Advertisement

Improving Accuracy of an Artificial Neural Network Model to Predict Effort and Errors in Embedded Software Development Projects

  • Kazunori Iwata
  • Toyoshiro Nakashima
  • Yoshiyuki Anan
  • Naohiro Ishii
Part of the Studies in Computational Intelligence book series (SCI, volume 295)

Abstract

In this paper we propose a method for reducing the margin of error in effort and error prediction models for embedded software development projects using artificial neural networks(ANNs). In addition, we perform an evaluation experiment that uses Welch’s t-test to compare the accuracy of the proposed ANN method with that of our original ANN model. The results show that the proposed ANN model is more accurate than the original one in predicting the number of errors for new projects, since the means of the errors in the proposed ANN are statistically significantly lower.

Keywords

Hide Node Improve Accuracy Large Scale Project Predict Effort Target Project 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Aoki, S.: In testing whether the means of two populations are different (in Japanese), http://aoki2.si.gunma-u.ac.jp/lecture/BF/index.html
  2. 2.
    Boehm, B.: Software engineering. IEEE Trans. Software Eng. C-25(12), 1226–1241 (1976)Google Scholar
  3. 3.
    Hirayama, M.: Current state of embedded software (in japanese). Journal of Information Processing Society of Japan (IPSJ) 45(7), 677–681 (2004)MathSciNetGoogle Scholar
  4. 4.
    Iwata, K., Anan, Y., Nakashima, T., Ishii, N.: Using an artificial neural network for predicting embedded software development effort. In: Proceedings of 10th ACIS International Conference on Software Engineering, Artificial Intelligence, Nteworking, and Parallel/Distributed Computing – SNPD 2009, pp. 275–280 (2009)Google Scholar
  5. 5.
    Iwata, K., Nakashima, T., Anan, Y., Ishii, N.: Error estimation models integrating previous models and using artificial neural networks for embedded software development projects. In: Proceedings of 20th IEEE International Conference on Tools with Artificial Intelligence, pp. 371–378 (2008)Google Scholar
  6. 6.
    Komiyama, T.: Development of foundation for effective and efficient software process improvement (in japanese). Journal of Information Processing Society of Japan (IPSJ) 44(4), 341–347 (2003)Google Scholar
  7. 7.
    Ubayashi, N.: Modeling techniques for designing embedded software (in japanese). Journal of Information Processing Society of Japan (IPSJ) 45(7), 682–692 (2004)Google Scholar
  8. 8.
    Nakamoto, Y., Takada, H., Tamaru, K.: Current state and trend in embedded systems (in japanese). Journal of Information Processing Society of Japan (IPSJ) 38(10), 871–878 (1997)Google Scholar
  9. 9.
    Nakashima, S.: Introduction to model-checking of embedded software (in japanese). Journal of Information Processing Society of Japan (IPSJ) 45(7), 690–693 (2004)Google Scholar
  10. 10.
    Ogasawara, H., Kojima, S.: Process improvement activities that put importance on stay power (in japanese). Journal of Information Processing Society of Japan (IPSJ) 44(4), 334–340 (2003)Google Scholar
  11. 11.
    Student: The probable error of a mean. Biometrika 6(1), 1–25 (1908)Google Scholar
  12. 12.
    Takagi, Y.: A case study of the success factor in large-scale software system development project (in japanese). Journal of Information Processing Society of Japan (IPSJ) 44(4), 348–356 (2003)Google Scholar
  13. 13.
    Tamaru, K.: Trends in software development platform for embedded systems (in japanese). Journal of Information Processing Society of Japan (IPSJ) 45(7), 699–703 (2004)Google Scholar
  14. 14.
    Watanabe, H.: Product line technology for software development (in japanese). Journal of Information Processing Society of Japan (IPSJ) 45(7), 694–698 (2004)Google Scholar
  15. 15.
    Welch, B.L.: The generalization of student’s problem when several different population variances are involved. Biometrika 34(28) (1947)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Kazunori Iwata
    • 1
  • Toyoshiro Nakashima
    • 2
  • Yoshiyuki Anan
    • 3
  • Naohiro Ishii
    • 4
  1. 1.Dept. of Business AdministrationAichi UniversityMiyoshJapan
  2. 2.Dept. of Culture-Information StudiesSugiyama Jogakuen UniversityNagoyaJapan
  3. 3.Omron Software Co., Ltd.KyotoJapan
  4. 4.Dept. of Information ScienceAichi Institute of TechnologyToyotaJapan

Personalised recommendations