Recently Genetic Algorithms (GAs) have frequently been used for optimizing the solution of estimation problems. One of the main advantages of using these techniques is that they require no knowledge or gradient information about the response surface. The poor behavior of genetic algorithms in some problems, sometimes attributed to design operators, has led to the development of other types of algorithms. One such class of these algorithms is compact Genetic Algorithm (cGA), it dramatically reduces the number of bits reqyuired to store the poulation and has a faster convergence speed. In this paper compact Genetic Algorithm is used to optimize the maximum likelihood estimator of the first order moving avergae model MA(1). Simulation results based on MSE were compared with those obtained from the moments method and showed that the Canonical GA and compact GA can give good estimator of θ for the MA(1) model. Another comparison has been conducted to show that the cGA method has less number of function evaluations, minimum searched space percentage, faster convergence speed and has a higher optimal precision than that of the Canonical GA.
This study is a trail to know if the genes controlling some of heavy metals resistance ( lead, zinc, cadmium, cromium) in two types of pathogenic bacteria E. coli as gram negative bacteria and S. aureus as gram positive bacteria, present on the β-lactamase plasmid. Ten isolates of each bacterial types which produced β-lactamase enzyme, were cultivated in the presence of acridine orange. The growing in the presence of acridine orange resulted in loss of the β-lactamase genes in S. aureus and E. coli, and loss of the heavy metals resistance in S. aureus, while the resistance of E. coli against heavy metals still without any change. The results indicate that the genes for heavy
... Show MoreIn this paper a mathematical model that describes the flow of infectious disease in a population is proposed and studied. It is assumed that the disease divided the population into four classes: susceptible individuals (S), vaccinated individuals (V), infected individuals (I) and recover individuals (R). The impact of immigrants, vaccine and external sources of disease, on the dynamics of SVIRS epidemic model is studied. The existence, uniqueness and boundedness of the solution of the model are discussed. The local and global stability of the model is studied. The occurrence of local bifurcation as well as Hopf bifurcation in the model is investigated. Finally the global dynamics of the proposed model is studied numerically.
Abstract
Binary logistic regression model used in data classification and it is the strongest most flexible tool in study cases variable response binary when compared to linear regression. In this research, some classic methods were used to estimate parameters binary logistic regression model, included the maximum likelihood method, minimum chi-square method, weighted least squares, with bayes estimation , to choose the best method of estimation by default values to estimate parameters according two different models of general linear regression models ,and different s
... Show MoreThe nigra scale, Parasaissetia nigra (Nietner, 1861) (Hemiptera, Coccidae) recorded as a new insect pest attacking fig trees, Ficus carica (Moraceae) in Iraq. It was observed during April 2014 in residential garden at Al-Hurriyah district in Baghdad.
The aim of this study is to highlight this species of gastropoda Cochlicellabarbara( Linnaeus, 1758), which is recorded for the first time in Iraq, which is an exotic animal in this country. It is a terrestrial Molluscan, the study for three months (February, March and April) 2017. In garden houses in Baghdad Al-Karkh, we studied the development stages from the egg to the adult, they lay a hundred of eggs in about (15-20) eggs in each gelatinous sac, the shell with 7 whorls and about 10 mm in length.
In this work, a new development of predictive voltage-tracking control algorithm for Proton Exchange Membrane Fuel Cell (PEMFCs) model, using a neural network technique based on-line auto-tuning intelligent algorithm was proposed. The aim of proposed robust feedback nonlinear neural predictive voltage controller is to find precisely and quickly the optimal hydrogen partial pressure action to control the stack terminal voltage of the (PEMFC) model for N-step ahead prediction. The Chaotic Particle Swarm Optimization (CPSO) implemented as a stable and robust on-line auto-tune algorithm to find the optimal weights for the proposed predictive neural network controller to improve system performance in terms of fast-tracking de
... Show MoreThis study was conducted in College of Science \ Computer Science Department \ University of Baghdad to compare between automatic sorting and manual sorting, which is more efficient and accurate, as well as the use of artificial intelligence in automated sorting, which included artificial neural network, image processing, study of external characteristics, defects and impurities and physical characteristics; grading and sorting speed, and fruits weigh. the results shown value of impurities and defects. the highest value of the regression is 0.40 and the error-approximation algorithm has recorded the value 06-1 and weight fruits fruit recorded the highest value and was 138.20 g, Gradin
Semi-parametric models analysis is one of the most interesting subjects in recent studies due to give an efficient model estimation. The problem when the response variable has one of two values either 0 ( no response) or one – with response which is called the logistic regression model.
We compare two methods Bayesian and . Then the results were compared using MSe criteria.
A simulation had been used to study the empirical behavior for the Logistic model , with different sample sizes and variances. The results using represent that the Bayesian method is better than the at small samples sizes.
... Show More