12,308 Hits in 5.8 sec

Defect Prediction Technology of Aerospace Software Based on Deep Neural Network and Process Measurement

Tianwen Yao, Ben Zhang, Jun Peng, Zhiqiang Han, Zhaobing Yang, Zhi Zhang, Bo Zhang, Antonio M. Gonçalves de Lima
2022 Mathematical Problems in Engineering  
Therefore, this paper proposed a software defect prediction method based on deep neural network and process measurement.  ...  Based on the NASA data set and combined with the software process data, the software defect measurement set is constructed. 35 measurement elements are used as the original input, and multiple single-layer  ...  [8] used active learning to build a defect prediction model.  ... 
doi:10.1155/2022/1276830 fatcat:gr4nhvyzzzey3k6wcno2sthnsu

Cross-version defect prediction via hybrid active learning with kernel principal component analysis

Zhou Xu, Jin Liu, Xiapu Luo, Tao Zhang
2018 2018 IEEE 25th International Conference on Software Analysis, Evolution and Reengineering (SANER)  
, i.e., Cross-Version Defect Prediction (CVDP).  ...  As defects in software modules may cause product failure and financial loss, it is critical to utilize defect prediction methods to effectively identify the potentially defective modules for a thorough  ...  They used an uncertainty based Active Learning method to select the candidate modules after performing a dimensionality reduction with MDS. We name this method as MDSAL.  ... 
doi:10.1109/saner.2018.8330210 dblp:conf/wcre/XuLLZ18 fatcat:ykk6t52qvbc2fhgbkefron2rom

Defect Prediction Leads to High Quality Product

Naheed Azeem, Shazia Usmani
2011 Journal of Software Engineering and Applications  
So, defect prediction is very important in the field of software quality and software reliability. This paper gives you a vivid description about software defect prediction.  ...  Defect prediction is relatively a new research area of software quality assurance. A project team always aims to produce a quality product with zero or few defects.  ...  Reduction in the false alarm is done by a two-dimensional ROC analysis. The author changed the decision threshold on Naïve Bayes and observed the changes in prediction performance measures.  ... 
doi:10.4236/jsea.2011.411075 fatcat:4myguuo6gngzfczxm6je4snxy4

Using Source Code and Process Metrics for Defect Prediction - A Case Study of Three Algorithms and Dimensionality Reduction

Wenjing Han, Chung-Horng Lung, Samuel Ajila
2016 Journal of Software  
Software defect prediction is very important in helping the software development team allocate test resource efficiently and better understand the root cause of defects.  ...  The evaluation of variable importance allows for the reduction of data size and saves computational cost, and also identifies key features for defect prediction.  ...  Acknowledgment This research is partly sponsored by two research grants (Engage and Discovery grants) from the Natural Sciences and Engineering Research Council of Canada (NSERC).  ... 
doi:10.17706/jsw.11.9.883-902 fatcat:4xxeaepxdzgzjpevqmh7yzih64

Towards Predicting Software Defects with Clustering Techniques

Waheeda Almayyan
2021 International Journal of Artificial Intelligence & Applications  
Our aim was to evaluate the performance of clustering techniques with feature selection schemes to address the problem of software defect prediction problem.  ...  The purpose of software defect prediction is to improve the quality of a software project by building a predictive model to decide whether a software module is or is not fault prone.  ...  Therefore, the software defect prediction process becomes an essential part of improving software reliability and predicting the potential defects during the early stages of any software development lifecycle  ... 
doi:10.5121/ijaia.2021.12103 fatcat:cnozclryubfd7lcaqwm6g2nxc4

A Novel Multiple Ensemble Learning Models Based on Different Datasets for Software Defect Prediction [article]

Ali Nawaz, Attique Ur Rehman, Muhammad Abbas
2020 arXiv   pre-print
More the defects found in the software ensure more efficiency is the software testing Different techniques have been proposed to detect the defects in software and to utilize the resources and achieve  ...  This reveals that Ensemble is more efficient method for making the defect prediction as compared other techniques.  ...  [18] proposed a software defect prediction approach in which firstly they perform dimensionality reduction via Principle Component Analysis (PCA), a most famous dimensionality reduction approach and  ... 
arXiv:2008.13114v1 fatcat:boi5w4h5cjg3bmp6wnqf4qjjaq

Using Deep Image Colorization to Predict Microstructure-Dependent Strain Fields

Pranav Milind Khanolkar, Aaron Abraham, Christopher McComb, Saurabh Basu
2020 Procedia Manufacturing  
This research proposes the use of Deep Learning algorithms to achieve a significant reduction in the time required to predict high-accuracy strain fields in a two-dimensional microstructure with defects  ...  This research proposes the use of Deep Learning algorithms to achieve a significant reduction in the time required to predict high-accuracy strain fields in a two-dimensional microstructure with defects  ...  Any opinions, findings, conclusions or recommendations expressed in this material are those of the authors and do not necessarily reflect the views of the National Science Foundation.  ... 
doi:10.1016/j.promfg.2020.05.138 fatcat:fw342htd7bdujdf2mb4zupcezu

CDS: A Cross–Version Software Defect Prediction Model with Data Selection

Jie Zhang, Jiajing Wu, Chuan Chen, Zibin Zheng, Michael R. Lyu
2020 IEEE Access  
Lu et al. noticed that the data distribution can differ from version to version, and integrated the method of active learning and dimensionality reduction to address this issue [11] .  ...  We propose a Cross-version defect prediction model with Data Selection (CDS) to address the version selection problem by learning a proper weight for each version and predict the labels of the current  ... 
doi:10.1109/access.2020.3001440 fatcat:u4puqru2knah3i6sdmsosx42ya

Active Learning using Uncertainty Sampling and Query-by-Committee for Software Defect Prediction

Qu Yubin, Chen Xiang, Chen Ruijie, Ju Xiaolin, Guo Jiangfeng
2019 International Journal of Performability Engineering  
In the process of software defect prediction dataset construction, there are problems such as high labeling costs. Active learning can reduce labeling costs when using uncertainty sampling.  ...  Therefore, a hybrid active learning query strategy is proposed. For the sample with lowest information entropy, query-by-committee will analyze it again using vote entropy.  ...  Acknowledgements This work was supported by the Nantong Science and Technology Project (No. JC2018134).  ... 
doi:10.23940/ijpe.19.10.p16.27012708 fatcat:ekgu2sciwvghdlcgfocumd2qku

Software Defect Prediction Using Non-Negative Matrix Factorization

Rui Hua Chang, Xiao Dong Mu, Li Zhang
2011 Journal of Software  
However, building quality software is very expensive, in order to raise the effectiveness and efficiency of quality assurance and testing, software defect prediction is used to identify defect-prone modules  ...  in an upcoming version of a software system and help to allow the effort on those modules.  ...  ACKNOWLEDGMENT The authors would like to thank the anonymous reviewers and the editor for their constructive evaluation of this paper.  ... 
doi:10.4304/jsw.6.11.2114-2120 fatcat:lximoxvdnzf65hw74qdblu5mwq

Weighted software metrics aggregation and its application to defect prediction

Maria Ulan, Welf Löwe, Morgan Ericsson, Anna Wingkvist
2021 Empirical Software Engineering  
To evaluate the effectiveness, we conducted two empirical studies on defect prediction, one on ca. 200 000 code changes, and another ca. 5 000 software classes.  ...  We propose an automated approach to weighted metrics aggregation that is based on unsupervised learning. It sets metrics scores and their weights based on probability theory and aggregates them.  ...  We are also grateful to the authors (Fu and Menzies 2017) , who made their well-packaged and well-documented software available for others 18 .  ... 
doi:10.1007/s10664-021-09984-2 fatcat:cij67aaxgzfulddj3jmqmsobea

Software Defect Prediction Based on Elman Neural Network and Cuckoo Search Algorithm

Kun Song, ShengKai Lv, Die Hu, Peng He, Yun-Wen Feng
2021 Mathematical Problems in Engineering  
In software engineering, defect prediction is significantly important and challenging. The main task is to predict the defect proneness of the modules.  ...  The F-measure values are generally increased with a maximum growth rate of 49.5% for the POI project.  ...  e Advantage of Cs-Enn Compared with the Baselines. We compared the performance of software defect prediction between the improved Elman neural network classifier and the general classifiers.  ... 
doi:10.1155/2021/5954432 fatcat:mf2ltw2nyrc75i23ux53hoydcq

ALTRA: Cross-project Software Defect Prediction via Active Learning and TrAdaBoost

Zhidan Yuan, Xiang Chen, Zhanqi Cui, Yanzhou Mu
2020 IEEE Access  
INDEX TERMS Cross-project defect prediction, active learning, TrAdaBoost, Burak Filter, empirical study.  ...  In these new target projects, we can easily extract and then measure these modules with software measurement tools.  ...  They considered both active learning and feature compression techniques (i.e., feature selection techniques and dimensionality reduction techniques). For the cross-version defect prediction, Xu et al.  ... 
doi:10.1109/access.2020.2972644 fatcat:fjw4jsvlvnhixj3t5drjunjt5e

Defect Identification, Categorization, and Repair: Better Together [article]

Chao Ni, Kaiwen Yang, Xin Xia, David Lo, Xiang Chen, Xiaohu Yang
2022 arXiv   pre-print
The whole input of CompDefect consists of three parts (exampled with positive functions): the clean version of a function (i.e., the version before defect introduced), the buggy version of a function and  ...  In multiclass classification task, CompDefect categorizes the type of defect via multiclass classification with the information in both the clean version and the buggy version.  ...  ., function-level software defect prediction and defect repair), we think the two tasks are equivalently important.  ... 
arXiv:2204.04856v1 fatcat:ke7ug6epi5aplgm74t4dzyvot4

Best Suited Machine Learning Techniques for Software Fault Prediction

2020 International journal of recent technology and engineering  
Machine learning techniques for both classification and determination are used for the purpose of software fault prediction.  ...  The software fault prediction model will first train the learning techniques to generate base learners and then apply these base learners to unseen projects.  ...  Software release of previous version of software along with software Revised Manuscript Received on February 01, 2020. * Correspondence Author Devika S, department of Computer Science and Engineering,  ... 
doi:10.35940/ijrte.f9456.038620 fatcat:4bxbol7ux5dwna55q7ep6w5e2y
« Previous Showing results 1 — 15 out of 12,308 results