The Experts below are selected from a list of 187239 Experts worldwide ranked by ideXlab platform
Ying Zou - One of the best experts on this subject based on the ideXlab platform.
-
towards building a Universal defect prediction Model with rank transformed predictors
Empirical Software Engineering, 2016Co-Authors: Feng Zhang, Audris Mockus, Iman Keivanloo, Ying ZouAbstract:Software defects can lead to undesired results. Correcting defects costs 50 % to 75 % of the total software development budgets. To predict defective files, a prediction Model must be built with predictors (e.g., software metrics) obtained from either a project itself (within-project) or from other projects (cross-project). A Universal defect prediction Model that is built from a large set of diverse projects would relieve the need to build and tailor prediction Models for an individual project. A formidable obstacle to build a Universal Model is the variations in the distribution of predictors among projects of diverse contexts (e.g., size and programming language). Hence, we propose to cluster projects based on the similarity of the distribution of predictors, and derive the rank transformations using quantiles of predictors for a cluster. We fit the Universal Model on the transformed data of 1,385 open source projects hosted on SourceForge and GoogleCode. The Universal Model obtains prediction performance comparable to the within-project Models, yields similar results when applied on five external projects (one Apache and four Eclipse projects), and performs similarly among projects with different context factors. At last, we investigate what predictors should be included in the Universal Model. We expect that this work could form a basis for future work on building a Universal Model and would lead to software support tools that incorporate it into a regular development workflow.
-
towards building a Universal defect prediction Model
Mining Software Repositories, 2014Co-Authors: Feng Zhang, Audris Mockus, Iman Keivanloo, Ying ZouAbstract:To predict files with defects, a suitable prediction Model must be built for a software project from either itself (within-project) or other projects (cross-project). 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. A Universal Model could also be interpreted as a basic relationship between software metrics and defects. However, the variations in the distribution of predictors pose a formidable obstacle to build a Universal Model. Such variations exist among projects with different context factors (e.g., size and programming language). To overcome this challenge, we propose context-aware rank transformations for predictors. We cluster projects based on the similarity of the distribution of 26 predictors, and derive the rank transformations using quantiles of predictors for a cluster. We then fit the Universal Model on the transformed data of 1,398 open source projects hosted on SourceForge and GoogleCode. Adding context factors to the Universal Model improves the predictive power. The Universal Model obtains prediction performance comparable to the within-project Models and yields similar results when applied on five external projects (one Apache and four Eclipse projects). These results suggest that a Universal defect prediction Model may be an achievable goal.
Feng Zhang - One of the best experts on this subject based on the ideXlab platform.
-
towards building a Universal defect prediction Model with rank transformed predictors
Empirical Software Engineering, 2016Co-Authors: Feng Zhang, Audris Mockus, Iman Keivanloo, Ying ZouAbstract:Software defects can lead to undesired results. Correcting defects costs 50 % to 75 % of the total software development budgets. To predict defective files, a prediction Model must be built with predictors (e.g., software metrics) obtained from either a project itself (within-project) or from other projects (cross-project). A Universal defect prediction Model that is built from a large set of diverse projects would relieve the need to build and tailor prediction Models for an individual project. A formidable obstacle to build a Universal Model is the variations in the distribution of predictors among projects of diverse contexts (e.g., size and programming language). Hence, we propose to cluster projects based on the similarity of the distribution of predictors, and derive the rank transformations using quantiles of predictors for a cluster. We fit the Universal Model on the transformed data of 1,385 open source projects hosted on SourceForge and GoogleCode. The Universal Model obtains prediction performance comparable to the within-project Models, yields similar results when applied on five external projects (one Apache and four Eclipse projects), and performs similarly among projects with different context factors. At last, we investigate what predictors should be included in the Universal Model. We expect that this work could form a basis for future work on building a Universal Model and would lead to software support tools that incorporate it into a regular development workflow.
-
towards building a Universal defect prediction Model
Mining Software Repositories, 2014Co-Authors: Feng Zhang, Audris Mockus, Iman Keivanloo, Ying ZouAbstract:To predict files with defects, a suitable prediction Model must be built for a software project from either itself (within-project) or other projects (cross-project). 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. A Universal Model could also be interpreted as a basic relationship between software metrics and defects. However, the variations in the distribution of predictors pose a formidable obstacle to build a Universal Model. Such variations exist among projects with different context factors (e.g., size and programming language). To overcome this challenge, we propose context-aware rank transformations for predictors. We cluster projects based on the similarity of the distribution of 26 predictors, and derive the rank transformations using quantiles of predictors for a cluster. We then fit the Universal Model on the transformed data of 1,398 open source projects hosted on SourceForge and GoogleCode. Adding context factors to the Universal Model improves the predictive power. The Universal Model obtains prediction performance comparable to the within-project Models and yields similar results when applied on five external projects (one Apache and four Eclipse projects). These results suggest that a Universal defect prediction Model may be an achievable goal.
Jiří Kučerík - One of the best experts on this subject based on the ideXlab platform.
-
introducing a soil Universal Model method summ and its application for qualitative and quantitative determination of poly ethylene poly styrene poly vinyl chloride and poly ethylene terephthalate microplastics in a Model soil
Chemosphere, 2019Co-Authors: Jan David, Z Steinmetz, Lucie Kabelikova, Michael Scott Demyan, Jana Simeckova, David Tokarski, Helena Doležalová Weissmannová, Gabriele E. Schaumann, Christian Siewert, Jiří KučeríkAbstract:Abstract Methods for analysis of microplastic in soils are still being developed. In this study, we evaluated the potential of a soil Universal Model method (SUMM) based on thermogravimetry (TGA) for the identification and quantification of microplastics in standard loamy sand. Blank and spiked soils (with amounts of one of four microplastic types) were analyzed by TGA. For each sample, thermal mass losses (TML) in 10 °C intervals were extracted and used for further analysis. To explain and demonstrate the principles of SUMM, two scenarios were discussed. The first refers to a rare situation in which an uncontaminated blank of investigated soil is available and TML of spiked and blank soils are subtracted. The results showed that the investigated microplastics degraded in characteristic temperature areas and differences between spiked and blank soils were proportional to the microplastics concentrations. The second scenario reflects the more common situation where the blank is not available and needs to be replaced by the previously developed interrelationships representing soil Universal Models. The Models were consequently subtracted from measured TML. Sparse principal component analysis (sPCA) identified 8 of 14 Modeled differences between measured TMLs and the Universal Model as meaningful for microplastics discrimination. Calibrating various microplastics concentrations with the first principal component extracted from sPCA resulted in linear fits and limits of detection in between environmentally relevant microplastics concentrations. Even if such an approach using calculated standards still has limitations, the SUMM shows a certain potential for a fast pre-screening method for analysis of microplastics in soils.
Iman Keivanloo - One of the best experts on this subject based on the ideXlab platform.
-
towards building a Universal defect prediction Model with rank transformed predictors
Empirical Software Engineering, 2016Co-Authors: Feng Zhang, Audris Mockus, Iman Keivanloo, Ying ZouAbstract:Software defects can lead to undesired results. Correcting defects costs 50 % to 75 % of the total software development budgets. To predict defective files, a prediction Model must be built with predictors (e.g., software metrics) obtained from either a project itself (within-project) or from other projects (cross-project). A Universal defect prediction Model that is built from a large set of diverse projects would relieve the need to build and tailor prediction Models for an individual project. A formidable obstacle to build a Universal Model is the variations in the distribution of predictors among projects of diverse contexts (e.g., size and programming language). Hence, we propose to cluster projects based on the similarity of the distribution of predictors, and derive the rank transformations using quantiles of predictors for a cluster. We fit the Universal Model on the transformed data of 1,385 open source projects hosted on SourceForge and GoogleCode. The Universal Model obtains prediction performance comparable to the within-project Models, yields similar results when applied on five external projects (one Apache and four Eclipse projects), and performs similarly among projects with different context factors. At last, we investigate what predictors should be included in the Universal Model. We expect that this work could form a basis for future work on building a Universal Model and would lead to software support tools that incorporate it into a regular development workflow.
-
towards building a Universal defect prediction Model
Mining Software Repositories, 2014Co-Authors: Feng Zhang, Audris Mockus, Iman Keivanloo, Ying ZouAbstract:To predict files with defects, a suitable prediction Model must be built for a software project from either itself (within-project) or other projects (cross-project). 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. A Universal Model could also be interpreted as a basic relationship between software metrics and defects. However, the variations in the distribution of predictors pose a formidable obstacle to build a Universal Model. Such variations exist among projects with different context factors (e.g., size and programming language). To overcome this challenge, we propose context-aware rank transformations for predictors. We cluster projects based on the similarity of the distribution of 26 predictors, and derive the rank transformations using quantiles of predictors for a cluster. We then fit the Universal Model on the transformed data of 1,398 open source projects hosted on SourceForge and GoogleCode. Adding context factors to the Universal Model improves the predictive power. The Universal Model obtains prediction performance comparable to the within-project Models and yields similar results when applied on five external projects (one Apache and four Eclipse projects). These results suggest that a Universal defect prediction Model may be an achievable goal.
Audris Mockus - One of the best experts on this subject based on the ideXlab platform.
-
towards building a Universal defect prediction Model with rank transformed predictors
Empirical Software Engineering, 2016Co-Authors: Feng Zhang, Audris Mockus, Iman Keivanloo, Ying ZouAbstract:Software defects can lead to undesired results. Correcting defects costs 50 % to 75 % of the total software development budgets. To predict defective files, a prediction Model must be built with predictors (e.g., software metrics) obtained from either a project itself (within-project) or from other projects (cross-project). A Universal defect prediction Model that is built from a large set of diverse projects would relieve the need to build and tailor prediction Models for an individual project. A formidable obstacle to build a Universal Model is the variations in the distribution of predictors among projects of diverse contexts (e.g., size and programming language). Hence, we propose to cluster projects based on the similarity of the distribution of predictors, and derive the rank transformations using quantiles of predictors for a cluster. We fit the Universal Model on the transformed data of 1,385 open source projects hosted on SourceForge and GoogleCode. The Universal Model obtains prediction performance comparable to the within-project Models, yields similar results when applied on five external projects (one Apache and four Eclipse projects), and performs similarly among projects with different context factors. At last, we investigate what predictors should be included in the Universal Model. We expect that this work could form a basis for future work on building a Universal Model and would lead to software support tools that incorporate it into a regular development workflow.
-
towards building a Universal defect prediction Model
Mining Software Repositories, 2014Co-Authors: Feng Zhang, Audris Mockus, Iman Keivanloo, Ying ZouAbstract:To predict files with defects, a suitable prediction Model must be built for a software project from either itself (within-project) or other projects (cross-project). 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. A Universal Model could also be interpreted as a basic relationship between software metrics and defects. However, the variations in the distribution of predictors pose a formidable obstacle to build a Universal Model. Such variations exist among projects with different context factors (e.g., size and programming language). To overcome this challenge, we propose context-aware rank transformations for predictors. We cluster projects based on the similarity of the distribution of 26 predictors, and derive the rank transformations using quantiles of predictors for a cluster. We then fit the Universal Model on the transformed data of 1,398 open source projects hosted on SourceForge and GoogleCode. Adding context factors to the Universal Model improves the predictive power. The Universal Model obtains prediction performance comparable to the within-project Models and yields similar results when applied on five external projects (one Apache and four Eclipse projects). These results suggest that a Universal defect prediction Model may be an achievable goal.
