2019
DOI: 10.2991/ijcis.2018.125905638
|View full text |Cite
|
Sign up to set email alerts
|

An Empirical Study for Enhanced Software Defect Prediction Using a Learning-Based Framework

Abstract: The object of software defect prediction (SDP) is to identify defect-prone modules. This is achieved through constructing prediction models using datasets obtained by mining software historical depositories. However, data mined from these depositories are often associated with high dimensionality, class imbalance, and mislabels which deteriorate classification performance and increase model complexity. In order to mitigate the consequences, this paper proposes an integrated preprocessing framework in which fea… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
6
0

Year Published

2019
2019
2025
2025

Publication Types

Select...
6
1
1

Relationship

1
7

Authors

Journals

citations
Cited by 10 publications
(6 citation statements)
references
References 25 publications
0
6
0
Order By: Relevance
“…Class imbalance in classification models represents those situations where the number of examples of one class is much smaller than others (Bashir et al, 2018). If the model is trained on imbalanced datasets, the prediction results will be biased towards the majority class.…”
Section: Class Imbalance and Sampling Techniquesmentioning
confidence: 99%
“…Class imbalance in classification models represents those situations where the number of examples of one class is much smaller than others (Bashir et al, 2018). If the model is trained on imbalanced datasets, the prediction results will be biased towards the majority class.…”
Section: Class Imbalance and Sampling Techniquesmentioning
confidence: 99%
“…Class imbalance in classification models represents those situations, where the number of examples of one class is much smaller than other classes. The class with the higher size of data is the majority class, while the class with a smaller size is considered as minority class [42]. Class imbalance is an important special of the software defects data, which consists of only a few defective instances and there are large number of non-defective instances.…”
Section: 4class Imbalance and Sampling Techniquesmentioning
confidence: 99%
“…Finding potential defects among millions of code lines and thousands of documents is a difficult task for a software tester [1]. However, finding as many errors as feasible is vital to improving software quality, particularly in some critical scenarios where even a minor undiscovered software failure might have devastating effects [2,3]. Software fault prediction which is entrenched in static code features and can lead engineers to discover problem-prone modules earlier instead of random inspection in the sector has drawn increasing interest from researchers in recent years [4][5][6].…”
Section: Introductionmentioning
confidence: 99%