Software defect prediction using relational association rule mining

Czibula, Gabriela; Marian, Zsuzsanna; Czibula, Istvan Gergely

doi:10.1016/j.ins.2013.12.031

Cited by 136 publications

(74 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It basically deals with finding rules that will predict the occurrence of item based on the occurrence of other items. [11,17,40,26] 3. Clustering: Clustering is a way to categorize a collection of items into groups or clusters whose members are similar in some way.…”

Section: Software Defect Predictionmentioning

confidence: 99%

A Study on Software Metrics based Software Defect Prediction using Data Mining and Machine Learning Techniques

Prasad¹,

Florence²,

Arya³

2015

IJDTA

View full text Add to dashboard Cite

show abstract

Section: Software Defect Predictionmentioning

confidence: 99%

A Study on Software Metrics based Software Defect Prediction using Data Mining and Machine Learning Techniques

Prasad¹,

Florence²,

Arya³

2015

IJDTA

View full text Add to dashboard Cite

show abstract

“…After using the some data preprocessing methods such as oversampling, discretization and input selection, they applied AntMiner+ and then compared the performance of the model with the performances of the models which were built with C4.5, logistic regression and SVM. In the study of Czibula, Marian and Czibula; relational association rules mining which was a kind of classification method was used for defect prediction [14]. The irrelevant metrics were eliminated by preprocessing.…”

Section: Related Workmentioning

confidence: 99%

Software Fault Inference Based on Expert Opinion

Erturkr¹,

Sezer²

2015

JSW

View full text Add to dashboard Cite

Software fault prediction is a process which predicts that the software modules are faulty or not by using the software metrics and some soft computing methods. Software metrics are divided into two main categories such as object-oriented and method-level metrics. While class relationships and dependencies are covered by object-oriented metrics, behaviors of the classes can be also measured by method-level metrics. Actually, the complementary relationship between these metric groups is focused in this study and different predictive models are built by using different parameter sets. Each parameter set includes some object-oriented and some method-level metrics. Furthermore, Mamdani style fuzzy inference system (FIS) is employed here to predict faultiness. In contrast to data-driven methods, FIS does not require historical or previous data for modeling. In fact, it is a rule-based approach and rules are extracted with the help of domain experts. In this study, the dataset which consists of the method-level and the class-level metrics' values that are collected from KC1 project of PROMISE repository is employed and most successful model whose performance is 0.8181 according to the evaluation criteria (the area under receiver operating characteristics (ROC) curve (AUC)) is built with the parameters of "coupling between object", "line of code" and, "cyclomatic complexity".

show abstract

“…Initial methods of prediction for software fault-proneness were built using statistics, though the prediction efficiency was insufficient of these methods. For this reason, most modern studies introduce the machine learning systems comprising data mining [4], SVMs [5], ANN [6], naive Bayes algorithm [7], and fuzzy logic, etc. While software faults were explored using these methods, yet there are numerous characteristics of faults continuing vague.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Approach for Software Fault Prediction Using Artificial Neural Network and Simplified Swarm Optimization

Pahal¹,

Chillar²

2017

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

Abstract:The major task in the software developing is to provide a software which is free from any kind of defects. But this task is hard to accomplish by the developers. Fault prediction can be classified as one main region to forecast the possibility of the software containing faults. The aim of the fault prediction in software development life cycle is to categorize the software modules in fault-prone and non fault-prone modules as soon as possible. This classification of fault-proneness of a module is actually essential for reducing the cost and increasing the efficiency of the software development process. In this paper, we propose a hybrid model using artificial neural network (ANN) and Simplified Swarm Optimization (SSO) for fault prediction. ANN is used for categorization the software modules in fault-prone and non-fault-prone modules, and SSO is then used to reduce dimensionality of dataset. This approach is easy to implement as no expert knowledge is required. The attained results confirms a preferred performance of this approach for fault prediction and output rate or recognition. The results indicates the prediction rates of proposed method is more than 90 percent in best condition.

show abstract

Software defect prediction using relational association rule mining

Cited by 136 publications

References 29 publications

A Study on Software Metrics based Software Defect Prediction using Data Mining and Machine Learning Techniques

A Study on Software Metrics based Software Defect Prediction using Data Mining and Machine Learning Techniques

Software Fault Inference Based on Expert Opinion

A Hybrid Approach for Software Fault Prediction Using Artificial Neural Network and Simplified Swarm Optimization

Contact Info

Product

Resources

About