• 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.

• 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.

• 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 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.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1566-1582
• /
• 2019

Silent Data Corruptions (SDCs) is a serious reliability issue in many domains of computer system. The identification and protection of the program instructions that cause SDCs is one of the research hotspots in computer reliability field at present. A lot of solutions have already been proposed to solve this problem. However, many of them are hard to be applied widely due to time-consuming and expensive costs. This paper proposes an intelligent approach named SDCPredictor to identify the instructions that cause SDCs. SDCPredictor identifies SDC-causing Instructions depending on analyzing the static and dynamic features of instructions rather than fault injections. The experimental results demonstrate that SDCPredictor is highly accurate in predicting the SDCs proneness. It can achieve higher fault coverage than previous similar techniques in a moderate time cost.

• 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.

• 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.

• Steel and Composite Structures
• /
• v.47 no.4
• /
• pp.451-454
• /
• 2023

Landslides are one of the natural disasters that cause a lot of financial and human losses every year It will be all over the world. China, especially. The Mainland China can be divided into 12 zones, including 4 high susceptibility zones, 7 medium susceptibility zones and 1 low susceptibility zone, according to landslide proneness. Climate and physiography are always at risk of landslides. The purpose of this research is to prepare a landslide hazard map using the Hierarchical Analysis Process method. In the GIS environment, it is in a part of China watershed. In order to prepare a landslide hazard map, first with Field studies, a distribution map of landslides in the area and then a map of factors affecting landslides were prepared. In the next stage, the factors are prioritized using expert opinion and hierarchical analysis process and nine factors including height, slope, slope direction, geological units, land use, distance from Waterway, distance from the road, distance from the fault and rainfall map were selected as effective factors. Then Landslide risk zoning in the region was done using the hierarchical analysis process model. The results showed that the three factors of geological units, distance from the road and slope are the most important have had an effect on the occurrence of landslides in the region, while the two factors of fault and rainfall have the least effect The landslide occurred in the region.