A deep learning approach for cost effective learning of defective prone modules


  • Satya Srinivas Maddipati KLEF,Guntur, India
  • Mallidi Srinivas KLEF,Guntur, India






Software Defect Prediction, Imbalanced Data, Principle Component Analysis, Adaptive Neuro Fuzzy Inference System.


Software Defect Prediction is a cost effective problem, in which the cost of majority class (Non defective) is low compared with the cost of minority class ( Defective). Learning from imbalanced data bias the classifier towards majority class. In this paper we are proposing a deep learning approach for classifying Imbalanced and Cost effective data. We applied Principle Component Analysis for feature selection and then constructed a classifier using Adaptive Neuro Fuzzy Inference System. The performance of the classifier was evaluated using AuC measures. We observed the performance of the classifier was improved compared with neural networks.




[1] Mingxia Liu,Linsong Miao & Daoqiang Zhang,†Two-Stage Cost-Sensitive Learning for Software Defect Predictionâ€, IEEE Transactions on Reliability,63(2),2014. https://doi.org/10.1109/TR.2014.2316951.

[2] Bathia D, Gupta A†A framework to assess the effectiveness of fault-prediction techniques for quality assurance†In: 7th CSI International Conference on Software Engineering. Pune; 2013. p. 40-49.

[3] Satya Srinivas M, G Pradeepini, A Yesubabu,†Software Defect Prediction using Adaptive Neuro Fuzzy Inference Systemâ€,International Journal of Applied Engineering & Research, 13(1), pp:394-397.

[4] Manjula C, Lilly Florence,†Software Defect Prediction using Deep Belief Network with L1-Regularization Based Optimizationâ€, IJARCS,9(1), pp:864-870. https://doi.org/10.26483/ijarcs.v9i1.5476.

[5] Jaroslaw Hryszko,Lech Madeyski,†Cost Effectiveness of Software Defect Prediction in an industrial projectâ€,Foundations of Computing and Decision Sciencs,43(1). https://doi.org/10.1515/fcds-2018-0002.

[6] Yun ZHANG, David LO, Xin XIA, Jianling SUN,†Combined classifier for cross-project defect prediction: an extended empirical studyâ€, Frontiers Computer Science,2018, pp:1-17.

[7] Satya Srinivas Maddipati, G Pradeepini, A Yesubabu,†Software Defect Prediction using Adaptive Neuro Fuzzy Inference Systemâ€, International Journal of Applied Engineering Researchâ€, 13(1), pp:394-397.

[8] Linh Nhat Chu,â€Metric learning for Software Defect Predictionâ€,Monash University,(2015).

[9] Ming Li Hongyu zhang, Rongxin Wu, Zhi-hua Zhou,†Sample based Software Defect Prediction with active and semi supervised learningâ€, Autom Softw Eng,2011.

[10] Hao Tang, Tian Lan, Dan hao & Lu Zhang,â€Enhancing Defect Prediction with Static Defect Analysis†, Proceedings of the 7th Asia-Pacific Symposium on Internetware,PP:43-51

[11] Satya Srinivas M, G Pradeepini,†Class Imbalance Learning of Defective Prone Modules using Adaptive Neuro Fuzzy Inference Systemâ€, International Journal of Pure and Applied Mathematics,118(5), pp:739-744.

[12] Divya Tomar, Sonali Agarwal,†Prediction of Defective Software Modules Using Class Imbalance Learningâ€,Applied Computational Intelligence and Soft Computing,2016. https://doi.org/10.1155/2016/7658207.

[13] Romi Satria Wahono, N Suryana & Sabrina Ahmad,†Neural Network Parameter Optimization Based on Genetic Algorithm for Software Defect Predictionâ€,Advanced Science Letters,20,pp:10-12. https://doi.org/10.1166/asl.2014.5641.

[14] Zhou Xu,Jin Liu,Zijiang Yang, Gerge An & Xiangyang Jia,†The Impact of Feature Selection on Defect Prediction Performance: An Emipirical Comparisionâ€, 2016 IEEE 27th International Symposium on Software Reliability Engineering,2016.

[15] Satya Srinivas M, A Yesubabu, G Pradeepini,†Feature Selection Based Neural Networks for Software Defect Predictionâ€, IOSR Journal of Computer Engineering,18(6),2016.

[16] Lei Gu,†A novel subtractive clustering method by increasing and using new data samplesâ€, 2016 IEEE International Conference of Online Analysis and Computing Science,2016. https://doi.org/10.1109/ICOACS.2016.7563053.

View Full Article: