A Density Based Clustering approach for early detection of fault prone modules

Quality of a software component can be measured in terms of fault proneness of data. Quality estimations are made using fault proneness data available from previously developed similar type of projects and the training data consisting of software measurements. To predict fault-proneness of modules different techniques have been proposed which includes statistical methods, machine learning techniques, neural network techniques and clustering techniques. The aim of proposed approach is to investigate that whether metrics available in the early lifecycle (i.e. requirement metrics), metrics available in the late lifecycle (i.e. code metrics) and metrics available in the early lifecycle (i.e. requirement metrics) combined with metrics available in the late lifecycle (i.e. code metrics) can be used to identify fault prone modules by using Density Based Clustering technique. This approach has been tested with real time defect datasets of NASA software projects named as PC1. Predicting faults early in the software life cycle can be used to achieve high software quality. The results show that the fusion of requirement and code metric is the best prediction model for detecting the faults as compared with mostly used code based model.