IJE TRANSACTIONS B: Applications Vol. 19, No. 1 (December 2006) 35-44   

downloaded Downloaded: 61   viewed Viewed: 1545

Nidhi Gupta and Manu Pratap Singh*

Department of Computer Science, Institute of Basic Science
Khandari, Dr. B. R. A. University, AGRA, India

*Corresponding Author

( Received: July 29, 2004 – Accepted: November 02, 2006 )

Abstract    Various problems of combinatorial optimization and permutation can be solved with neural network optimization. The problem of estimating the software reliability can be solved with the optimization of failed components to its minimum value. Various solutions of the problem of estimating the software reliability have been given. These solutions are exact and heuristic, but all the exact approaches are of considerable theoretical interest. In this paper, we propose the simulated annealing technique of mean field approximation for finding the possible minimum number of failed components in the sequential testing. These minimum numbers of failed components are depending upon the selection of time intervals or slots. The selection of time intervals or slots satisfies all the necessary constraints of the problem. The new energy function with the mean field approximation is also proposed. The constraint parameter for the annealing schedule is also dynamically defined that is changed with the selection of a time interval or slot on each iteration of the processing. The algorithm of the whole process shows that this approach can generate the optimal solution.


Keywords    Software Reliability, Mean field Approximation, Simulated Annealing, Optimization



1. Hassoun, M. H., “Fundamentals of Artificial Neural Networks”, MIT Press, Cambridge, MA, (1995).

2. Wasserman, P. D., “Advanced Method in Neural Computing”, Van Nostrand Reinhold, New York, NY, (1993).

3. Fogel, D. B., “An Introduction to Simulated Evolutionary Optimization”, IEEE Trans. Neural Network, 5, (1994), 3-14.

4. Fogel, D. B., “System Identification through Simulated Evolution: A Machine Learning Approach to Modeling”, Ginn press, Nedham, MA, (1991).

5. Musa, J. D., Iannino, A. and Okumoto, K., “Software Reliability: Measurement, Prediction, Application, Professional Edition”, Software Engineering Series, McGraw - Hill, New York, NY, (1990).

6. Karunanithi, K., Whitley, D. and Malaiya, Y., “Using Neural Networks in Reliability Prediction”, IEEE Software, 9-4, (1992), 53-59.

7. Traintafyllos, G., Vassiliadis, S. and Kobrosly, W., “On the Prediction of Computer Implementation Faults Via static Error Prediction Models”, Journal of Systems and Software, 28-2, (1995), 129-142.

8. Sharma, N. K., Mangal, M. and Singh, M. P., “Solution of Traveling Salesman Problem with Simulated Annealing of Mean Field Approximation Neural Network”, Proceeding of the Second International Conference on Mathematical and Computational Models, Coimbatore Allied Publishers, (2003), 297-304.

9. Srinath, L. S., “Reliability Engineering”, Affiliated East West Press Pvt. Ltd., (1991).

10. Waterman, R. E. and Hayatt L. E., “Testing-When do I Stop?”, (Invited), International Testing and Evaluation Conference, Washington, DC, USA, (1994).

International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir