東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Improve Software Defect Estimation w...

Almakadmeh, Mhammed.

FindBook

Google Book

Amazon

博客來

Improve Software Defect Estimation with Six Sigma Defect Measures: Empirical Studies with Imputation Techniques on ISBSG Data Repository with a High Ratio of Missing Data.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Improve Software Defect Estimation with Six Sigma Defect Measures: Empirical Studies with Imputation Techniques on ISBSG Data Repository with a High Ratio of Missing Data./
作者:	Almakadmeh, Mhammed.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2017,
面頁冊數:	230 p.
附註:	Source: Dissertations Abstracts International, Volume: 79-10, Section: B.
Contained By:	Dissertations Abstracts International79-10B.
標題:	Computer Engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10751452
ISBN:	9780355798777

Improve Software Defect Estimation with Six Sigma Defect Measures: Empirical Studies with Imputation Techniques on ISBSG Data Repository with a High Ratio of Missing Data.
Almakadmeh, Mhammed.

Improve Software Defect Estimation with Six Sigma Defect Measures: Empirical Studies with Imputation Techniques on ISBSG Data Repository with a High Ratio of Missing Data. - Ann Arbor : ProQuest Dissertations & Theses, 2017 - 230 p.

Source: Dissertations Abstracts International, Volume: 79-10, Section: B.

Thesis (Ph.D.)--Ecole de Technologie Superieure (Canada), 2017.

This item must not be added to any third party search indexes.

This research analysis work reports on a set of empirical studies tackling the research issues of improving software defect estimation models with Sigma defect measures (e.g., Sigma levels) using the ISBSG data repository with a high ratio of missing data. Three imputation techniques that were selected for this research work: single imputation, regression imputation, and stochastic regression imputation. These imputation techniques were used to impute the missing data within the variable 'Total Number of Defects', and were first compared with each other using common verification criteria. A further verification strategy was developed to compare and assess the performance of the selected imputation techniques through verifying the predictive accuracy of the obtained software defect estimation models form the imputed datasets. A Sigma-based classification was carried out on the imputed dataset of the better performance imputation technique on software defect estimation. This classification was used to determine at which levels of Sigma; the software projects can be best used to build software defect estimation models: which has resulted in Sigma-based datasets with Sigma ranging (e.g., dataset of software projects with a range from 3 Sigma to 4 Sigma). Finally, software defect estimation models were built on the Sigma-based datasets.

ISBN: 9780355798777Subjects--Topical Terms:

1567821
Computer Engineering.
Subjects--Index Terms:

Defect estimation

Improve Software Defect Estimation with Six Sigma Defect Measures: Empirical Studies with Imputation Techniques on ISBSG Data Repository with a High Ratio of Missing Data.
LDR:04369nmm a2200385 4500 001 2269016
005 20200908082312.5
008 220629s2017 ||||||||||||||||| ||eng d
020 $a 9780355798777
035 $a (MiAaPQ)AAI10751452
035 $a (MiAaPQ)etsmh:10978
035 $a AAI10751452
040 $a MiAaPQ $c MiAaPQ
100 1 $a Almakadmeh, Mhammed. $3 3546320
245 1 0 $a Improve Software Defect Estimation with Six Sigma Defect Measures: Empirical Studies with Imputation Techniques on ISBSG Data Repository with a High Ratio of Missing Data.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2017
300 $a 230 p.
500 $a Source: Dissertations Abstracts International, Volume: 79-10, Section: B.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Abran, Alain.
502 $a Thesis (Ph.D.)--Ecole de Technologie Superieure (Canada), 2017.
506 $a This item must not be added to any third party search indexes.
506 $a This item must not be sold to any third party vendors.
520 $a This research analysis work reports on a set of empirical studies tackling the research issues of improving software defect estimation models with Sigma defect measures (e.g., Sigma levels) using the ISBSG data repository with a high ratio of missing data. Three imputation techniques that were selected for this research work: single imputation, regression imputation, and stochastic regression imputation. These imputation techniques were used to impute the missing data within the variable 'Total Number of Defects', and were first compared with each other using common verification criteria. A further verification strategy was developed to compare and assess the performance of the selected imputation techniques through verifying the predictive accuracy of the obtained software defect estimation models form the imputed datasets. A Sigma-based classification was carried out on the imputed dataset of the better performance imputation technique on software defect estimation. This classification was used to determine at which levels of Sigma; the software projects can be best used to build software defect estimation models: which has resulted in Sigma-based datasets with Sigma ranging (e.g., dataset of software projects with a range from 3 Sigma to 4 Sigma). Finally, software defect estimation models were built on the Sigma-based datasets.
520 $a Cette analyse de recherche fait etat d'un ensemble d'etudes empiriques abordant les problemes de recherche visant a ameliorer les modeles d'estimation des defauts logiciels avec des mesures de defaut Sigma (par exemple, les niveaux Sigma 3 et 4) en utilisant le referentiel de donnees ISBSG avec un ratio eleve de donnees manquantes. Trois techniques d'imputation ont ete selectionnees pour ce travail de recherche: imputation unique, imputation de regression et imputation de regression stochastique. Ces techniques d'imputation ont ete utilisees pour imputer les donnees manquantes dans la variable 'Nombre total de defauts', et ont d'abord ete comparees les unes aux autres en utilisant des criteres de verification communs. Une autre strategie de verification a ete developpee pour comparer et evaluer la performance des techniques d'imputation selectionnees en verifiant la precision predictive des modeles d'estimation des defauts logiciels obtenus dans les jeux de donnees imputes. Une classification basee sur Sigma a ete effectuee sur l'ensemble de donnees impute de la meilleure technique d'imputation de performance sur l'estimation des defauts logiciels. Cette classification a ete utilisee pour determiner a quels niveaux de Sigma; Les projets logiciels peuvent etre utilises pour construire des modeles d'estimation des defauts logiciels: ce qui a entraine des ensembles de donnees Sigma avec la gamme Sigma (par exemple, l'ensemble de donnees de projets logiciels d'une gamme allant de 3 Sigma a 4 Sigma). Enfin, les modeles d'estimation des defauts logiciels ont ete construits sur les ensembles de donnees Sigma.
590 $a School code: 1246.
650 4 $a Computer Engineering. $3 1567821
653 $a Defect estimation
653 $a Design for Six Sigma
653 $a Imputation techniques
653 $a Six sigma
690 $a 0464
710 2 $a Ecole de Technologie Superieure (Canada). $b Departement de genie logiciel et des technologies de l'information. $3 3188618
773 0 $t Dissertations Abstracts International $g 79-10B.
790 $a 1246
791 $a Ph.D.
792 $a 2017
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10751452