An empirical analysis of software effort estimation with outlier elimination

Seo, Yeong-Seok; Yoon, Kyung-A; Bae, Doo‐Hwan

doi:10.1145/1370788.1370796

Cited by 41 publications

(35 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The literature shows that SEE data sets frequently have a few outliers, which may hinder the SEEs for future projects [27]. In the current work, outliers were detected using kmeans.…”

Section: Outliersmentioning

confidence: 82%

“…In the current work, outliers were detected using kmeans. This method was chosen because it has shown to improve performance in the SEE context [27]. K-means is used to divide the projects into clusters.…”

Section: Outliersmentioning

confidence: 99%

“…We used n = 3, as in [27]. The number of clusters k was chosen among k = {2, 3, 4, 5}, according to the average silhouette values.…”

Section: Outliersmentioning

confidence: 99%

See 2 more Smart Citations

A principled evaluation of ensembles of learning machines for software effort estimation

Minku

Yao

2011

Proceedings of the 7th International Conference on Predictive Models in Software Engineering

View full text Add to dashboard Cite

Background: Software effort estimation (SEE) is a task of strategic importance in software management. Recently, some studies have attempted to use ensembles of learning machines for this task. Aims: We aim at (1) evaluating whether readily available ensemble methods generally improve SEE given by single learning machines and which of them would be more useful; getting insight on (2) how to improve SEE; and (3) how to choose machine learning (ML) models for SEE. Method: A principled and comprehensive statistical comparison of three ensemble methods and three single learners was carried out using thirteen data sets. Feature selection and ensemble diversity analyses were performed to gain insight on how to improve SEE based on the approaches singled out. In addition, a risk analysis was performed to investigate the robustness to outliers. Therefore, the better understanding/insight provided by the paper is based on principled experiments, not just an intuition or speculation. Results: None of the compared methods is consistently the best, even though regression trees and bagging using multilayer perceptrons (MLPs) are more frequently among the best. These two approaches usually perform similarly. Regression trees place more important features in higher levels of the trees, suggesting that feature weights are important when using ML models for SEE. The analysis of bagging with MLPs suggests that a self-tuning ensemble diversity method may help improving SEE. Conclusions: Ideally, principled experiments should be done in an individual basis to choose a model. If an organisation has no resources for that, regression trees seem to be a good choice for its simplicity. The analysis also suggests approaches to improve SEE.

show abstract

“…The literature shows that SEE data sets frequently have a few outliers, which may hinder the SEEs for future projects [27]. In the current work, outliers were detected using kmeans.…”

Section: Outliersmentioning

confidence: 82%

Section: Outliersmentioning

confidence: 99%

See 1 more Smart Citation

A principled evaluation of ensembles of learning machines for software effort estimation

Minku

Yao

2011

Proceedings of the 7th International Conference on Predictive Models in Software Engineering

View full text Add to dashboard Cite

show abstract

“…A past project dataset sometimes includes project data which should not be used for estimation [25]. For example, projects where an exceptional amount of rework occurred have a larger effort than other projects of the same scale (atypical cases).…”

Section: Introductionmentioning

confidence: 99%

“…Cook's distance is widely used as an outlier deletion method when applying linear regression analysis. In addition to Cook's distance, some outlier deletion methods for effort estimation [5][15] [25] have been proposed. However, there are few case studies which apply outlier deletion methods to analogy-based estimation and compare their effects on analogy-based estimation.…”

Section: Introductionmentioning

confidence: 99%

An empirical evaluation of outlier deletion methods for analogy-based cost estimation

Tsunoda

Kakimoto

Monden

et al. 2011

Proceedings of the 7th International Conference on Predictive Models in Software Engineering

View full text Add to dashboard Cite

Background: Any software project dataset sometimes includes outliers which affect the accuracy of effort estimation. Outlier deletion methods are often used to eliminate them. However, there are few case studies which apply outlier deletion methods to analogy-based estimation, so it is not clear which method is more suitable for analogy-based estimation. Aim: Clarifying the effects of existing outlier deletion methods (Cook's distance based deletion, LTS based deletion, k-means based deletion, Mantel's correlation based deletion, and EID based deletion) and our method for analogy-based estimation. Method: In the experiment, outlier deletion methods were applied to three kinds of datasets (the ISBSG, Kitchenham, and Desharnais datasets), and their estimation accuracy evaluated based on BRE (Balanced Relative Error). Our method eliminates outliers from the neighborhoods of a target project when the effort is extremely different from other neighborhoods. Results: Deletion methods which are designed to apply to analogy-based estimation (i.e. Mantel's correlation based deletion, EID based deletion, and our method) showed stable performance. Especially, only our method showed over 10% improvement of the average BRE on two datasets. Conclusions: It is reasonable to apply deletion methods designed for analogy-based estimation, and more preferable to apply our method to analogybased estimation.

show abstract

Synthesis and Biological Evaluation of 1‐Phenyl‐1,2,3,4‐dihydroisoquinoline Compounds as Tubulin Polymerization Inhibitors

Zheng¹,

Liu²,

Zhou³

et al. 2012

Archiv der Pharmazie

View full text Add to dashboard Cite

A series of 1-phenyl-3,4-dihydroisoquinoline derivatives and several 1-phenyl-1,2,3,4-tetrahydroisoquinoline, 1-phenyl-isoquinoline analogues were synthesized, and their cytotoxicity and tubulin polymerization inhibitory activity were evaluated. The 1-phenyl-3,4-dihydroisoquinoline compounds were found to be potential tubulin polymerization inhibitors. Compound 5n, bearing a 3'-OH and 4'-OCH(3) substituted 1-phenyl B-ring, was shown to confer optimal bioactivity. The single-crystal structure of 5n was further determined by X-ray diffraction, and the binding mode of 5n to tubulin was obtained by molecular docking, which can explain the structure-activity relationships. The studies presented here provide a new structural type for the development of novel antitumor agents.

show abstract

An empirical analysis of software effort estimation with outlier elimination

Cited by 41 publications

References 17 publications

A principled evaluation of ensembles of learning machines for software effort estimation

A principled evaluation of ensembles of learning machines for software effort estimation

An empirical evaluation of outlier deletion methods for analogy-based cost estimation

Synthesis and Biological Evaluation of 1‐Phenyl‐1,2,3,4‐dihydroisoquinoline Compounds as Tubulin Polymerization Inhibitors

Contact Info

Product

Resources

About