Application of Soft Computing Techniques to Prediction of Faulty Classes in Object Oriented Software Jain Divya1, Sharma Vibhor2 1Assistant Professor (CSE/IT), HMR Institute of Technology and Management, Delhi 2Assistant Professor, Lovely Professional University, Phagwara, Punjab Online published on 29 June, 2013. Abstract Estimating number of defects or predicting fault-proneness in object oriented software modules plays a key role in quality control of software products. Over the last few years, software quality has become one of the most important requirements in the development of systems. Fault-proneness of a software module is the probability that the module contains faults. The objective of this paper is to analyze experimentally the object oriented metrics as predictors of fault-prone classes and, therefore, determine whether they can be used as early quality indicators. This early detection of fault-prone software components enables verification experts to concentrate their time and resources on the problem areas of the software system under development. In this paper we describe how we calculated the object oriented metrics given by Chidamber and Kemerer to illustrate how fault-proneness detection can be carried out. Empirical validation of software metrics to predict quality using machine learning methods is important to ensure their practical relevance in the software organizations. The aim of this research work is to establish a method for identifying software defects using machine learning methods. In this work we used NASA's Metrics Data Program (MDP) as software metrics data. The repository at NASA IV & V Facility MDP contains software metric data and error data at the function/method level. In this paper we introduce Generalized Regression Neural Networks, fuzzy subtractive clustering and Adaptive-Neuro Fuzzy Inference System (ANFIS) for predicting number of defects using Object Oriented metrics. Top Keywords Object Oriented Software metrics, Neural Networks, fuzzy logic, fuzzy inference, Subtractive Clustering, Software quality, Fault count, Adaptive Neuro-Fuzzy Inference System. Top |