Conference Proceeding

Prediction of software reliability: a comparison between regression and neural network non-parametric models

Sch. of Inf. Tech., George Mason Univ., Fairfax, VA
02/2001; DOI:10.1109/AICCSA.2001.934046 ISBN: 0-7695-1165-1 pp.470 - 473 In proceeding of: Computer Systems and Applications, ACS/IEEE International Conference on. 2001
Source: IEEE Xplore

ABSTRACT In this paper, neural networks have been proposed as an
alternative technique to build software reliability growth models. A
feedforward neural network was used to predict the number of faults
initially resident in a program at the beginning of a test/debug
process. To evaluate the predictive capability of the developed model,
data sets from various projects were used. A comparison between
regression parametric models and neural network models is provided

0 0
 · 
0 Bookmarks
 · 
33 Views
  • Source
    Conference Proceeding: Predicting the Reliability of Software Systems Using Fuzzy Logic
    S. Aljahdali, A.F. Sheta
    [show abstract] [hide abstract]
    ABSTRACT: Software industry suffer many challenges in developing a high quality reliable software. Many factors affect their development such as the schedule, limited resources, uncertainty in the developing environment and inaccurate requirement specification. Software Reliability Growth Models (SRGM)were significantly used to help in solving these problems by accurately predicting the number of faults in the software during both development and testing processes. The issue of building growth models was the subject of many research work. In this paper, we explore the use of fuzzy logic to build a SRGM. The proposed fuzzy model consists of a collection of linear sub-models joined together smoothly using fuzzy membership functions to represent the fuzzy model. Results and analysis based data set developed by John Musa of Bell Telephone Laboratories are provided to show the potential advantages of using fuzzy logic in solving this problem.
    Information Technology: New Generations (ITNG), 2011 Eighth International Conference on; 05/2011
  • Source
    Article: A Genetic Programming Approach for Software Reliability Modeling
    E.O. Costa, A. Pozo, S.R. Vergilio
    [show abstract] [hide abstract]
    ABSTRACT: Genetic programming (GP) models adapt better to the reliability curve when compared with other traditional, and non-parametric models. In a previous work, we conducted experiments with models based on time, and on coverage. We introduced an approach, named genetic programming and Boosting (GPB), that uses boosting techniques to improve the performance of GP. This approach presented better results than classical GP, but required ten times the number of executions. Therefore, we introduce in this paper a new GP based approach, named (?? + ??) GP. To evaluate this new approach, we repeated the same experiments conducted before. The results obtained show that the (?? + ??) GP approach presents the same cost of classical GP, and that there is no significant difference in the performance when compared with the GPB approach. Hence, it is an excellent, less expensive technique to model software reliability.
    IEEE Transactions on Reliability 04/2010; · 1.28 Impact Factor
  • Source
    Conference Proceeding: Predicting the Reliability of Software Systems Using Fuzzy Logic.
    Sultan Aljahdali, Alaa F. Sheta
    Eighth International Conference on Information Technology: New Generations, ITNG 2011, Las Vegas, Nevada, USA, 11-13 April 2011; 01/2011

Show more

Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.

Keywords

alternative technique
 
developed model
 
feedforward neural network
 
neural network models
 
regression parametric models
 
software reliability growth models
 
various projects
 

S.H. Aljahdali