S. marcescence (S4) was affected by ZnCl2, PbCl2, FeC12
... Show More