International Journal of Applied Information Systems |
Foundation of Computer Science (FCS), NY, USA |
Volume 11 - Number 2 |
Year of Publication: 2016 |
Authors: Pankaj Kumar, S. K. Singh |
10.5120/ijais2016451579 |
Pankaj Kumar, S. K. Singh . Defect Prediction Model for AOP-based Software Development using Hybrid Fuzzy C-Means with Genetic Algorithm and K-Nearest Neighbors Classifier. International Journal of Applied Information Systems. 11, 2 ( Jul 2016), 26-30. DOI=10.5120/ijais2016451579
The number of defects has often been considered a vital indicator of quality of software. It is well known that we cannot go back and add quality. Software Quality and reliability are considered to be one of the most important concerns of software product. In this paper, we give a brief overview of an Aspect-Oriented Programming (AOP) and a model is proposed to predict defects. The model is empirically validated on the PROMISE Software Engineering Repository dataset with three different types of methods. One is Fuzzy C-Means Clustering (FCM) approach and another is K-Nearest Neighbors (KNN) classifier technique, have been performed in real data. Third is a hybrid approach (i.e. combination of fuzzy c-means and genetic algorithms) have been performed. The performance of data is evaluated in terms of Reliability, Accuracy, Mean Absolute Error (MAE), and Root Mean Square Error (RMSE).