A DEEP ENSEMBLE LEARNING METHOD FOR EFFORT-AWARE JUST-IN-TIME DEFECT PREDICTION
Since the introduction of Just-in-Time effort aware defect prediction, many researchers are focusing on evaluating the different learning methods for defect prediction. To predict the changes that are defect-inducing, it is im-portant for learning model to consider the nature of the dataset, its imb...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Polish Association for Knowledge Promotion
2020-09-01
|
Series: | Applied Computer Science |
Subjects: | |
Online Access: | http://acs.pollub.pl/pdf/v16n3/1.pdf |
id |
doaj-c4511f309b7c4e5599c1cdcb920154a0 |
---|---|
record_format |
Article |
spelling |
doaj-c4511f309b7c4e5599c1cdcb920154a02020-11-25T03:43:35ZengPolish Association for Knowledge PromotionApplied Computer Science1895-37352353-69772020-09-0116351510.23743/acs-2020-17A DEEP ENSEMBLE LEARNING METHOD FOR EFFORT-AWARE JUST-IN-TIME DEFECT PREDICTIONSaleh ALBAHLI0Qassim University, College of Computer, Department of Information Technology, Saudi Arabia, 51452, Qassim, salbahli@qu.edu.saSince the introduction of Just-in-Time effort aware defect prediction, many researchers are focusing on evaluating the different learning methods for defect prediction. To predict the changes that are defect-inducing, it is im-portant for learning model to consider the nature of the dataset, its imbalance properties and the correlation between different attributes. In this paper, we evaluated the importance of dataset properties, and proposed a novel methodology for learning the effort aware just-in-time defect prediction model. We form an ensemble classifier, which consider the output of three individuals classifier i.e. Random forest, XGBoost and Deep Neural Network. Our proposed methodology shows better performance with 77% accuracy on sample dataset and 81% accuracy on different dataset.http://acs.pollub.pl/pdf/v16n3/1.pdfdeep neural networkunlabeled datasetjust-in-time defect predictionunsupervised prediction |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Saleh ALBAHLI |
spellingShingle |
Saleh ALBAHLI A DEEP ENSEMBLE LEARNING METHOD FOR EFFORT-AWARE JUST-IN-TIME DEFECT PREDICTION Applied Computer Science deep neural network unlabeled dataset just-in-time defect prediction unsupervised prediction |
author_facet |
Saleh ALBAHLI |
author_sort |
Saleh ALBAHLI |
title |
A DEEP ENSEMBLE LEARNING METHOD FOR EFFORT-AWARE JUST-IN-TIME DEFECT PREDICTION |
title_short |
A DEEP ENSEMBLE LEARNING METHOD FOR EFFORT-AWARE JUST-IN-TIME DEFECT PREDICTION |
title_full |
A DEEP ENSEMBLE LEARNING METHOD FOR EFFORT-AWARE JUST-IN-TIME DEFECT PREDICTION |
title_fullStr |
A DEEP ENSEMBLE LEARNING METHOD FOR EFFORT-AWARE JUST-IN-TIME DEFECT PREDICTION |
title_full_unstemmed |
A DEEP ENSEMBLE LEARNING METHOD FOR EFFORT-AWARE JUST-IN-TIME DEFECT PREDICTION |
title_sort |
deep ensemble learning method for effort-aware just-in-time defect prediction |
publisher |
Polish Association for Knowledge Promotion |
series |
Applied Computer Science |
issn |
1895-3735 2353-6977 |
publishDate |
2020-09-01 |
description |
Since the introduction of Just-in-Time effort aware defect prediction, many researchers are focusing on evaluating the different learning methods for defect prediction. To predict the changes that are defect-inducing, it is im-portant for learning model to consider the nature of the dataset, its imbalance properties and the correlation between different attributes. In this paper, we evaluated the importance of dataset properties, and proposed a novel methodology for learning the effort aware just-in-time defect prediction model. We form an ensemble classifier, which consider the output of three individuals classifier i.e. Random forest, XGBoost and Deep Neural Network. Our proposed methodology shows better performance with 77% accuracy on sample dataset and 81% accuracy on different dataset. |
topic |
deep neural network unlabeled dataset just-in-time defect prediction unsupervised prediction |
url |
http://acs.pollub.pl/pdf/v16n3/1.pdf |
work_keys_str_mv |
AT salehalbahli adeepensemblelearningmethodforeffortawarejustintimedefectprediction AT salehalbahli deepensemblelearningmethodforeffortawarejustintimedefectprediction |
_version_ |
1724518896226009088 |