Quality Measurement Challenges for Artificial Intelligence Software

International Journal of Computer & Organization Trends  (IJCOT)          
© 2017 by IJCOT Journal
Volume - 8 Issue - 1
Year of Publication : 2018
AuthorsZafar Ali


Zafar Ali "Quality Measurement Challenges for Artificial Intelligence Software", International Journal of Computer & organization Trends (IJCOT), V8(1):1-7 January - February  2018, ISSN:2249-2593, www.ijcotjournal.org. Published by Seventh Sense Research Group.

Abstract In this paper, various metrics of software measurements are explained with examples. The standards developed for software measurement is described. The goals of these standards are also explained. The challenges of quality measurement for AI software are discussed here. AI software is different from the common software in two ways: it generally solves different kind of problems and it solves the problems in a very different way. AI software generally comes with a vague or a quickly changing requirement list. Quality measurement becomes meaningless as how far the objective has been achieved cannot be decided when the objective itself is not clear. Rapid prototyping and freezing of requirements is a short term measure for this issue. The other option is to identify the modules that can be implemented by conventional software and to integrate the measurement plan of all these modules with suitable modifications. Another issue is; AI software is often implemented in a heuristic manner that gives a poor readability and measurement problems. Further a conflict between the prejudiced human being as a tester and tolerant expert system may take place. Ultimate goal of development of expert system is to provide solutions to problems impossible for normal human beings. Future research trends, both long and short term, are briefed here.


[1] J. Rushby, “Quality measures and assurance for AI software, Technical Report CSL-88-7R, Computer Science Laboratory, SRI International, Menlo Park, CA 94025, also available as NASA contractor report 4187, pp. 1 – 134, September 1988. Available: http://www.csl.sri.com/papers/csl-88-7/csl-88-7r.pdf Viewed: 9th July 2015.
[2] W. J. Rapaport, “Some definitions of artificial intellgence”. State University of New York at Buffalo, Buffalo, NY 14260-2000, September 2012. Available: http://www.cse.buffalo.edu/~rapaport/572/S02/aidefs.html Viewed: 6th July, 2015.
[3] N. Fenton, P. Krause, and M. Neil, “Software measurement: uncertainty and causal modelling”, IEEE Software, vol. 19, no. 4, pp. 116 - 122, July 2002.
[4] M. Khraiwesh, “Process and product quality assurance measures in CMMI”, International Journal of Computer Science and Engineering Survey, IJCES, vol. 5, no. 3, pp. 1 - 15, June 2014.
[5] J. Mylopoulos, L. Chung, and B. Nixon. “Representing and using nonfunctional requirements: A process oriented approach”, IEEE Trans. Software Engineering, vol. 18, no. 6, pp. 483 – 497, June 1992.
[6] L. Prechelt, “A quantitative study of experimental evaluations of neural network learning algorithms: current research practice”, Neural Networks, vol. 9. pp. 1 – 7, 1995.
[7] D. F. Specht, “A general regression neural network”, IEEE Trans. Neural Networks, vol. 2, no. 2, pp. 568 – 576, November 1991.
[8] I. F. B. Tronto, J. D. S. Silva, N. S. Anna, “Comparison of artificial neural network and regression models in software effort estimation”, Proc. International Joint Conference on Neural Networks, Orlando, Florida, USA, August 2007, pp. 1 – 6.
[9] R. S. Behara, W. W. Fisher, and J. G. A. M. Lemmink, “Modelling and evaluating service quality measurement using neural networks”, International Journals of Operations and Production Management, IJOPM, vol. 22, no. 2, pp. 1162 – 1185, 2002.
[10] M. R. Genesereth and S. P. Ketchpel, “Software agents”, Center for Integrated Facilty Engineering, CIFE, Stanford University, CA 94305-4020, no.32, pp. 1 – 12, April 1994.
[11] F. Zambonelli and A. Omicini, “Challenges and research directions in agent-oriented software engineering”, Autonomous Agents and Multi-Agent Systems, Kluwer Academic Publishers, vol. 9, pp. 253 – 283, 2004.
[12] M. Harman and B. F. Jones, “Search based software engineering”, Information and Software Technology, vol. 43, Elsevier, pp. 833 - 839, 2001.

artificial-intelligence, software, quality, measurement.