International Journal of Engineering Research in Computer Science and Engineering (IJERCSE)

An Ensemble Classification Model For Software Defect Prediction

Author : Baldeep Kaur ¹ Dr. Sumeet Kaur Sehra ² Dr. Daljeet Singh ³

Date of Publication :31st July 2021

Abstract: Software developed for a specific requirement is called software product. Engineering at the same time, is related to the product development by means of explicit technical fundamentals and techniques. The software defect prediction have various phases which are include data set input, pre-processing, feature extraction and classification. The various classification schemes are applied for the software defect prediction in this research work. The classification schemes like Gaussian Naive Bayes, Bernoulli Naive Bayes, Random Forest and Decision Tree are used for the software defect prediction. To improve performance for the software defect the ensemble classification method is designed in this research work. The proposed ensemble classification method is the combination of PCA algorithm with class balancing. The proposed model is implemented in python and results are analyzed in terms of Accuracy, Precision and Recall.

Reference :

1. L. Zhang and Z. Shang, “CLASSIFYING FEATURE DESCRIPTION FOR SOFTWARE DEFECT,” pp. 10–13, 2011.
2. J. Wang, B. Shen, and Y. Chen, “Compressed C4 . 5 Models for Software Defect Prediction,” vol. 2, no. 1, pp. 4–7, 2012, doi: 10.1109/QSIC.2012.19
3. Y. Chen and B. Ge, “Research on Software Defect Prediction Based on Data Mining,” vol. 1, pp. 563–567, 2010.
4. Y. Guo and M. Shepperd, “Posterâ€¯: Bridging Effort-Aware Prediction and Strong Classification - a Just-in-Time Software Defect Prediction Study,” no. 1, pp. 325–326, 2018.
5. C. Shan, H. Zhu, C. Hu, J. Cui, and J. Xue, “Software Defect Prediction Model Based on Improved LLE-SVM,” no. Iccsnt, pp. 530–535, 2015.
6. T. Nadu, “Software Defect Prediction Using Software Metrics - A survey,” pp. 2–5.
7. K. E. Bennin, J. Keung, P. Phannachitta, and A. Monden, “MAHAKILâ€¯: Diversity based Oversampling Approach to Alleviate,” vol. 5, no. 1903, p. 3182520, 2018.
8. F. Wu et al., “Cross-project and Within-project Semi-supervised Software Defect Prediction Problems Study Using a Unified Solution,” pp. 39–41, 2017, doi: 10.1109/ICSE-C.2017.72.
9. G. MauË‡ and T. G. Grbac, “Software Defect Prediction with Bug-Code Analyzer - a Data Collection Tool Demo.”
10. H. A. Ai-jamimi, “Toward Comprehensible Software Defect Prediction Models Using Fuzzy Logic,” pp. 127–130, 2016.
11. H. Iru and U. S. Hihfw, “Manifold Learning for Cross-project Software Defect Prediction,” 2018 5th IEEE Int. Conf. Cloud Comput. Intell. Syst., pp. 567–571, 2018.
12. S. I. Ayon, “Neural Network based Software Defect Prediction using Genetic Algorithm and Particle Swarm Optimization,” 2019 1st Int. Conf. Adv. Sci. Eng. Robot. Technol., vol. 2019, no. Icasert, pp. 1–4, 2019.
13. Y. Xia, “Analyzing The Significance of Process Metrics for TT & C Software Defect Prediction.”