LDFR: Learning deep feature representation for software defect prediction

Zhou, Xu; Li, Shuai; Xu, Jun; Liu, Jin; Luo, Xiapu; Zhang, Yifeng; Tao, Zhang; Keung, Jacky; Tang, Yutian

doi:10.1016/j.jss.2019.110402

Cited by 53 publications

(25 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• F(C) is a comprehensive measure of change-prone precision and change-prone recall, which is the weighted harmonic mean of these two measures. It can be computed by Formula (12).…”

Section: Performance Measuresmentioning

confidence: 99%

“…In view of this, deep learning becomes an effective choice to improve performance of change‐proneness prediction. The convolutional neural network (CNN) model, which has been used in software defect prediction and provided positive results, is employed 12–15 . The CNN model can mine relationship between adjacent change features, then it further explores relationship between adjacent sets of change features, and at last it utilizes relationship between all the change features to make the final prediction result.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Software change‐proneness prediction based on deep learning

Zhu

Wang

2022

J Software Evolu Process

View full text Add to dashboard Cite

Software change-proneness prediction can help reduce software maintenance costs.Thus, it has drawn the attention of many researchers. In this paper, we propose a CNN (convolutional neural network)-based method for software change-proneness prediction, aiming to utilize the powerful prediction ability to make score of the performance measure higher than other baseline methods. Moreover, to alleviate the effect of the class imbalance problem, resampling methods are employed with the CNN. To validate the performance of the proposed CNN-based method, an empirical study was conducted. The experimental results show that the CNN-based method together with the resampling method performs better than the baseline methods, and the scores of performance measure of CNN with the ROS (random oversampling) method are higher than other method, especially the important performance measure.

show abstract

“…• F(C) is a comprehensive measure of change-prone precision and change-prone recall, which is the weighted harmonic mean of these two measures. It can be computed by Formula (12).…”

Section: Performance Measuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Software change‐proneness prediction based on deep learning

Zhu

Wang

2022

J Software Evolu Process

View full text Add to dashboard Cite

show abstract

“…Another deep learning-based model for defect prediction is proposed in [26]. The training of the neural network utilizes the triplet loss technique and the weighted cross-entropy loss technique.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

A Survey on Software Defect Prediction Using Deep Learning

et al. 2021

View full text Add to dashboard Cite

Defect prediction is one of the key challenges in software development and programming language research for improving software quality and reliability. The problem in this area is to properly identify the defective source code with high accuracy. Developing a fault prediction model is a challenging problem, and many approaches have been proposed throughout history. The recent breakthrough in machine learning technologies, especially the development of deep learning techniques, has led to many problems being solved by these methods. Our survey focuses on the deep learning techniques for defect prediction. We analyse the recent works on the topic, study the methods for automatic learning of the semantic and structural features from the code, discuss the open problems and present the recent trends in the field.

show abstract

“…The first group learns defect feature from traditional software metrics such as object‐oriented design metrics, process metrics, and network metrics. Xu et al 47 proposed a defect prediction model which leveraged a DNN with a new hybrid loss function to learn defect feature representation from CK metrics, process metrics, and network metrics. Yang et al 15 leveraged DBN to generate and integrate advanced features from 14 basic process metrics.…”

Section: Related Workmentioning

confidence: 99%

MPT‐embedding: An unsupervised representation learning of code for software defect prediction

Shi

Liu

Wei

et al. 2020

J Software Evolu Process

View full text Add to dashboard Cite

Software project defect prediction can help developers allocate debugging resources. Existing software defect prediction models are usually based on machine learning methods, especially deep learning. Deep learning‐based methods tend to build end‐to‐end models that directly use source code‐based abstract syntax trees (ASTs) as input. They do not pay enough attention to the front‐end data representation. In this paper, we propose a new framework to represent source code called multiperspective tree embedding (MPT‐embedding), which is an unsupervised representation learning method. MPT‐embedding parses the nodes of ASTs from multiple perspectives and encodes the structural information of a tree into a vector sequence. Experiments on both cross‐project defect prediction (CPDP) and within‐project defect prediction (WPDP) show that, on average, MPT‐embedding provides improvements over the state‐of‐the‐art method.

show abstract

LDFR: Learning deep feature representation for software defect prediction

Cited by 53 publications

References 42 publications

Software change‐proneness prediction based on deep learning

Software change‐proneness prediction based on deep learning

A Survey on Software Defect Prediction Using Deep Learning

MPT‐embedding: An unsupervised representation learning of code for software defect prediction

Contact Info

Product

Resources

About