Study on Effective Classifier for Software Engineering Data Sets

Abstract:

A wide range of important software engineering problems need solutions that involve accurately predicting outcomes, such as the number of defects in a module, the estimated cost, or deciding the best software development process to use. Mathematically a classifier is a function that maps an N-dimensional attribute space to a discrete set of labels of the class variable. We proposed an effective classifier for software engineering data sets, the results show that the accurate predictions can have an enormous positive impact on reducing these problems and ensure projects’ successes.

• Periodical: Advanced Materials Research (Volumes 671-674)
• Pages: 3208-3211
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.671-674.3208
• Online since: March 2013
• Authors: Yong Hong Gao
• Keywords: Classifier, Data Sets, Proposed Approach

References

[1] E. J. M. Lauría and P. J. Duchessi: Decision Support Systems, Vol. 42 (2006), p.1573.

[2] D. Aha, D. Kibler: Instance-based learning algorithms. Machine Learning, Vol. 6 (1991), p.37.

[3] R. C. Quinlan: Programs for Machine Learning. Morgan Kaufman, (1992).

[4] R. Holte: Machine Learning, Vol. 11 (1993), p.63.

[5] N. Friedman, D. Geiger, M. Goldszmidt: Machine Learning, Vol. 29 (1997), p.131.

[6] B. Challagulla: Empirical Assessment of Machine Learning based Software Defect Prediction Techniques. WORDS'05, p.263, (2005).

[7] T. Menzies: IEEE Transactions on Software Engineering, Vol. 32 (2007), p.2.

[8] N. E. Fenton, M. A. Neil: IEEE transaction on Software Engineering, Vol. 25 (1999), p.675.

[9] T. R. Zimmermann: Predicting Defects for Eclipse, Predictor Models in Software Engineering, PROMISE'07: ICSE Workshops. (2007).

DOI: 10.1109/promise.2007.10

[10] P. C. Pendharkar: IEEE Transactions on Software Engineering, Vol. 31 (2005), p.615.