Benchmarking Machine Learning Techniques for Software Defect Detection

Aleem, Saiqa; Capretz, Luiz Fernando; Ahmed, Faheem

doi:10.5121/ijsea.2015.6302

Cited by 45 publications

(34 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The researchers achieve the fair and rigorous comparison of learners by using significance test [39] because of its ability to distinguish significant observation from chance observations. According to [39], Wilcoxon signed rank test is recommended as a non-parametric test to be utilized for comparing between two learners over multiple datasets.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Early Prediction of Software Defect using Ensemble Learning: A Comparative Study

Abdou¹,

Darwish²

2018

IJCA

View full text Add to dashboard Cite

Recently, early prediction of software defects using the machine learning techniques has attracted more attention of researchers due to its importance in producing a successful software. On the other side, it reduces the cost of software development and facilitates procedures to identify the reasons for determining the percentage of defect-prone software in future. There is no conclusive evidence for specific types of machine learning that will be more efficient and accurate to predict of software defects. However, some of the previous related work proposes the ensemble learning techniques as a more accurate alternative. This paper introduces the resample technique with three types of ensemble learners; Boosting, Bagging and Rotation Forest, using eight of base learner tested on seven types of benchmark datasets provided in the PROMISE repository. Results indicate that accuracy has been improved using ensemble techniques more than single leaners especially in conjunction with Rotation Forest with the resample technique in most of the algorithms used in the experimental results.

show abstract

Section: Resultsmentioning

confidence: 99%

“…According to [39], Wilcoxon signed rank test is recommended as a non-parametric test to be utilized for comparing between two learners over multiple datasets. Otherwise, in case of comparing the multiple learners over multiple datasets, the fireman test is recommended by Post-hoc Nemenyi test.…”

Section: Resultsmentioning

confidence: 99%

Early Prediction of Software Defect using Ensemble Learning: A Comparative Study

Abdou¹,

Darwish²

2018

IJCA

View full text Add to dashboard Cite

show abstract

“…Aleem et al [23] "used 15 NASA datasets from the PROMISE repository to compare the performance of 11 machine learning methods". The study included NB, multi-layer perception (MLP), support vector machines (SVMs), AdaBoost, bagging, DS, RF, J48, KNN, RBF, and k-means.…”

Section: Related Researchmentioning

confidence: 99%

Hybrid Ensemble Learning Technique for Software Defect Prediction

Khan¹

2020

IJMECS

View full text Add to dashboard Cite

The reliability of software depends on its ability to function without error. Unfortunately, errors can be generated during any phase of software development. In the field of software engineering, the prediction of software defects during the initial stages of development has therefore become a top priority. Scientific data are used to predict the software's future release. Study shows that machine learning and hybrid algorithms are change benchmarks in the prediction of defects. During the past two decades, various approaches to software defect prediction that rely on software metrics have been proposed. This paper explores and compares well-known supervised machine learning and hybrid ensemble classifiers in eight PROMISE datasets. The experimental results showed that AdaBoost support vector machines and bagging support vector machines were the best performing classifiers in Accuracy, AUC, recall and F-measure.

show abstract

“…Aleem et al [27] compared the performance of 11 machine learning methods and used 15 NASA datasets from the PROMISE repository. NB, MLP, SVM, AdaBoost, bagging, DS, RF, J48, KNN, RBF, and k-means were applied in their study.…”

Section: Related Workmentioning

confidence: 99%

“…In addition, Bowes [22] suggested the use of classifier ensembles to effectively predict defects. A number of works have been accomplished in the field of SDP utilizing ensemble methods such as bagging [23] [24] [25], voting [22] [26], boosting [23] [24] [25], random tree [22], RF [27] [28], and stacking [22]. Neural networks (NN) can be used to predict defect prone software modules [29] [30] [31] [32].…”

Section: Introductionmentioning

confidence: 99%

Software Defect Prediction Using Supervised Machine Learning and Ensemble Techniques: A Comparative Study

Alsaeedi¹,

Khan²

2019

JSEA

View full text Add to dashboard Cite

An essential objective of software development is to locate and fix defects ahead of schedule that could be expected under diverse circumstances. Many software development activities are performed by individuals, which may lead to different software bugs over the development to occur, causing disappointments in the not-so-distant future. Thus, the prediction of software defects in the first stages has become a primary interest in the field of software engineering. Various software defect prediction (SDP) approaches that rely on software metrics have been proposed in the last two decades. Bagging, support vector machines (SVM), decision tree (DS), and random forest (RF) classifiers are known to perform well to predict defects. This paper studies and compares these supervised machine learning and ensemble classifiers on 10 NASA datasets. The experimental results showed that, in the majority of cases, RF was the best performing classifier compared to the others.

show abstract

Benchmarking Machine Learning Techniques for Software Defect Detection

Cited by 45 publications

References 29 publications

Early Prediction of Software Defect using Ensemble Learning: A Comparative Study

Early Prediction of Software Defect using Ensemble Learning: A Comparative Study

Hybrid Ensemble Learning Technique for Software Defect Prediction

Software Defect Prediction Using Supervised Machine Learning and Ensemble Techniques: A Comparative Study

Contact Info

Product

Resources

About