In the present study, an ARTIFICIAL NEURAL NETWORK ((ANN)) model is developed to predict the correlation between the friction stir extrusion (FSE) parameters and the recycled wires’ average grain sizes. FSE is a solid– state synthesis technique, in which machining chips are firstly loaded into the container, and then a rotating tool with a central hole is plunged into the chips at a selected rotational speed and feed rate to achieve indirect extrusion. Selecting rotational speed (RS), vertical speed (VS), and extrusion hole size (HS) as the input and average grain size as the output of the system, the 3– 6– 1 (ANN) is used to show the correlation between the input and output parameters. Checking the accuracy of the NEURAL NETWORK, R squared value and Root– Mean– Square– Error (RMSE) of the developed model (0. 94438 and 0. 75794, respectively) have shown that there is a good agreement between experimental and predicted results. A sensitivity analysis has been conducted on the (ANN) model to determine the impact of each input parameter on the average grain size. The results showed that the rotational speed has more effect on average grain size during the FSE process in comparison to other input parameters.

Background: Leukemia is one of the mostcommon cancers in children, comprising more than a third of all childhood cancers. Newly affected patients in USA are estimated as 10100cases, and if these cases are diagnosed late or proper treatment is not applied, then it can be mortal. Because rapid and proper diagnosis of leukemia based on clinical or medicinal findings (without biopsy) is impossible, we decided to apply ARTIFICIAL NEURAL NETWORK for rapid leukemia diagnosis. For this aim we used clinical and medical parameters taken from 131 patients of Sina hospital of Hamadan.Methods: We carried out independent sample T-test with SPSS software for 38 parameters. With regard to the results of this analysis we selected 8 parameters that had lowest sig for (ANN) analysis (among parameters, whose sig were less than 0.05).Selected parameters of 131 patients were applied for training NETWORK with Levenberg-Marquardt learning algorithm, with learning rate of 0.1.Results: Performance of learning was 0.094. The Relationship between the output of trained NETWORK for test data and real results of test data was high and the area under ROC curve was 0.967.Conclusions: With these results we can conclude that training process was done successfully and accurately.Therefore we can use ARTIFICIAL NEURAL NETWORK for rapid and reliable leukemia recognition.

The estimation of alongshore sediment transport rate (LSTR) is the most important factor in analyzing the amount of erosion or accretion along a coast. In the present research, an LSTR measurement was done at daily intervals using sediment traps in Noor coastal area, north of Iran, from March 21 to June 22, 2012. The existing empirical relations are linear or exponential regressions based on the observations and measurements data. Based on calculations, the yearly average of sediment transport rate is 928.73 (m3/day) for Noor coastal area. One of the most widely used methods for estimating LSTR, which has advantages compared with others, is setting up and application of an ARTIFICIAL NEURAL NETWORK ((ANN)s) and the present study attempts to develop such a model. Different (ANN)s with different input configurations and transfer functions were examined. The results reveal that usage of the hyperbolic tangent is better than application of the sigmoid as the transfer functioning. Moreover, the (ANN) with wave breaking height (), surf zone width (W), and alongshore current velocity (V), as inputs and sediment transport rate (Q) as output configures the best model and predicts more reliably, with higher correlation coefficient, R2, of 0.96, the L.S.T.R among others. Using the (ANN)s model presented in this research, therefore, the sediment transport rate can be estimated with sufficient accuracy.

In this research, ARTIFICIAL NEURAL NETWORKs((ANN)s) have been used to predict the viscosity of lubricant/refrigerant mixtures. Temperature, pressure, molecular weight, the mole fraction of refrigerant, and viscosity of refrigerant are used as input variables and viscosity of refrigerant + lubricant mixtures is used as a target. The total number of experimental data point of viscosity that used in this study is 1053 that is trained, validated, and tested with random70%(837 data points), 15% (158 data points), and 15% (158 data points), respectively. The results of the AAD% for the train, validation and test sets of data are 0. 39, 0. 48, and 0. 49, respectively. Therefore, studied (ANN) models with 15 neurons in a hidden layer are in good agreement with experimental data.

Maintenance reliability and efficiency in industrial hydraulic systems operation has become a point of concern for the professionals in maintenance engineering. One practical approach in this regard is the realization of symptoms of early stage malfunctioning in fluid power systems after which maintenance pl(ANN)ing and preventive means would follow upon a reasonably accurate and subsequently acceptable determination. Among the highly reliable sources providing such convenience, ARTIFICIAL NEURAL NETWORK ((ANN)) stands a high chance of success NEURAL NETWORK method has been used to detect faults occurring in most hydraulic systems. These faults could be related to supply pressure, effective bulk modulus and total leakage. The simulated system in this study consists of hydraulic servo valve, double acting cylinder and a spring that resists piston movement. Two main reasons causing this system to have a nonlinear behavior are hydraulic servo valve and compressibility effect of hydraulic fluid. The NEURAL NETWORK approach in this investigation comprises of an efficient use in nonlinear systems and requires advance knowledge about the system behavior under faulty conditions and assumptions about the type and severity of faults likely to occur. NEURAL NETWORKs trained with different training algorithms are investigated. After training the NETWORK, the system was examined for different inputs and obtained results were compared.      

In this study, a single tire tester was used to study the effects of vertical load, inflation pressure and moisture content on tire rolling resistance in a soil bin. A Goodyear 12. 4-28, 6 ply tractor drive tire was employed and the soil texture was a clay loam. The experimental design was a completely randomized with factorial layout at three replications. A multivariate regression model was obtained with the correlation coefficient of R2=0. 85 to predict the tire rolling resistance based on vertical load, inflation pressure, and moisture content. A multilayer feed-forward (ANN) (ARTIFICIAL NEURAL NETWORK) with standard BP (back propagation) algorithm and LM (Levenberg-Marquardt) training function by using of two hidden layer in the NETWORK architecture was employed. RMSE (root mean squared error) and R2 was used as modeling performance criteria. Tire inflation pressure was identified as the controller parameter of tire rolling resistance at low moisture content and also moisture content was the most effective parameter on changing of rolling resistance in regression model. Also the obtained R2=0. 977 from (ANN) model showed that (ANN) data were more close to actual data than the regression model.

A new computational method based on an ARTIFICIAL NEURAL NETWORK has been proposed to calculate solute solubility in binary mixed solvents. The accuracy of the proposed method has been compared with that of the best multiple linear regression method taken from the literature employing seven numerical analyses and the results showed that the proposed method was superior in six numerical analyses and there was no significant difference between two methods in a numerical analysis.

introduction: Soybean is recognized as a good source of essential nutrients including protein, oil and several bioactive compounds and soybean has the potential to be used as snack and roasted nut, but most significant factor responsible for such limitation is probably considered as the characteristic flavor of soybean. Raw soybean has beany, bitter and astringent flavors. Therefore to improve its consumption, the particular flavor of raw soybean must be removed. Roasting might be considered as one of the best methods for this object.Materials and Methods: In this study, the infrared roaster is designed and soybean has been prepared and roasted according to the experimental condition. In this work, an ARTIFICIAL NEURAL NETWORK model was developed for modeling of moisture content of soybean snack during infrared roasting. In order to do this, infrared lamp powers of 250, 350 and 450 W, distance between lamp and sample of 4, 7 and 10 cm and roasting time of 30 min were considered as the inputs and the amount of moisture ratio (MR) was estimated as the output. In addition, three different mathematical models were fitted to the experimental data and compared with the (ANN) model.Results: Based on these results, ARTIFICIAL NEURAL NETWORK model for MR with one hidden layer, Sigmoid function as the transfer function, Levenberg-Marquardt method as the learning rule, 4 hidden neurons, 55% for training subset and 25 and 20 percent for each of validation and test subsets respectively had the best over fitting. The determination coefficient (R2) and root mean square error (RMSE) computed for the (ANN) model were 0.9992 and 0.01099and for the best mathematical model (Two term model) were 0.9776 and 0.02758, respectively.Conclusion: It was concluded that the ARTIFICIAL NEURAL NETWORK model satisfied the work better than the mathematical model concerned with soybean snack roasting.