7,740 Hits in 7.3 sec

Towards building a universal defect prediction model

Feng Zhang, Audris Mockus, Iman Keivanloo, Ying Zou
2014 Proceedings of the 11th Working Conference on Mining Software Repositories - MSR 2014  
A universal defect prediction model that is built from the entire set of diverse projects would relieve the need for building models for an individual project.  ...  However, the variations in the distribution of predictors pose a formidable obstacle to build a universal model.  ...  The authors would also like to thank Professor Daniel German from University of Victoria for his insightful advice.  ... 
doi:10.1145/2597073.2597078 dblp:conf/msr/0001MKZ14 fatcat:xspbyv43urfg7eg4hbhtda22wu

Guest editorial: mining software repositories

Martin Pinzger, Sunghun Kim
2016 Empirical Software Engineering  
In the paper "Studying Just-In-Time Defect Prediction Using Cross-Project Models" by Kamei, Fukushima, McIntosh, Yamashita, Ubayashi, and Hassan, the cold start problem  ...  Some commonly explored areas include software evolution, models of software development processes, characterization of developers and their activities, prediction of future software qualities, use of machine  ...  We also thank the authors for keeping up with the review schedule and the reviewers for their detailed and constructive comments which helped to shape the papers.  ... 
doi:10.1007/s10664-016-9450-8 fatcat:yu2pzpbdp5gbhjnw67i3om56cy

Data Mining Static Code Attributes to Learn Defect Predictors

Tim Menzies, Jeremy Greenwald, Art Frank
2007 IEEE Transactions on Software Engineering  
Also, contrary to prior pessimism, we show that such defect predictors are demonstrably useful and, on the data studied here, yield predictors with a mean probability of detection of 71 percent and mean  ...  The value of using static code attributes to learn defect predictors has been widely debated.  ...  ACKNOWLEDGMENTS The research described in this paper was carried out at West Virginia University and Portland State University under contracts and subcontracts with NASA's Software Assurance Research Program  ... 
doi:10.1109/tse.2007.256941 fatcat:rnyudvlthrejna4prmup6eqxzq

Bellwethers: A Baseline Method For Transfer Learning [article]

Rahul Krishna, Tim Menzies
2018 arXiv   pre-print
Software analytics builds quality prediction models for software projects.  ...  Further, bellwethers appear in many SE tasks such as defect prediction, effort estimation, and bad smell detection.  ...  They used a Markov model with a kNN-based classifier to perform their prediction.  ... 
arXiv:1703.06218v4 fatcat:dxjlgluvkncy3lqvctrtnuvlmm

A General Software Defect-Proneness Prediction Framework

Qinbao Song, Zihan Jia, Martin Shepperd, Shi Ying, Jin Liu
2011 IEEE Transactions on Software Engineering  
The defect predictor builds models according to the evaluated learning scheme and predicts software defects with new data according to the constructed model.  ...  BACKGROUND -predicting defect-prone software components is an economically important activity and so has received a good deal of attention.  ...  That is, we build a predictive model according to a scheme with only 'historical' data and validate the model on the independent 'new' data.  ... 
doi:10.1109/tse.2010.90 fatcat:5fvmbkzhgzcmfpc7dhk2ueclt4

An empirical study on software defect prediction with a simplified metric set

Peng He, Bing Li, Xiao Liu, Jun Chen, Yutao Ma
2015 Information and Software Technology  
The objective of this work is to validate the feasibility of the predictor built with a simplified metric set for software defect prediction in different scenarios, and to investigate practical guidelines  ...  Software defect prediction plays a crucial role in estimating the most defect-prone components of software, and a large number of studies have pursued improving prediction accuracy within a project or  ...  In other words, can we find a universal predictor built with few metrics (e.g., Lines of Code (LOC)) that achieves an acceptable result compared with those complex prediction models?  ... 
doi:10.1016/j.infsof.2014.11.006 fatcat:wq6dgwcnjnantn5it62zvyltfa

Participative Mechanisms to Improve Office Maintenance Performance and Customers' Satisfaction

Cheong Peng Au-Yong
2017 Figshare  
regression model for prediction purpose.  ...  Buildings can be poorly maintained due to lack of understanding towards the role of building maintenance in achieving organisation's objective and long-term profitability.  ...  Table 4 : Criteria of the significant predictor to be concerned A case study was obtained from one of the interviewees to compare with the predication model.  ... 
doi:10.6084/m9.figshare.5220745 fatcat:qdf4xmhgl5aspbskbuwpglotrm

Participative Mechanisms to Improve Office Maintenance Performance and Customer Satisfaction

Cheong Peng Au-Yong, Azlan Shah Ali, Faizah Ahmad
2015 Journal of performance of constructed facilities  
Then, a prediction model generated through SPSS revealed that the provision of knowledge-sharing and communication platform is the most significant predictor of the downtime variance.  ...  regression model for prediction purpose.  ...  Table 4 : Criteria of the significant predictor to be concerned A case study was obtained from one of the interviewees to compare with the predication model.  ... 
doi:10.1061/(asce)cf.1943-5509.0000609 fatcat:ohqb3fsyejd35bze5v2kxxhu5q

TDSelector: A Training Data Selection Method for Cross-Project Defect Prediction [article]

Peng He, Yutao Ma, Bing Li
2016 arXiv   pre-print
In recent years, cross-project defect prediction (CPDP) attracted much attention and has been validated as a feasible way to address the problem of local data sparsity in newly created or inactive software  ...  Besides, an additional experiment shows that selecting those instances with more bugs directly as training data can further improve the performance of the bug predictor trained by our method.  ...  [12] proposed a cross-company defect prediction approach using defect data from other companies to build predictors for target projects.  ... 
arXiv:1612.09065v1 fatcat:7eqyje4gvbffjktnqrevnmgnfy

Special issue on repeatable results in software engineering prediction

Tim Menzies, Martin Shepperd
2012 Empirical Software Engineering  
-Kitchenham et al. (2007) reviewed empirical studies that checked, if data imported from other organizations were as useful as local data (for the purposes of building effort models).  ...  From a total of seven studies, three found that models from other organizations were not significantly worse than those based on local data, while four found that they were significantly different (and  ...  - Zimmermann et al. (2009) learned defect predictors from 622 pairs of projects project 1 , project 2 . In only 4% of pairs did defect predictors learned in project 1 worked in project 2 .  ... 
doi:10.1007/s10664-011-9193-5 fatcat:4bj2qreoobc7ro3natu7jg3gra

Cross-Validation-Based Association Rule Prioritization Metric for Software Defect Characterization

Takashi WATANABE, Akito MONDEN, Zeynep YÜCEL, Yasutaka KAMEI, Shuji MORISAKI
2018 IEICE transactions on information and systems  
This paper proposes a cross-validation -based metric that quantifies the predictive power of such rules for characterizing software defects.  ...  their predictive power.  ...  We should note that, although moving toward higher rule ranks along the x-axis should lead to higher SumNormPre values, there is a small decline at around a rank of 90 in Fig. 3 -b.  ... 
doi:10.1587/transinf.2018edp7020 fatcat:rnyfewgl5rd6dfkhi2pig3xswu

Predicting the postoperative blood coagulation state of children with congenital heart disease by machine learning based on real-world data

Kai Guo, Xiaoyan Fu, Huimin Zhang, Mengjian Wang, Songlin Hong, Shuxuan Ma
2021 Translational Pediatrics  
Subsequently, we furtherly build improved models. Among them, the true positive rate of the AdaBoost, Random Forest and SVM prediction models reached more than 80% in the ROC curve.  ...  These overall accuracy rate indicated a good classification model.  ...  Acknowledgments We acknowledge colleagues from F&E Data Technology (Tianjin) Corporation for providing technical support in machine learning model building.  ... 
doi:10.21037/tp-20-238 pmid:33633935 pmcid:PMC7882284 fatcat:udjk3ke3rjet3ptjj62xiiwr4q

Using In-Process Testing Metrics to Estimate Post-Release Field Quality

Nachiappan Nagappan, Laurie Williams, Mladen Vouk, Jason Osborne
2007 The 18th IEEE International Symposium on Software Reliability (ISSRE '07)  
We built and validated a prediction model using the STREW-J metrics via a three-phase case study approach which progressively involved 22 small-scale academic projects, 27 medium-sized open source projects  ...  The ability of the STREW-J metric suite to estimate post-release field quality via a statistical regression model was evaluated in the three different environments.  ...  Model Building This section describes the model building strategies that were used for predicting post-release field quality.  ... 
doi:10.1109/issre.2007.18 dblp:conf/issre/NagappanWVO07 fatcat:7wpyr7tz4fdwnikazntt36pvgm

A Systematic Literature Review and Meta-Analysis on Cross Project Defect Prediction

Seyedrebvar Hosseini, Burak Turhan, Dimuthu Gunarathna
2017 IEEE Transactions on Software Engineering  
Cross project defect prediction (CPDP) recently gained considerable attention, yet there are no systematic efforts to analyse existing empirical evidence.  ...  Objective: To synthesise literature to understand the state-of-the-art in CPDP with respect to metrics, models, data approaches, datasets and associated performances.  ...  The universal defect prediction model proposed by Zhang et al. [S40] offers a context-aware rank transformation to address the difference in the distribution of the data.  ... 
doi:10.1109/tse.2017.2770124 fatcat:puodxjkkdjglpdxynaktjiycpu

Software defect prediction based on stacked sparse denoising autoencoders and enhanced extreme learning machine

Nana Zhang, Shi Ying, Kun Zhu, Dandan Zhu
2021 IET Software  
The SSDAE is compared with eleven state-of-the-art feature extraction methods in effect and efficiency, and the SSEPG model is compared with multiple baseline models that contain five classic defect predictors  ...  To address these two issues, a novel defect prediction model called SSEPG based on Stacked Sparse Denoising AutoEncoders (SSDAE) and Extreme Learning Maching (ELM) optimised by Particle Swarm Optimisation  ...  In RQ3 and RQ4, our SSEPG model can achieve the optimal prediction performance compared with five classic defect predictors and three variants.  ... 
doi:10.1049/sfw2.12029 fatcat:225jhgnn6nebra7fh6fxcucqpe
« Previous Showing results 1 — 15 out of 7,740 results