Back to search

Institutional Repository of Vilnius University

Vartotojų reikalavimų kokybės vertinimas taikant dirbtinio intelekto metodus /

Abstract

dc:description

Ensuring user requirements quality is an important part of software development process as 70 % to 85 % of the unplanned project budget must be used to solve problems, caused by inadequate requirements quality. In order to solve this problem, this thesis aims to create and analyze an algorithm, which would be capable of evaluating the quality of a requirement, written as a user story. This algorithm aims to determine if requirements are complete and atomic by using a machine learning model. Furthermore, an analysis of the effectiveness of created model is provided in this thesis, which evaluates the influence of different learning process parameters to the results provided by the model. This analysis shows that the most influential parameters are the number of training epochs and neurons in hidden layers, as well as the amount of data used for training the model.

Degree

thesis:*
Grantor dc:publisher
Institutional Repository of Vilnius University
Year dc:date
2022

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Čenys, Matas,

Rights

dc:rights
Statement dc:rights
  • info:eu-repo/semantics/openAccess
Language dc:language
lit

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Vilnius University
Base URL
epublications.vu.lt/oai
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Čenys, Matas,. Vartotojų reikalavimų kokybės vertinimas taikant dirbtinio intelekto metodus /. Institutional Repository of Vilnius University, 2022. https://repository.vu.lt/VU:ELABAETD146238669&prefLang=en_US