Software Reliability Prediction Model Research Articles

A multifaceted model for software reliability prediction during testing

A multifaceted model for software reliability prediction during testing

Robust feedforward and recurrent neural network based dynamic weighted combination models for software reliability prediction

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 (PFFNNDWCM) 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.

Software reliability prediction model based on support vector regression with improved estimation of distribution algorithms

Software reliability prediction plays a very important role in the analysis of software quality and balance of software cost. The data during software lifecycle is used to analyze and predict software reliability. However, predicting the variability of software reliability with time is very difficult. Recently, support vector regression (SVR) has been widely applied to solve nonlinear predicting problems in many fields and has obtained good performance in many situations; however it is still difficult to optimize SVR's parameters. Previously, some optimization algorithms have been used to find better parameters of SVR, but these existing algorithms usually are not fully satisfactory. In this paper, we first improve estimation of distribution algorithms (EDA) in order to maintain the diversity of the population, and then a hybrid improved estimation of distribution algorithms (IEDA) and SVR model, called IEDA-SVR model, is proposed. IEDA is used to optimize parameters of SVR, and IEDA-SVR model is used to predict software reliability. We compare IEDA-SVR model with other software reliability models using real software failure datasets. The experimental results show that the IEDA-SVR model has better prediction performance than the other models.

Software reliability prediction based on learning vector quantization neutral network

The application of traditional software prediction model has poor generalized performance.This paper put forward a software reliability prediction model based on Learning Vector Quantization(LVQ) neural network.First,this paper analyzed the structure characteristics of LVQ neural network and its relation with software reliability prediction.Then the network was used to predict the software reliability.In the end,the authors confirmed the algorithm through multiple simulation experiments under the Matlab environment and the data from Metrics Data Program(MDP) database of National Aeronautics and Space Administration(NASA) of USA.The experimental results indicate that the method is feasible and has a higher prediction precision than the traditional software prediction method.

A study on software reliability prediction models using soft computing techniques

Accurate software reliability prediction can not only enable developers to improve the quality of software but also provide useful information to help them for planning valuable resources. In this paper, we examine an analytical perspective of software reliability prediction using soft computing techniques with specific focus on methods, metrics and datasets. Based on the investigated results, usage percentage of datasets of public domain and soft computing techniques has increased significantly in last ten years. However, measurements using metrics are still the most dominant methods for predicting software reliability. In practice, intelligent machine learning techniques have shown remarkable improvements for reliability prediction. Therefore, software practitioners working on software reliability prediction should continue to use public datasets and other machine learning algorithms to build better prediction models. The significant findings of our study, in conjunction with previous research, could be used as guidelines for practitioners to make predictions in more realistic operating-context.

An empirical study of software reliability prediction using machine learning techniques

The applications of machine learning techniques have shown remarkable improvements for the prediction of software reliability than traditional statistical techniques. In this paper, we apply some well-known machine learning methods such as artificial neural networks, support vector machines, cascade correlation neural network, decision trees and fuzzy inference system to predict the reliability of a software product. The proposed models have been evaluated using mean absolute error, root mean squared error, correlation coefficient and precision. The 16 software life cycle databases have been used for empirical studies. These databases are extracted from data and analysis center for software. A comparative analysis is performed in order to determine the importance of each method to assess the capability of software reliability prediction models. We also observe that these models may use in reliability predictions and results may be more close to the reality and precision is very effective with varied real-life failure datasets. Finally we conclude that proposed approach is more precise in its prediction capacity having better capability of generalization.

Software Reliability Prediction using Neural Network with Encoded Input

neural network based software reliability model to predict the cumulative number of failures based on Feed Forward architecture is proposed in this paper. Depending upon the available software failure count data, the execution time is encoded using Exponential and Logarithmic function in order to provide the encoded value as the input to the neural network. The effect of encoding and the effect of different encoding parameter on prediction accuracy have been studied. The effect of architecture of the neural network in terms of hidden nodes has also been studied. The performance of the proposed approach has been tested using eighteen software failure data sets. Numerical results show that the proposed approach is giving acceptable results across different software projects. The performance of the approach has been compared with some statistical models and statistical models with change point considering three datasets. The comparison results show that the proposed model has a good prediction capability. Software engineers can measure or forecast software reliability using software reliability models. In real software development process, cost and time are limited. The models are used to develop reliable software under given time and cost constraints. The software managers also determine the release time of the software with the help these models. In past few years, a large number of software reliability models/statistical models have been developed. Every model is based on certain assumptions. So the predictive capability of different models is different for different data sets. There exist no single models that can best suit for all cases. The statistical models are also influenced by different external parameters. To overcome these problems, non-parametric models like neural network and support vector machines have been used for last few years. The non-parametric models are not influenced by any external parameter and also not based on assumptions which are unrealistic in real situation. Neural network has become an alternative method in software reliability modeling, evaluation and prediction. In the literature, many neural network based software reliability prediction models exist and their prediction capability is proven better than some statistical models (4-6). All the neural network based software reliability models are basically experimental in nature. Anyone who wants to apply the models on real software data set, they have to first find out the architecture of the network in hit and trial method. In real cases, people lose their confidence to apply the models with high level of confidence. In this work, neural network models with Exponential and Logarithmic encoding scheme have been proposed to build non-parametric models for software reliability prediction. It has been shown in (14) that neural network models with the above two encoding scheme has better prediction for cumulative number of failures than some statistical models. But in (14), the value of the encoding parameter is determined by doing repeated experiments with hit and trial method. The purpose of this paper is to provide a guideline for the selection of encoding parameter which gives consistent results for different datasets. The proposed approach is applied using eighteen different data sets and found to provide consistent result for all datasets. The approach has been compared using three data sets with existing statistical models with change points. The rest of the paper has been organized as follows: In Section 2, some works related to software reliability prediction are introduced. Section 3 presents the proposed method to predict cumulative number of failures in software using neural network with two different encoding schemes such as Exponential and Logarithmic encoding. Section 4 shows the experimental result. Finally, Section 5 concludes the paper.

Measuring software reliability

Software reliability is an essential part of software engineering to ensure the quality of a system. There are various techniques, which can be used in building models for predicting quality attributes. This paper presents a Fuzzy model for software reliability prediction. We have proposed three parameters Availability, Failure Probability and Recoverability as an integrated measure of software reliability. Fuzzy Model provides a way to arrive at a discrete Reliability Non-functional requirement (NFR) in contrast to imprecise, vague and ambiguous. This model will help us to evolve intermediate stages between reliable state and unreliable state of a system. Results obtained by proposed model show that this is suitable for predicting software reliability of the software.

Application of feed-forward neural networks for software reliability prediction

Many analytical models have been proposed for modeling software reliability growth trends with different predictive capabilities at different phases of testing yet there still is a need to develop a model that can be applied for accurate predictions in a realistic environment. In this paper we describe a software reliability prediction model using feed-forward neural network for better reliability prediction through back-propagation algorithm and discuss the issues of network architecture and data representation methods. We demonstrate a comparative analysis between the proposed approach and three well known software reliability growth prediction models using seven different failure datasets collected from standard software projects to test the validity of the presented method. A numerical example also has been cited to illustrate the results that revealed significant improvement by using Artificial Neural Network (ANN) over conventional statistical models based on NHPP.

Quantifying software performance, reliability and security: An architecture-based approach

With component-based systems becoming popular and handling diverse and critical applications, the need for their thorough evaluation has become very important. In this paper we propose an architecture-based unified hierarchical model for software performance, reliability, security and cache behavior prediction. We employ discrete time Markov chains (DTMCs) to model software systems and provide expressions for predicting the overall behavior of the system based on its architecture as well as the characteristics of individual components. This approach also facilitates the identification of various bottlenecks. We illustrate its use through some case studies and also provide expressions to perform sensitivity analysis.

A hierarchical mixture model for software reliability prediction

It is important to develop general prediction models in current software reliability research. In this paper, we propose a hierarchical mixture of software reliability models (HMSRM) for software reliability prediction. This is an application of the hierarchical mixtures of experts (HME) architecture. In HMSRM, individual software reliability models are used as experts. During the training of HMSRM, an Expectation–Maximizing (EM) algorithm is employed to estimate the parameters of the model. Experiments illustrate that our approach performs quite well in the later stages of software development, and better than single classical software reliability models. We show that the method can automatically select the most appropriate lower-level model for the data and performances are well in prediction.

On-line prediction of software reliability using an evolutionary connectionist model

An on-line adaptive software reliability prediction model using evolutionary connectionist approach based on multiple-delayed-input single-output architecture is proposed. Based on the currently available software failure time data, genetic algorithm is used to globally optimize the number of the delayed input neurons and the number of neurons in the hidden layer of the neural network architecture. Bayesian regularization is applied to our network training scheme to improve the generalization capability. The corresponding optimized neural network architecture is iteratively and dynamically reconfigured in real-time as new actual failure time data arrives. The performance of our proposed approach has been tested using four real-time control and flight dynamic application data sets. Numerical results show that our proposed approach is robust across different software projects, and has a better performance with respect to next-step-predictability compared to existing neural network model for failure time prediction.

A Software Reliability Prediction Model Based on Software Reviewing Process Characteristics and Its Evaluation

A Software Reliability Prediction Model Based on Software Reviewing Process Characteristics and Its Evaluation

Software process simulation for reliability management

This paper describes the use of a process simulator to support software project planning and management. The modeling approach here focuses on software reliability, but is just as applicable to other software quality factors, as well as to cost and schedule factors. The process simulator was developed as a part of a decision support system for assisting project managers in planning or tailoring the software development process, in a quality driven manner. The original simulator was developed using the system dynamics approach. As the model evolved by applying it to a real software development project, a need arose to incorporate the concepts of discrete event modeling. The system dynamics model and discrete event models each have unique characteristics that make them more applicable in specific situations. The continuous model can be used for project planning and for predicting the effect of management and reliability engineering decisions. It can also be used as a training tool for project managers. The discrete event implementation is more detailed and therefore more applicable to project tracking and control. In this paper the structure of the system dynamics model is presented. The use of the discrete event model to construct a software reliability prediction model for an army project, the Crusader, is described in detail.

Proposed structure for decomposition software reliability prediction model

Considerable emphasis in the software community has been directed at software quality. A major difficulty in dealing with software, however, is the absence of a widely accepted definition of software quality and lack of quantitative measures of software quality products. A general discussion is presented on the issues relating to the importance, definition, and measurement of software quality. The effectiveness of current approaches to enhance software quality is analysed. An approach is suggested that allows periodic measurement of software quality at different stages of the development process in a quantitative fashion. This approach allows the prediction of the degree to which the final product can be relied on to perform its intended function.