DSpace Repository

Empirical based effort estimation using machine learning algorithms [articol]

Show simple item record

dc.contributor.author Vignaraj Ananth, V.
dc.contributor.author Srinivasan, S.
dc.date.accessioned 2025-02-17T09:59:45Z
dc.date.available 2025-02-17T09:59:45Z
dc.date.issued 2018
dc.identifier.citation Vignaraj Ananth,V.; Srinivasan,S.: Empirical based effort estimation using machine learning algorithms. Timişoara: Editura Politehnica, 2018. en_US
dc.identifier.issn 1582-4594
dc.identifier.uri https://dspace.upt.ro/xmlui/handle/123456789/7171
dc.description.abstract Estimation the budget is one of the major tasks in project management. There arises a need to more accurately estimate the required schedule and resources for the software projects. The software estimation process includes estimating the size of the software product, effort needed, development of project schedules, and estimating the overall budget of the project. To estimate the budget we need to consider effort, time and environment. Estimating the effort is the tedious process. Effort is represented as a function of size. In this paper, size is represented in term as Fuzzy number. A new model is approached in this paper by machine learning algorithms to estimate the effort required in the software process. The optimization of the effort parameters is achieved using the M5P technique to obtain better prediction accuracy. Furthermore, performance comparisons of the models obtained using the M5P technique with Random Forest technique are presented in order to highlight the performance achieved by each technique. en_US
dc.language.iso en en_US
dc.publisher Timișoara : Editura Politehnica en_US
dc.relation.ispartofseries Journal of Electrical Engineering;Vol 18 No 4
dc.subject Lines of Code (LOC) en_US
dc.subject Function Point Analysis(FPA) en_US
dc.subject Triangular Membership Function (TAMF) en_US
dc.subject Trapezoidal Membership Function (TPMF) en_US
dc.subject M5P technique en_US
dc.subject Random Forest technique en_US
dc.title Empirical based effort estimation using machine learning algorithms [articol] en_US
dc.type Article en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account