Abstract
Software reliability analysis is inevitable for modern medical systems, since a large amount of medical system functionality is now dependent on software, and software does contribute to system failures. Most software reliability models are based on software failure data collected from the project. This creates a problem for the designers since, during the early stage, software failure data are not available. However, a valuable knowledge can be learned from the analysis of previous projects and applied to the new ones. This paper presents the approach that predicts the potentially dangerous software modules under development based on the analysis of the already finished modules using the machine-learning techniques. On the basis of the prediction given by our method software designers are able to devote more testing effort to the dangerous parts of the system, which results in a more reliable medical software system.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
REFERENCES
Musa, J. D., and Okumoto, K., A logarithmic Poisson execution time model for software reliability measurement. Proc. 7th Int. Conf. Softw. Eng. pp. 230–237, 1984.
Jelinski, Z., and Moranda, P., Software reliability research. In Freiberger, W. (ed.), Statistical Computer Performance Evaluation, Academic Press, New York, pp. 465–484,1972.
Lyu, M. R. (ed.), Handbook of Software Reliability Engineering, McGraw-Hill, New York, 1996.
Lyu, M. R., A phase-based approach to creating highly reliable software. Proc. 2000 Int. Conf. Comput. Syst. Appl. COMPSAC’2000, 2000.
Coleman, M., Using metrics to evaluate software system maintainability. IEEE Comput. 27(8):44–49, 1994.
Paulish, D. J., and Carleton, A. D., Case studies of software process improvement measurement. IEEE Comput. 27(9):50–57, 1994.
Pighin, M., and Zamolo, R., Predictive metric based on discriminant statistical analysis. Proc. ICSE’97, pp. 262–270, 1997.
Fenton, N. E., and Pfleeger, S. L., Software metrics (2nd edition): A Rigorous & Practical Approach, PWS Publishing Co., Boston, MA, 1998.
Fioravanti, F., and Nesi, P., Prediction model for software fault correction effort. Proc. Fifth Eur. Conf. Softw. Maint. Reeng. CMSR2001, IEEE Publ., pp. 114–120, 2001.
Grady, R. B., Practical results from measuring software quality. Commun. ACM 36(11):62–68, 1993.
Munson, J. C., and Khoshgoftaar, T. M., The detection of fault-prone programs. IEEE Trans. Softw. Eng. 18(5):423–433, 1992.
Pighin, M., and Kokol, P., RPSM: A risk-predictive structural experimental metric. Proc. FESMA’99, Technologish Institut, pp. 459–464, 1999.
Podgorelec, V., Kokol, P., Stiglic, B., and Rozman, I., Decision trees: An overview and their use in medicine. J. Med. Syst. 26(5):445–463, 2002.
Quinlan, J. R., C4.5: Programs for Machine Learning, Morgan Kaufmann, San Francisco, CA, 1993.
Goldberg, D. E., Genetic Algorithms in Search, Optimization, and Machine Learning, Addison Wesley, Reading, MA, 1989.
Podgorelec, V., and Kokol, P., Evolutionary induced decision trees for dangerous software modules prediction. Inf. Process. Letts. 82(1):31–38, 2002.
Podgorelec, V., and Kokol, P., Towards more optimal medical diagnosing with evolutionary algorithms. J. Med. Syst. 25(3):195–220, 2001.
Koza, J. R., Genetic Programming: On the Programming of Computers by Natural Selection, MIT Press, Cambridge, MA, 1992.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Podgorelec, V., Heričko, M., Jurič, M.B. et al. Improving the Reliability of Medical Software by Predicting the Dangerous Software Modules. J Med Syst 29, 3–11 (2005). https://doi.org/10.1007/s10916-005-1100-4
Issue Date:
DOI: https://doi.org/10.1007/s10916-005-1100-4