Volume 12 Number 10 (Oct. 2017)
Home > Archive > 2017 > Volume 12 Number 10 (Oct. 2017) >
JSW 2017 Vol.12(10): 759-772 ISSN: 1796-217X
doi: 10.17706/jsw.12.10.759-772

Modeling Software Defects as Anomalies: A Case Study on Promise Repository

Kamrun Nahar Neela, Syed Ali Asif, Amit Seal Ami, Alim Ul Gia
Institute of Information Technology, University of Dhaka, Dhaka – 1000, Bangladesh.

Abstract—Software defect prediction is a highly studied domain in Software Engineering research due to its importance in software development. In literature, various classification methods with static code attributes have been used to predict defects. However, defected instances are very few compared to non-defected instances and as such lead to imbalanced data. Traditional machine learning techniques give poor results for such data. In this paper an anomaly detection technique for software defect prediction, is proposed which is not affected by imbalanced data. The technique incorporates both univariate and multivariate Gaussian distribution to model non-defected software module. The defected software modules are then predicted based on their deviation from the generated model. To evaluate our approach, we implemented the algorithm and tested it on the NASA datasets from the PROMISE repository. By utilizing this approach, we observed an average balance of 63.36% and 69.06% in univariate model and multivariate model respectively. Without utilizing optimization or filter, this approach yield better result than industry standard of 60%.

Index Terms—Software defect prediction, anomaly detection, univariate gaussian distribution, multivariate gaussian distribution, promise repository.

[PDF]

Cite: Kamrun Nahar Neela*, Syed Ali Asif, Amit Seal Ami, Alim Ul Gia, "Modeling Software Defects as Anomalies: A Case Study on Promise Repository," Journal of Software vol. 12, no. 10, pp. 759-772, 2017.

General Information

ISSN: 1796-217X
Frequency: Monthly
Editor-in-Chief: Prof. Antanas Verikas
Executive Editor: Ms. Yoyo Y. Zhou
Abstracting/ Indexing: DBLP, EBSCO, DOAJ, ProQuest, INSPEC, ULRICH's Periodicals Directory, WorldCat, CNKI,etc
E-mail: jsw@iap.org
  • Aug 02, 2017 News!

    Papers published in JSW Vol. 12, No. 1- Vol. 12, No. 8 have been indexed by DBLP.    [Click]

  • Jan 05, 2017 News!

    [CFP] 2017 the annual meeting of JSW Editorial Board, ICSTE 2017, will be held in Hong Kong, October 27-29, 2017.   [Click]

  • Sep 27, 2017 News!

    Vol.12, No.5 has been indexed by EI (Inspec).   [Click]

  • Oct 30, 2017 News!

    Vol 12, No. 11 has been published with online version 8 original aritcles from 4 countries are published in this issue.      [Click]

  • Oct 30, 2017 News!

    The papers published in Vol.12, No. 11 have all received dois from Crossref.