AIML -Volume 8 - Issue I

AIML Issue (I) ICGST
Genetic Algorithms for Optimizing Ensemble of Models in Software Reliability Prediction
Sultan H. Aljahdali1 and Mohammed E. El-Telbany2
1College of Computers and Information Systems, Taif University Taif , Saudi Arabia
2Computers and Systems Department Electronics Research Institute, Cairo, Egypt
1http://www.tu.edu.sa/taef/init  

Abstract

Software reliability models are very useful to estimate the probability of the software fail along the time. Several different models have been proposed to predict the software reliability growth (SRGM); however, none of them has proven to perform well considering different project characteristics. The ability to predict the number of faults in the software during development and testing processes. In this paper, we explore Genetic Algorithms (GA) as an alternative approach to derive these models. GA is a powerful machine learning technique and optimization techniques to estimate the parameters of well known reliably growth models. Moreover, machine learning algorithms, proposed the solution overcome the uncertainties in the modeling by combining multiple models aiming at a more accurate prediction at the expense of increased uncertainty. The main motivation to choose GA for this task is its capability of estimating optimal parameters through learning from historical data. In this paper, experiments were conducted to confirm these hypotheses by evaluating the predictive capability of the developed ensemble of models and the results were compared with traditional models.

Keywords: genetic algorithms, software reliability, prediction, ensemble

( P1120820002, 1.21 MB)

Biographies:

Sultan Hamadi Aljahdali, Ph.D. received the B.S from Winona State University, Winona, Minnesota in 1992, and M.S. with honor from Minnesota State University, Mankato, Minnesota, 1996, and Ph.D. Information Technology from George Mason University, Fairfax, Virginia, U.S.A, 2003. He is an associate dean of the college of computers and information systems at Taif University. His research interest includes software testing, developing software reliability models, soft computing for software engineering, computer security, reverse engineering, and medical imaging, also he is a member of ACM, IEEE, and ISCA.

Mohammed El-Telbany, Ph.D. was born in Dammitta, Egypt, in 1968. He received the B.S. degree in computer engineering and science from the University of Minufia in 1991 and the M.Sc. and Ph.D degree in Computer Engineering, from Electronics and Communication Department, Cairo University, Faculty of Engineering, in 1997 and 2003 respectively. He has been an associative professor at the Electronics Research Institute. He has also worked at the ESA at European Space Research Institute (ESRIN), 1998-1999, Frascati, Italy, at the Faculty of Engineering, Al-Ahliyya Amman University, Jordan, 2004-2005, College of Computer Sciences, King Khalid University, KSA, 2005-2008 and College of Computer Sciences, Taif University, KSA. He has been involved in the field of autonomous mobile robots and machine leaning. His pervious research includes work on Evolutionary Computation and Forecasting. Current research includes work in robotics and reinforcement learning, and swarm intelligence.

@ARTICLE{P1120820002,

AUTHOR = {Sultan H. Aljahdali and Mohammed E. El-Telbany},

TITLE = {Genetic Algorithms for Optimizing Ensemble of Models in Software Reliability Prediction},

JOURNAL =  {The International Journal of Artificial Intelligence and Machine Learning},

YEAR = {2008},

VOLUME = {8},

ISSUE ={I},

PAGES = {5--13}

}

( P1120820002, 1.21 MB)