Comments on ‘Evolutionary neural network modelling for software cumulative failure time prediction’ by Liang Tian and Afzel Noore [Reliability Engineering and System Safety 87 (2005) 45–51] (original) (raw)
Related papers
Evolutionary Neural Network Prediction for Software Reliability Modeling
2016
Abstract: Software Reliability is a key concern of many users and developers of softwares. Demand for high software reliability requires robust modeling techniques for software quality prediction. This paper presents a new approach to software reliability assessment by using neural network. The neural network model has been applied to three different applications and normalized root mean of the square of error as an evaluation criterion. Results show that the neural network model adopted has good predictive capability.
Evolutionary neural network prediction for cumulative failure modeling
2009
An evolutionary neural network modeling approach for software cumulative failure prediction based on feed-forward neural network is proposed. A real coded genetic algorithm is used to optimize the mean square of the error produced by training a neural network established by Aljahdali S. [3]. In this paper we present a real coded genetic algorithm that uses the appropriate operators for this encoding type to train feed-forward neural network. We describe the genetic algorithm and we also experimentally compare our approach with the back propagation learning algorithm for the regression model order 4. Numerical results show that both the goodness-offit and the next-step-predictability of our proposed approach have greater accuracy in predicting software cumulative failure compared to other approaches.
Evolutionary Prediction for Cumulative Failure Modeling: A Comparative Study
2011 Eighth International Conference on Information Technology: New Generations, 2011
In the past 35 years more than 100 software reliability models are proposed. Most of them are parametric models. In this paper we present a comparative study of different non-parametric models based on the neural networks and regression model learned by the real coded genetic algorithm to predict the cumulative failure in the software. Experimental results show that the training of different models by our real coded genetic algorithm have a good predictive capability across different projects.
An Artificial Neural-Network Approach to Software Reliability Growth Modeling
Software reliability growth models (SRGM) are statistical interpolation of software failure data by mathematical functions. The functions are used to estimate future failure rates and reliability or the number of residual defects in the software. The SRGM facilitates reliability engineers to decide when to stop testing. Although more than 200 traditional SRGMs have been proposed to estimate failure occurrence times, the research is still continuing to develop more robust models. Inherently the SRGMs are based on assumptions. In order to increase the estimation accuracy of the models we propose the SRGM based on Feed-Forward Neural Network (FFNN) approach. It seems to have significant advantages over the traditional SRGMs. Traditional parameter estimation of SRGMs need estimation ranges of parameter beforehand. The proposed artificial neural network (ANN) model does not have this requirement and hence the parameter estimation gives consistent results without any assumptions. In this paper a new neural network combination model based on the dynamically evaluated weights is proposed in order to improve the goodness of fit of already proposed traditional SRGMs and ANN based combination models. The performance comparison from practical software failure data sets seems to confirm that, the goodness of fit of proposed model is better than that of traditional SRGMs, both independent and ANN based models.
Accuracy of Artificial Neural Network Models of Software Reliability Growth – A Survey
Research in Computing Science, 2015
Software Engineering data is being analyzed by classical statistical methods and non parametric methods. Performance models are constructed using classical approach as a high maturity practice. Such practices are constrained by data quality and inadequacy of data analysis methods to treat data from real life projects. Data mining techniques can broaden the data analysis capability and improve prediction accuracy even with commonly presented data. Artificial neural networks are found as an improved prediction error estimation method against traditional parametric software reliability growth models. In this paper, we study prediction errors of Artificial Neural Networks (ANN) based Software Reliability Growth Models (ANN SRGM) with the objective of arriving at a criteria for selecting the methods having least prediction errors. All major works in ANN SRGM's are considered and reported errors are analyzed. Accuracy of ANN SRGM's are compared against that of parametric models. Then, inter-comparison of error performances of ANN SRGM's of different applications is made.
Prediction of software reliability using neural networks
Proceedings. 1991 International Symposium on Software Reliability Engineering, 1991
Software reliability growth models have achieved considerable importance in estimating reliability of software products. This paper explores the use of feed-forward neural networks as a model for software reliability growth prediction. To empirically evaluate the predictive capability of this new approach data sets from di erent software projects are used. The neural networks approach exhibits a consistent behavior in prediction and the predictive performance is comparable to that of parametric models.
IFIP International Federation for Information Processing
Software failure and software reliability are strongly related concepts. Introducing a model that would perform successful failure prediction could provide the means for achieving higher software reliability and quality. In this context, we have employed artificial neural networks and genetic algorithms to investigate whether software failure can be accurately modeled and forecasted based on empirical data of real systems.
Evolutionary regression prediction for software cumulative failure modeling: A comparative study
2009
An evolutionary regression modeling approach for software cumulative failure prediction based on auto-regression order 4, 7 and 10 models are proposed. A real coded genetic algorithm is used to optimize the mean square of the error produced by training the auto-regression model. In this paper, we present a real coded genetic algorithm that uses the appropriate operators for this encoding type to train the autoregression model. To evaluate the predictive capability of the developed model data sets, various projects were used. A comparison between auto-regression order 4 model trained using least square estimation [1] and real coded genetic algorithm training is provided, also a comparison between the autoregression order 7 and 10 models trained using the genetic algorithm is presented. Experimental results show that the training of different auto-regression model by the real coded genetic algorithm has a good predictive capability.
2001
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 [l]. A comparison between regression parametric models and neural network models is provided.