Software defect prediction based on enhanced metaheuristic feature selection optimization and a hybrid deep neural network
K Zhu, S Ying, N Zhang, D Zhu - Journal of Systems and Software, 2021 - Elsevier
Software defect prediction aims to identify the potential defects of new software modules in
advance by constructing an effective prediction model. However, the model performance is …
advance by constructing an effective prediction model. However, the model performance is …
A bidirectional LSTM language model for code evaluation and repair
MM Rahman, Y Watanobe, K Nakamura - Symmetry, 2021 - mdpi.com
Programming is a vital skill in computer science and engineering-related disciplines.
However, developing source code is an error-prone task. Logical errors in code are …
However, developing source code is an error-prone task. Logical errors in code are …
Learning object material categories via pairwise discriminant analysis
Z Fu, A Robles-Kelly - 2007 IEEE Conference on Computer …, 2007 - ieeexplore.ieee.org
In this paper, we investigate linear discriminant analysis (LDA) methods for multiclass
classification problems in hyperspectral imaging. We note that LDA does not consider …
classification problems in hyperspectral imaging. We note that LDA does not consider …
Predicting vulnerable components: Software metrics vs text mining
J Walden, J Stuckman… - 2014 IEEE 25th …, 2014 - ieeexplore.ieee.org
Building secure software is difficult, time-consuming, and expensive. Prediction models that
identify vulnerability prone software components can be used to focus security efforts, thus …
identify vulnerability prone software components can be used to focus security efforts, thus …
Fine-grained just-in-time defect prediction
Defect prediction models focus on identifying defect-prone code elements, for example to
allow practitioners to allocate testing resources on specific subsystems and to provide …
allow practitioners to allocate testing resources on specific subsystems and to provide …
An improved SDA based defect prediction framework for both within-project and cross-project class-imbalance problems
Background. Solving the class-imbalance problem of within-project software defect
prediction (SDP) is an important research topic. Although some class-imbalance learning …
prediction (SDP) is an important research topic. Although some class-imbalance learning …
Bug characteristics in open source software
To design effective tools for detecting and recovering from software failures requires a deep
understanding of software bug characteristics. We study software bug characteristics by …
understanding of software bug characteristics. We study software bug characteristics by …
Clami: Defect prediction on unlabeled datasets (t)
Defect prediction on new projects or projects with limited historical data is an interesting
problem in software engineering. This is largely because it is difficult to collect defect …
problem in software engineering. This is largely because it is difficult to collect defect …
The impact of feature importance methods on the interpretation of defect classifiers
Classifier specific (CS) and classifier agnostic (CA) feature importance methods are widely
used (often interchangeably) by prior studies to derive feature importance ranks from a …
used (often interchangeably) by prior studies to derive feature importance ranks from a …
Reducing features to improve code change-based bug prediction
S Shivaji, EJ Whitehead, R Akella… - IEEE Transactions on …, 2012 - ieeexplore.ieee.org
Machine learning classifiers have recently emerged as a way to predict the introduction of
bugs in changes made to source code files. The classifier is first trained on software history …
bugs in changes made to source code files. The classifier is first trained on software history …