Software faults prediction using multiple classifiers

In recent years, the use of machine learning algorithms (classifiers) has proven to be of great value in solving a variety of problems in software engineering including software faults prediction. This paper extends the idea of predicting software faults by using an ensemble of classifiers which has...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2011 3rd International Conference on Computer Research and Development Ročník 4; s. 504 - 510
Hlavní autor: Twala, B
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.03.2011
Témata:
Accuracy
Boosting
classifers
Classification algorithms
ensemble
fault prediction
machine learning
Prediction algorithms
Software
software metrics
Support vector machines
Training
ISBN:1612848397, 9781612848396
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In recent years, the use of machine learning algorithms (classifiers) has proven to be of great value in solving a variety of problems in software engineering including software faults prediction. This paper extends the idea of predicting software faults by using an ensemble of classifiers which has been shown to improve classification performance in other research fields. Benchmarking results on two NASA public datasets show all the ensembles achieving higher accuracy rates compared with individual classifiers. In addition, boosting with AR and DT as components of an ensemble is more robust for predicting software faults.
ISBN:1612848397
9781612848396
DOI:10.1109/ICCRD.2011.5763845