Using neural networks in reliability prediction

Karunanithi, N.; Whitley, Darrell; Malaiya, Yashwant K.

doi:10.1109/52.143107

Cited by 226 publications

(88 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, attention has turned to a variety of machine learning (ML) methods to predict software development eort. Arti®cial neural nets (ANNs), case-based reasoning (CBR) and rule induction (RI) are examples of such methods (see Karunanithi et al, 1992;Gray and MacDonell, 1997;Jorgensen, 1995). This paper outlines some comparative research into the use of ML methods to build software cost prediction systems.…”

Section: Background To Researchmentioning

confidence: 99%

An investigation of machine learning based prediction systems

Mair

Kadoda

Lefley

et al. 2000

Journal of Systems and Software

192

View full text Add to dashboard Cite

Traditionally, researchers have used either o-the-shelf models such as COCOMO, or developed local models using statistical techniques such as stepwise regression, to obtain software eort estimates. More recently, attention has turned to a variety of machine learning methods such as arti®cial neural networks (ANNs), case-based reasoning (CBR) and rule induction (RI). This paper outlines some comparative research into the use of these three machine learning methods to build software eort prediction systems. We brie¯y describe each method and then apply the techniques to a dataset of 81 software projects derived from a Canadian software house in the late 1980s. We compare the prediction systems in terms of three factors: accuracy, explanatory value and con®gurability. We show that ANN methods have superior accuracy and that RI methods are least accurate. However, this view is somewhat counteracted by problems with explanatory value and con®gurability. For example, we found that considerable eort was required to con®gure the ANN and that this compared very unfavourably with the other techniques, particularly CBR and least squares regression (LSR). We suggest that further work be carried out, both to further explore interaction between the enduser and the prediction system, and also to facilitate con®guration, particularly of ANNs. Ó

show abstract

Section: Background To Researchmentioning

confidence: 99%

An investigation of machine learning based prediction systems

Mair

Kadoda

Lefley

et al. 2000

Journal of Systems and Software

192

View full text Add to dashboard Cite

show abstract

“…The former attempts to construct a model that describes the relationship between dependent and independent variables of the underlying process. Neural networks are a common example of such a model, and are used by many practitioners to predict software effort [9,29,47,69,73]. The latter (Also known as Case-Based Reasoning [1] or Instance-Based Reasoning [67]), however, tries to find a range of well documented similar historical cases.…”

Section: Effort Prediction Methodsmentioning

confidence: 99%

“…These models, accompanying some statistical analysis, have been used to predict the effort required to develop and maintain software systems. Many models such as COCOMO [10] and Neural Networks [9,29,47,73] have become widely spread in the software community as effective prediction tools. Consequently, effort prediction has become an important tool in corporate management's arsenal, especially for today's multinational projects.…”

Section: Introductionmentioning

confidence: 99%

An effort prediction framework for software defect correction

Hassouna¹,

Tahvildari²

2010

Information and Software Technology

View full text Add to dashboard Cite

Developers apply changes and updates to software systems to adapt to emerging environments and address new requirements. In turn, these changes introduce additional software defects, usually caused by our inability to comprehend the full scope of the modified code. As a result, software practitioners have developed tools to aid in the detection and prediction of imminent software defects, in addition to the effort required to correct them. Although software development effort prediction has been in use for many years, research into defect-correction effort prediction is relatively new. The increasing complexity, integration and ubiquitous nature of current software systems has sparked renewed interest in this field. Effort prediction now plays a critical role in the planning activities of managers. Accurate predictions help corporations budget, plan and distribute available resources effectively and efficiently. In particular, early defect-correction effort predictions could be used by testers to set schedules, and by managers to plan costs and provide earlier feedback to customers about future releases.In this work, we address the problem of predicting the effort needed to resolve a software defect. More specifically, our study is concerned with defects or issues that are reported on an Issue Tracking System or any other defect repository. Current approaches use one prediction method or technique to produce effort predictions. This approach usually suffers from the weaknesses of the chosen prediction method, and consequently the accuracy of the predictions are affected. To address this problem, we present a composite prediction framework. Rather than using one prediction approach for all defects, we propose the use of multiple integrated methods which complement the weaknesses of one another. Our framework is divided into two sub-categories, Similarity-Score Dependent and Similarity-Score Independent. The Similarity-Score Dependent method utilizes the power of Case-Based Reasoning, also known as Instance-Based Reasoning, to compute predictions. It relies on matching target issues to similar historical cases, then combines their known effort for an informed estimate. On the other hand, the Similarity-Score Independent method makes use of other defect-related information with some statistical manipulation to produce the required estimate. To measure similarity between defects, some method of distance calculation must be used. In some cases, this method might produce misleading results due to observed inconsistencies in history, and the fact that current similarity-scoring techniques cannot account for all the variability in the data. In this case, the Similarity-Score Independent method can be used to estimate the effort, where the effect of such inconsistencies can be reduced.We have performed a number of experimental studies on the proposed framework to assess the effectiveness of the presented techniques. We extracted the data sets from an operational Issue Tracking System in order to test the validity...

show abstract

“…Cumulative execution time as the input and the number of failures as the output have been considered by Karunanithi et al, in [2]. On the other hand, [5] set the number of failures as input and the time of failure as the output.…”

Section: Literature Reviewmentioning

confidence: 99%