Using Artificial Neural-Networks in Stochastic Differential Equations Based Software Reliability Growth Modeling

600

Goodness-of-fit for DS-1

0

50

100

150

200

250

13579111315 17192123 25272931333537

Time (in weeks)

Actual DataGoel-Okumoto [1]Propose d Model (E quation 13)

Cumulative Faults

Figure 2. Goodness of fit curve for DS-1.

Goodness-of-fit for DS-2

0

5

10

15

20

25

30

12345678910 111213 1415 16 1718 192021

Time (in weeks)

Actual DataGoel-Okumoto Model [1]Proposed Model ( E quation 13)

Cumulative Faults

Figure 3. Goodness of fit curve for DS-2.

5. Conclusions

This paper presents an SRGM based on ˆ

to type Sto-

chastic Differential Equations using ANN approach. The

goodness of the fit analysis has been done on two real

software failure datasets. The goodness-of-fit of the pro-

posed Model is compared with Goel Okumoto model [1].

The results obtain ed show better fit and wider applicab il-

ity of the model to different types of failure datasets. From

the numerical illustrations, we see that the Proposed

Model provides improved results because of lower MSE,

Variation, RMSPE and Bias. The usability of SDE is not

only restricted to the model described in this paper but it

can also be extended to improve the results of any other

SRGM. For further research the Proposed Model can be

used along with error generation.

REFERENCES

[1] A. L. Goel and K. Okumoto, “Time Dependent Error De-

tection Rate Model for Software Reliability and Other

Performance Measure,” IEEE Transactions on Reliability,

Vol. 3, 1992, pp. 206-211. doi:10.1109/TR.1979.5220566

[2] P. K. Kapur, R. B. Garg and S. Kumar, “Contributions to

Hardware and Software Reliability,” World Scientific,

Singapore, 1999.

[3] B. Oksendal, “Stochastic Differential Equations—An

Introduction with Applications,” Springer, Berlin, 2003.

[4] S. Yamada and Y. Tamura, “A Flexible Stochastic Dif-

ferential Equation Model in Distributed Development En-

vironment,” European Journal of Operational Research,

Vol. 168, No. 1, 2006, pp. 143-152.

doi:10.1016/j.ejor.2004.04.034

[5] C. H. Lee, Y. T. Kim and D. H. Park, “S-Shaped Software

Reliability Growth Models Derived from Stochastic Dif-

ferential Equations,” IIE Transactions, Vol. 36, No. 12,

2004, pp. 1193-1199. doi:10.1080/07408170490507792

[6] N. Karunanithi and Y. K. Malaiya, “The Scaling Problem

in Neural Networks for Software Reliability Prediction,”

Proceedings of the 3rd International IEEE Symposium of

Software Reliability Engineering, Los Alamitos, 7-10 Oc-

tober 1992, pp. 76-82.

doi:10.1109/ISSRE.1992.285856

[7] N. Karunanithi, Y. K. Malaiya and D. Whitley, “Predic-

tion of Software Reliability Using Neural Networks,”

Proceedings of the 2nd IEEE International Symposium on

Software Reliability Engineering, Los Alamitos, 17-18

May 1991, pp. 124-130.

[8] N. Karunanithi, D. Whitley and Y. K. Malaiya, “Using

Neural Networks in Reliability Prediction,” IEEE Soft-

ware, Vol. 9, No. 4, 1992, pp. 53-59.

doi:10.1109/52.143107

[9] K. Y. Cai, L. Cai, W. D. Wang, Z. Y. Yu and D. Zhang,

“On the Neural Network Approach in Software Reliability

Modeling,” The Journal of Systems and Software, Vol. 58,

No. 1, 2001, pp. 47-62.

doi:10.1016/S0164-1212(01)00027-9

[10] S. A. Sherer, “Software Fault Prediction,” Journal of Sys-

tems and Software, Vol. 29, No. 2, 1995, pp. 97-105.

doi:10.1016/0164-1212(94)00051-N

[11] T. M. Khoshgoftar and R. M. Szabo, “Using Neural Net-

works to Predict Software Faults during Testing,” IEEE

Transactions on Reliability, Vol. 45, No. 3, 1996, pp. 456-

462. doi:10.1109/24.537016

[12] Y. S. Su, C. Y. Huang and Y. S. Chen, “An Artificial

Neural-Network Based Approach to Software Reliability

Assessment,” Proceedings of IEEE Region 10 Conference,

Melbourne, 21-24 November 2005, pp. 1-6.

[13] P. K. Kapur, S. K. Khatri, M. Basirzadeh and N. Dembla,

“Modeling Software Reliability Growth in Distributed

Environment Using Artificial Neural-Networks,” In: S. K.

Khatri and B. Kumar, Eds., Proceedings of International

Conference on Reliability, Infocom Technology and Op-

timization, Faridabad, 1-3 November 2010, pp. 372-382.

[14] P. K. Kapur, S. K. Khatri and D. N. Goswami, “A Gener-

alized Dynamic Integrated Software Reliability Growth

Model Based on Neural-Network Approach,” Proceed-

Copyright © 2011 SciRes. JSEA