Research on Cross-version Software Defect Prediction Based on Evolutionary Information

Yao, Zhexi; Song, Jian; Liu, Yushuai; Zhang, Tao; Wang, Jinbo

doi:10.1088/1757-899x/563/5/052092

Cited by 4 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, 40 different real‐world software defect datasets available in the Tera‐PROMISE repository (PROMISE Software Engineering Repository, 2015) for public use were selected to demonstrate the generalization abilities and prediction performances of the proposed MVOC models. A software metric, often known as a feature, is an indicator or parameter that indicates the qualities of a software product (Yao et al, 2019). Metrics can be divided into two types: static and dynamic metrics.…”

Section: Methodsmentioning

confidence: 99%

A novel multi‐view ordinal classification approach for software bug prediction

Taşer

2022

Expert Systems

View full text Add to dashboard Cite

Software bug prediction aims to enhance software quality and testing efficiency by constructing predictive classification models using code properties. This enables the prompt detection of fault‐prone modules. There are several machine learning‐based software bug prediction studies, which mainly focus on single view data by disregarding the natural ordering relation among the class labels in the literature. Thus, these studies cause losing each view's own intrinsic structure and the inherent order of the labels that positively affect the prediction performance. To overcome this drawback, this study focuses on integrating ordering information and a multi‐view learning strategy. This paper proposes a novel approach multi‐view ordinal classification (MVOC), which learns from different views (complexity, coupling, cohesion, inheritance and scale) of the software dataset separately and predicts software bugs taking the inherent order of class labels (non‐buggy, less buggy and more buggy) into consideration. To demonstrate its prediction performance, the MVOC approach was executed on the 40 different real‐world software datasets using six different classification algorithms as base learners. In the experiments, the MVOC approach was compared with traditional classifiers and their multi‐view implementations in terms of precision, recall, f‐measure and accuracy rate metrics. The results indicate that the MVOC approach presents better prediction performance on average than the multi‐view‐based and traditional classifiers. It is also observed from the results that the MVOC.RF model achieved the highest classification performance with an average accuracy rate of 85.65%.

show abstract

Section: Methodsmentioning

confidence: 99%

A novel multi‐view ordinal classification approach for software bug prediction

Taşer

2022

Expert Systems

View full text Add to dashboard Cite

show abstract

“…They conducted experiments on 32 releases of 45 software projects and observed the satisfied defect prediction performance. Yao et al [108] proposed transition class ratio and static metric category number evaluation metrics for defect prediction among the releases. The experimental study was conducted on 36 releases of 10 open-source software projects.…”

Section: Related Workmentioning

confidence: 99%

Inter-release defect prediction with feature selection using temporal chunk-based learning: An empirical study

Kabir

Keung

Turhan

et al. 2021

Applied Soft Computing

View full text Add to dashboard Cite

“…Each dataset consists of 20 independent object-oriented software metrics and one dependent defect variable that indicates the source code is buggy or not. As explained in the previous study [49], each dataset contains code metrics that indicate the characteristics of cohesion, complexity, coupling, scale, and inheritance features in software programs. Therefore, each dataset has five views.…”

Section: Spectf Heart Dataset: 5 This Dataset Contains Diagnosing Of mentioning

confidence: 99%

An improved version of multi-view k-nearest neighbors (MVKNN) for multiple view learning

Kiyak¹,

Birant²,

Birant³

2021

Turkish Journal of Electrical Engineering and Computer Sciences

View full text Add to dashboard Cite

Multi-view learning (MVL) is a special type of machine learning that utilizes more than one views, where views include various descriptions of a given sample. Traditionally, classification algorithms such as k-nearest neighbors (KNN) are designed for learning from single-view data. However, many real-world applications involve datasets with multiple views and each view may contain different and partly independent information, which makes the traditional single-view classification approaches ineffective. Therefore, this article proposes an improved MVL algorithm, called Multi-View K-Nearest Neighbors (MVKNN), based on the existing KNN algorithm. The experimental results conducted in this research show that a significant improvement is achieved by the proposed MVKNN algorithm compared to the well-known machine learning algorithms (KNN, support vector machine, decision tree, and Naive Bayes) in the case of multi-view data. The results also show that our method outperforms the state-of-the-art multi-view learning methods in terms of accuracy.

show abstract

Research on Cross-version Software Defect Prediction Based on Evolutionary Information

Cited by 4 publications

References 5 publications

A novel multi‐view ordinal classification approach for software bug prediction

A novel multi‐view ordinal classification approach for software bug prediction

Inter-release defect prediction with feature selection using temporal chunk-based learning: An empirical study

An improved version of multi-view k-nearest neighbors (MVKNN) for multiple view learning

Contact Info

Product

Resources

About