Support 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

The proposal of nonlinear models is one of the most important methods in time series analysis, which has a wide potential for predicting various phenomena, including physical, engineering and economic, by studying the characteristics of random disturbances in order to arrive at accurate predictions.

In this, the autoregressive model with exogenous variable was built using a threshold as the first method, using two proposed approaches that were used to determine the best cutting point of [the predictability forward (forecasting) and the predictability in the time series (prediction), through the threshold point indicator]. B-J seasonal models are used as a second method based on the principle of the two proposed approaches in dete

 The logistic regression model of the most important regression models a non-linear which aim getting estimators have a high of efficiency, taking character more advanced in the process of statistical analysis for being a models appropriate form of Binary Data.                                                          

Among the problems that appear as a result of the use of some statistical methods I

Leuconostoc bacteria was isolated from local pickled cabbage (Brassica oleracea capitata) and identified as Leuconostoc mesenteroides by morphology,biochemical and physiological. The local isolated L. mesenteroides bacteria under the optimal conditions of dextran production showed that, the highly production of dextran was 7.7g achieved by using a modified natural media comprised of 100ml whey, 10g refined sugar, 0.5g heated yeast extract, 0.01g CaCl2, 0.001g MgSO4, 0.001g MnCl2 and 0.001g NaCl at pH 6 and 25̊C for 24 hr of fermentation and by using 1ᵡ106 cell/ml as initial inoculums volume. Some applications in food technology (Ice cream, Loaf, Ketchup and Beef preservation) have been performed with processed dextran. The result

More than 95% of the industrial controllers in use today are PID or modified PID controllers. However, the PID is manually tuning to be responsive so that the Process Variable is rapidly and steady moved to track the set point with minimize overshoot and stable output. The paper presents generic teal-time PID controller architecture. The developed architecture is based on the adaption of each of the three controller parameters (PID) to be self- learning using individual least mean square algorithm (LMS). The adaptive PID is verified and compared with the classical PID. The rapid realization of the adaptive PID architecture allows the readily fabrication into a hardware version either ASIC or reconfigurable.

In this work chemical vapor deposition method (CVD) for the production of carbon nanotubes (CNTs) have been improved by the addition of S. Steel mesh container (SSMC) inside which the catalyst (Fe/Al2O3) was placed. Scanning electron microscopy (SEM) investigation method used to study nanotubes produced, showed that high yield of two types of (CNTs) obtained, single wall carbon nanotube (SWCNTs) with diameter and length of less than 50nm and several micrometers respectively and nanocoil tubes with a diameter and length of less than 100nm and several micrometers respectively. The chemical analysis of (CNTs) reveals that the main component is carbon (94%) and a little amount of Al (0.32%), Fe (2.22%) the reminder is oxygen. It was also fou

This paper includes the application of Queuing theory with of Particle swarm algorithm or is called (Intelligence swarm) to solve the problem of The queues and developed for General commission for taxes /branch Karkh center in the service stage of the Department of calculators composed of six  employees , and it was chosen queuing model is a single-service channel  M / M / 1 according to the nature of the circuit work mentioned above and it will be divided according to the letters system for each employee, and  it was composed of data collection times (arrival time , service time, departure time)

This research discussed, the process of comparison between the regression model of partial least squares and tree regression, where these models included two types of statistical methods represented by the first type "parameter statistics" of the partial least squares, which is adopted when the number of variables is greater than the number of observations and also when the number of observations larger than the number of variables, the second type is the "nonparametric statistic" represented by tree regression, which is the division of data in a hierarchical way. The regression models for the two models were estimated, and then the comparison between them, where the comparison between these methods was according to a Mean Square

The levels of shooting in basketball not very good appears un healthy phenomenon for age stages especially youth players on Iraq and therefore there is lower level in skills especially shooting that seems the players represent their players not good levels which cause difficult in choosing players for youth national team. The research sample were youth teams in Baghdad for season 2012-2013 their birth 1996 and the number teams (7) and after getting results and treat it statically the important ones were : there is a large number of failure attempts on success ones in basic shooting in basketball for youth teams in Baghdad teams (2012-2013) season and basic shooting have effective participation (positive relation) in youth teams ranking in B

        In this paper, an estimate has been made for parameters and the reliability function for Transmuted power function (TPF) distribution through using some estimation methods as proposed new technique for white, percentile, least square, weighted least square and modification moment methods. A simulation was used to generate random data that follow the (TPF) distribution on three experiments (E₁ , E₂ , E₃)  of the real values of the parameters, and with sample size (n=10,25,50 and 100) and iteration samples (N=1000), and taking reliability times (0< t < 0) . Comparisons have been made between the obtained results from the estimators using mean square error (MSE). The results showed the