Neuro-Fuzzy Based Software Risk Estimation Tool
To develop the secure software is one of the major concerns in the software industry. To make the easier task of finding and fixing the security flaws, software developers should integrate the security at all stages of Software Development Life Cycle (SDLC).In this paper, based on Neuro- Fuzzy approach software Risk Prediction tool is created. Firstly Fuzzy Inference system is created and then Neural Network based three different training algorithms: BR (Bayesian Regulation), BP (Back propagation) and LM (Levenberg-Marquardt) are used to train the neural network. From the results it is conclude that for the Software Risk Estimation, BR (Bayesian Regulation) performs better and also achieves the greater accuracy than other algorithms.
