• Journal of Applied Reliability
• /
• v.16 no.1
• /
• pp.48-55
• /
• 2016

Purpose: The purpose of this study is to identify the object-oriented metrics which have strong impact on the reliability and fault-proneness of software products. The reliability and fault-proneness of software product is closely related to the design properties of class diagrams such as coupling between objects and depth of inheritance tree. Methods: This study has empirically validated the object-oriented metrics to determine which metrics are the best to predict fault-proneness. We have tested the metrics using logistic regressions and artificial neural networks. The results are then compared and validated by ROC curves. Results: The artificial neural network models show better results in sensitivity, specificity and correctness than logistic regression models. Among object-oriented metrics, several metrics can estimate the fault-proneness better. The metrics are CBO (coupling between objects), DIT (depth of inheritance), LCOM (lack of cohesive methods), RFC (response for class). In addition to the object-oriented metrics, LOC (lines of code) metric has also proven to be a good factor for determining fault-proneness of software products. Conclusion: In order to develop fault-free and reliable software products on time and within budget, assuring quality of initial phases of software development processes is crucial. Since object-oriented metrics can be measured in the early phases, it is important to make sure the key metrics of software design as good as possible.

• Advances in Computational Design
• /
• v.2 no.4
• /
• pp.293-311
• /
• 2017

There are several claimed benefits for the impact of design patterns (DPs) on software quality. However, the association between design patterns and fault-proneness has been a controversial issue. In this work, we evaluate the fault-proneness of design patterns at four levels: the design level, category level, pattern level, and role level. We used five subject systems in our empirical study. As a result, we found that, at the design level, the classes that participate in the design patterns are less fault-prone than the non-participant classes. At the category level, we found that the classes that participate in the behavioral and structural categories are less fault-prone than the non-participant classes. In addition, we found that the classes that participate in the structural design patterns are less fault-prone than the classes that participate in the other categories. At the pattern level, we found that only five patterns show significant associations with fault-proneness: builder, factory method, adapter, composite, and decorator. All of these patterns except for builder show that the classes that participate in each one of them are less fault-prone than the non-participant classes in that pattern. The classes that participate in the builder design pattern were more fault-prone than the non-participant classes and the classes that participate in several patterns: the adapter, the composite, and the decorator design patterns. At the role level, the most significant differences were between the classes that participate in some roles and the non-participant classes. Only three pairs of design pattern roles show significant differences. These roles are concrete-product vs. concrete-creator, adapter vs. adaptee, and adapter vs. client. The results recommend the use of design patterns because they are less fault-prone in general except for the builder design pattern, which should be applied with care and addressed with more test cases.

• Journal of Information Processing Systems
• /
• v.8 no.2
• /
• pp.241-262
• /
• 2012

An understanding of quality attributes is relevant for the software organization to deliver high software reliability. An empirical assessment of metrics to predict the quality attributes is essential in order to gain insight about the quality of software in the early phases of software development and to ensure corrective actions. In this paper, we predict a model to estimate fault proneness using Object Oriented CK metrics and QMOOD metrics. We apply one statistical method and six machine learning methods to predict the models. The proposed models are validated using dataset collected from Open Source software. The results are analyzed using Area Under the Curve (AUC) obtained from Receiver Operating Characteristics (ROC) analysis. The results show that the model predicted using the random forest and bagging methods outperformed all the other models. Hence, based on these results it is reasonable to claim that quality models have a significant relevance with Object Oriented metrics and that machine learning methods have a comparable performance with statistical methods.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.5
• /
• pp.1739-1745
• /
• 2014

Prediction of fault-prone modules continues to attract researcher's interest due to its significant impact on software development cost. The most important goal of such techniques is to correctly identify the modules where faults are most likely to present in early phases of software development lifecycle. Various software metrics related to modules level fault data have been successfully used for prediction of fault-prone modules. Goal of this research is to predict the faulty modules at design phase using design metrics of modules and faults related to modules. We have analyzed the effect of pre-processing and different machine learning schemes on eleven projects from NASA Metrics Data Program which offers design metrics and its related faults. Using seven machine learning and four preprocessing techniques we confirmed that models built from design metrics are surprisingly good at fault proneness prediction. The result shows that we should choose Naïve Bayes or Voting feature intervals with discretization for different data sets as they outperformed out of 28 schemes. Naive Bayes and Voting feature intervals has performed AUC > 0.7 on average of eleven projects. Our proposed framework is effective and can predict an acceptable level of fault at design phases.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.2
• /
• pp.57-64
• /
• 2014

Most previous studies of software fault prediction model which determines the fault-proneness of input modules have focused on supervised learning model using training data set. However, Unsupervised learning model is needed in case supervised learning model cannot be applied: either past training data set is not present or even though there exists data set, current project type is changed. Building an unsupervised learning model is extremely difficult that is why only a few studies exist. In this paper, we build unsupervised models using representative clustering algorithms, EM and DBSCAN, that have not been used in prior studies and compare these models with the previous model using K-means algorithm. The results of our study show that the EM model performs slightly better than the K-means model in terms of error rate and these two models significantly outperform the DBSCAN model.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.5
• /
• pp.73-81
• /
• 2015

Most of the software fault prediction studies focused on the binary classification model that predicts whether an input entity has faults or not. However the ability to predict entity fault-proneness in various severity categories is more useful because not all faults have the same severity. In this paper, we propose fault prediction models at different severity levels of faults using traditional size and complexity metrics. They are ternary classification models and use four machine learning algorithms for their training. Empirical analysis is performed using two NASA public data sets and a performance measure, accuracy. The evaluation results show that backpropagation neural network model outperforms other models on both data sets, with about 81% and 88% in terms of accuracy score respectively.

• The Journal of Korean Association of Computer Education
• /
• v.8 no.5
• /
• pp.129-137
• /
• 2005

Criticality prediction models that identify fault-prone spots using system design specifications play an important role in reducing development costs of large systems such as telecommunication systems. Many criticality prediction models using complexity metrics have been suggested. But most of them need training data set for model training. And they are classification models that can only classify design entities into fault-prone group and non fault-prone group. To solve this problem, this paper builds a new prediction model, HMM, using two styled hybrid metrics. HMM has strong point that it does not need training data and it enables comparison between design entities by criticality. HMM is implemented and compared with a well-known prediction model, BackPropagation neural network Model(BPM), considering internal characteristics and accuracy of prediction.

• Journal of Information Processing Systems
• /
• v.14 no.3
• /
• pp.751-770
• /
• 2018

Web applications are indispensable in the software industry and continuously evolve either meeting a newer criteria and/or including new functionalities. However, despite assuring quality via testing, what hinders a straightforward development is the presence of defects. Several factors contribute to defects and are often minimized at high expense in terms of man-hours. Thus, detection of fault proneness in early phases of software development is important. Therefore, a fault prediction model for identifying fault-prone classes in a web application is highly desired. In this work, we compare 14 machine learning techniques to analyse the relationship between object oriented metrics and fault prediction in web applications. The study is carried out using various releases of Apache Click and Apache Rave datasets. En-route to the predictive analysis, the input basis set for each release is first optimized using filter based correlation feature selection (CFS) method. It is found that the LCOM3, WMC, NPM and DAM metrics are the most significant predictors. The statistical analysis of these metrics also finds good conformity with the CFS evaluation and affirms the role of these metrics in the defect prediction of web applications. The overall predictive ability of different fault prediction models is first ranked using Friedman technique and then statistically compared using Nemenyi post-hoc analysis. The results not only upholds the predictive capability of machine learning models for faulty classes using web applications, but also finds that ensemble algorithms are most appropriate for defect prediction in Apache datasets. Further, we also derive a consensus between the metrics selected by the CFS technique and the statistical analysis of the datasets.

• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.603-615
• /
• 2007

Software changes for various kinds of reasons and they increase maintenance cost. Software metrics, as quantitative values about attributes of software, have been adopted for predicting maintenance cost and fault-proneness. This paper proposes relationship between some typical object-oriented metrics and software changes in industrial settings. We used seven metrics which are concerned with size, complexity coupling, inheritance and polymorphism, and collected data about the number of changes during the development of an Information system on .NET platform. Based on them, this paper proposes a model for predicting the number of changes from the object-oriented metrics using multiple regression analysis technique.

• Journal of Information Technology Services
• /
• v.11 no.1
• /
• pp.211-221
• /
• 2012

Many metric-based classification models have been proposed to predict fault-proneness of software module. This paper presents two prediction models using Bayesian classifier which is one of the most popular modern classification algorithms. Bayesian model based on Bayesian probability theory can be a promising technique for software quality prediction. This is due to the ability to represent uncertainty using probabilities and the ability to partly incorporate expert's knowledge into training data. The two models, Na$\ddot{i}$veBayes(NB) and Bayesian Belief Network(BBN), are constructed and dimensionality reduction of training data and test data are performed before model evaluation. Prediction accuracy of the model is evaluated using two prediction error measures, Type I error and Type II error, and compared with well-known prediction models, backpropagation neural network model and support vector machine model. The results show that the prediction performance of BBN model is slightly better than that of NB. For the data set with ambiguity, although the BBN model's prediction accuracy is not as good as the compared models, it achieves better performance than the compared models for the data set without ambiguity.