An Artificial Neural-Network Approach to Software Reliability Growth Modeling (original) (raw)
Related papers
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.
Abstract Background/Objectives: To design a relatively simple Software Reliability Growth Model (SRGM) with testing effort function using Artificial Neural Network approach. Methods/Statistical Analysis: The results evaluation of the proposed SRGM using Artificial Neural Network (ANN) is measured by calculating the three vital criterians namely; AIC (Akaike Information Criterian), R2 (Coefficient of determination) and RMSE (Root Mean Squared Error). Findings: Traditional time-based models may not be appropriate in some situations where the effort is varying with time. Estimating the total effort required for testing the software in the Software Development Life Cycle (SDLC) is important. Hence, a multi-layer feed-forward Artificial Neural Network (ANN) based SRGM using back propagation training is proposed in this paper by incorporating test effort. The proposed ANN based model provides consistent performance for both exponential and S-shaped growth of mean value functions witnessed in software projects. Application/Improvements: The proposed SRGM using ANN will be performed to be eminently useful for software reliability applications, since it is able to maintain its performance in all situation.
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.
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.
An Artificial Neural-Network-Based Approach to Software Reliability Assessment
TENCON 2005 - 2005 IEEE Region 10 Conference, 2005
In this paper, we propose an artificial neuralnetwork-based approach for software reliability estimation and modeling. We first explain the network networks from the mathematical viewpoints of software reliability modeling. That is, we will show how to apply neural network to predict software reliability by designing different elements of neural networks. Furthermore, we will use the neural network approach to build a dynamic weighted combinational model. The applicability of proposed model is demonstrated through four real software failure data sets. From experimental results, we can see that the proposed model significantly outperforms the traditional software reliability models.
Journal of Software Engineering and Applications, 2011
Due to high cost of fixing failures, safety concerns, and legal liabilities, organizations need to produce software that is highly reliable. Software reliability growth models have been developed by software developers in tracking and measuring the growth of reliability. Most of the Software Reliability Growth Models, which have been proposed, treat the event of software fault detection in the testing and operational phase as a counting process. Moreover, if the size of software system is large, the number of software faults detected during the testing phase becomes large, and the change of the number of faults which are detected and removed through debugging activities becomes sufficiently small compared with the initial fault content at the beginning of the testing phase. Therefore in such a situation, we can model the software fault detection process as a stochastic process with a continuous state space. Recently, Artificial Neural Networks (ANN) have been applied in software reliability growth prediction. In this paper, we propose an ANN based software reliability growth model based on Î to type of stochastic differential equation. The model has been validated, evaluated and compared with other existing NHPP model by applying it on actual failure/fault removal data sets cited from real software development projects. The proposed model integrated with the concept of stochastic differential equation performs comparatively better than the existing NHPP based model.
The scaling problem in neural networks for software reliability prediction
[1992] Proceedings Third International Symposium on Software Reliability Engineering, 1992
Recently neural networks have been applied for software reliability growth prediction. Although the predictive capability of the neural network models are better than some of the well known analytic models, the scaling problem has not been completely addressed yet. With the present neural network models, it is necessary to scale the cumulative faults over a 0.0 to 1.0 range. So the user has to estimate in advance a maximum value for the total number of faults to be detected at the end of the test phase. In practice, such an estimate may not be accurate. Use of an inaccurate value for scaling the cumulative faults can severely affect the predictive capability of neural network models. This paper presents a solution to the scaling problem in terms of a clipped linear unit in the output layer. With a clipped linear output unit, the neural networks can predict positive values in any unbounded range. We demonstrate the applicability of the proposed network structure with three data sets and compare its predictive accuracy with that of our earlier models. Expressions for the failure rate process represented by the models of the proposed network structure are also derived.
Applied Soft Computing, 2014
Traditional parametric software reliability growth models (SRGMs) are based on some assumptions or distributions and none such single model can produce accurate prediction results in all circumstances. Non-parametric models like the artificial neural network (ANN) based models can predict software reliability based on only fault history data without any assumptions. In this paper, initially we propose a robust feedforward neural network (FFNN) based dynamic weighted combination model (PFFNND-WCM) for software reliability prediction. Four well-known traditional SRGMs are combined based on the dynamically evaluated weights determined by the learning algorithm of the proposed FFNN. Based on this proposed FFNN architecture, we also propose a robust recurrent neural network (RNN) based dynamic weighted combination model (PRNNDWCM) to predict the software reliability more justifiably. A real-coded genetic algorithm (GA) is proposed to train the ANNs. Predictability of the proposed models are compared with the existing ANN based software reliability models through three real software failure data sets. We also compare the performances of the proposed models with the models that can be developed by combining three or two of the four SRGMs. Comparative studies demonstrate that the PFFNNDWCM and PRNNDWCM present fairly accurate fitting and predictive capability than the other existing ANN based models. Numerical and graphical explanations show that PRNNDWCM is promising for software reliability prediction since its fitting and prediction error is much less relative to the PFFNNDWCM.
Conceptual Software Reliability Model using Neural Network
International Journal of Computer Applications, 2015
Reliability is the one of the most important attribute of the software for customer satisfaction. It is big challenge for the software development organizations to achieve the reliability of the software. Since research on software reliability is being carried out for last three decades and various software reliability models have been developed. These models calculate the reliability of the software and help to take decision to deploy the software or continue the testing process to meet the reliability objective. The models used so far, worked on the basis of some conventions which must be made before the beginning of the project like software development environment, the nature of software failures, the probability of individual failures. Recent research in the field of the Neural Network can also be applied to calculate the software reliability. The best thing to use Neural Network is to calculate the reliability without making any basic assumptions. In this paper, a conceptual model is proposed to develop the software reliability model using the approach of Neural Network.