Artificial neural network (ANN) has advantage in time series forecasting as it has potential to solve complex forecasting problems. This is because ANN is data driven approach which able to be trained to map past values of a time series. In this study the forecast performance between neural network and classical time series forecasting method namely seasonal autoregressive integrated moving average models was being compared by utilizing gold price data. Moreover, the effect of different data preprocessing on the forecast performance of neural network being examined. The forecast accuracy was evaluated using mean absolute deviation, root mean square error and mean absolute percentage error. It was found that ANN produced the most accurate forecast when Box-Cox transformation was used as data preprocessing. High degree of accuracy can be yield on a wide range of forecasting applications since ANN is a flexible computing frameworks and universal approximates [6]. Although ANN able to produce reliable forecast, but mathematical proofs underlying the ANN will need to be considered in order to determine the best conditions to be

The unsteady hydromagnetic flow adjacent to a stretching vertical sheet is studied. The unsteadiness in the flow and temperature fields is caused by the time dependence of the stretching velocity and the surface heat flux. The governing partial differential equations are reduced to nonlinear ordinary differential equations, before being solved numerically. Comparison with previously published results as well as the exact solution for the steady-state case of the present problem is made, and the results are found to be in good agreement. Effects of the unsteadiness parameter, magnetic parameter, and Prandtl number on the flow and heat transfer are fully examined.

No abstract

This paper investigated the problem of hydromagnetic boundary layer flow and heat transfer of a dusty fluid over a stretching sheet through a porous medium. The velocity slip was considered instead of the no-slip condition at the boundary. The governing partial equations were reduced into a set of non-linear ordinary differential equations by using the suitable similarity transformation. The transformed equations were numerically integrated using bvp4c in Matlab. The effects of various physical parameters on the velocity and temperature profiles of both phases, such as fluid-particle interaction parameter, magnetic parameter, mass concentration parameter, porosity parameter and Prandtl number were obtained and analyzed through several plots. Useful discussions were carried out with the help of plotted graphs and tables. Under the limiting cases, the obtained numerical results were compared and found to be in good agreement with previously published results.