• L.R.AravindBabu

Linear Programming Problems are mathematical models which are used to find out the conditions in the way of objective functions and constraint. Nowadays, we have various methods and techniques to find out these problems occurring in the Linear Programming Problem. When developing a Linear Programming model, system and researchers often include all possible constraints although some of them may not be binding at the optimal solution. To achieve optimality in computational effort and also in accuracy, we proposed a hybrid algorithmic structure with training model for optimization of parameters in real time linear programming problem. This algorithm proposes the class based on the environment. It constructs input information using the input parameters and constraints using formal or conventional methods like complex algorithm and/or identifying redundant constraints before the predicted time. It forecasts the appropriate parameters. In case the predicted time or value belongs to any of the conditions, the value of parameters may vary. Forecast the appropriate parameters with the physical sensitivities. This structure improves the accuracy of bounded variables in linear programming problem model by suggesting the training and learning of parameters and constraints. This training is possible in real world application by applying artificial neural network.

Linear Programming, Neural Network, Redundant Constraints, Back Propagation, Training Parameters

" ANN based training methodology for solving Linear Programming Problem", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.2, Issue 7, page no.3241-3245, July-2015, Available :http://www.jetir.org/papers/JETIR1507045.pdf

" ANN based training methodology for solving Linear Programming Problem", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.2, Issue 7, page no. pp3241-3245, July-2015, Available at : http://www.jetir.org/papers/JETIR1507045.pdf