Title: Classification of defective modules using object-oriented metrics

Authors: Satwinder Singh; Rozy Singla

Addresses: Centre for Computer Science Technology, Central University of Punjab, Bathinda, 151100, India ' CSE Department, Shankara Institute of Technology, Jaipur, 302028, India

Abstract: Software defect in today's era is crucial in the field of software engineering. Most of the organisations use various techniques to predict defects in their products before they are delivered. Defect prediction techniques help the organisations to use their resources effectively which results in lower cost and time requirements. There are various techniques that are used for predicting defects in software before it has to be delivered, e.g., clustering, neural networks, support vector machine (SVM). In this paper two defect prediction techniques: K-means clustering and multi-layer perceptron model (MLP) are compared. Both the techniques are implemented on different platforms. K-means clustering is implemented using WEKA tool and MLP is implemented using SPSS. The results are compared to find which algorithm produces better results. In this paper object-oriented metrics are used for predicting defects in the software.

Keywords: object-oriented metrics; defect prediction; K-means clustering; artificial neural networks; ANNs; WEKA; SPSS; classification; defective modules; software defects; software engineering; software development; multi-layer perceptron; MLP.

DOI: 10.1504/IJISTA.2017.081311

International Journal of Intelligent Systems Technologies and Applications, 2017 Vol.16 No.1, pp.1 - 13

Received: 28 Jul 2015
Accepted: 11 Apr 2016
Published online: 04 Jan 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article