Empirical Analysis of Fault Predication Techniques for Improving Software Process Control

Date Added: Jul 2012
Format: PDF

In this paper, the authors present the application of the neural network for the identification of Reusable Software modules in Oriented Software System. Metrics are used for the structural analysis of the different procedures. The values of Metrics will become the input dataset for the neural network systems and Fuzzy Systems. Training Algorithm based on Neural Network and fuzzy clustering is experimented and the results are recorded in terms of Accuracy, Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The results show that Fuzzy Clustering based technique have shown better results than Resilient Backpropagation on the basis of testing data in terms of prediction technique.