Affordable Access

Access to the full text

Activity Diagram Synthesis Using Labelled Graphs and the Genetic Algorithm

Authors
  • Wang, Chun-Hui1, 1, 2
  • Jin, Zhi1, 1
  • Zhang, Wei1, 1
  • Zowghi, Didar3
  • Zhao, Hai-Yan1, 1
  • Jiao, Wen-Pin1, 1
  • 1 Peking University, Beijing, 100871, China , Beijing (China)
  • 2 Inner Mongolia Normal University, Hohhot, 010022, China , Hohhot (China)
  • 3 University of Technology Sydney, Sydney, 2007, Australia , Sydney (Australia)
Type
Published Article
Journal
Journal of Computer Science and Technology
Publisher
Springer-Verlag
Publication Date
Nov 30, 2021
Volume
36
Issue
6
Pages
1388–1406
Identifiers
DOI: 10.1007/s11390-020-0293-9
Source
Springer Nature
Keywords
Disciplines
  • Regular Paper
License
Yellow

Abstract

Many applications need to meet diverse requirements of a large-scale distributed user group. That challenges the current requirements engineering techniques. Crowd-based requirements engineering was proposed as an umbrella term for dealing with the requirements development in the context of the large-scale user group. However, there are still many issues. Among others, a key issue is how to merge these requirements to produce the synthesized requirements description when a set of requirements descriptions from different participants are received. Appropriate techniques are needed for supporting the requirements synthesis. Diagrams are widely used in industry to represent requirements. This paper chooses the activity diagrams and proposes a novel approach for the activity diagram synthesis which adopts the genetic algorithm to repeatedly modify a population of individual solutions toward an optimal solution. As a result, it can automatically generate a resulting diagram which combines the commonalities as many as possible while leveraging the variabilities of a set of input diagrams. The approach is featured by: 1) the labelled graph proposed as the representation of the candidate solutions during the iterative evolution; 2) the generalized entropy proposed and defined as the measurement of the solutions; 3) the genetic algorithm designed for sorting out the high-quality solution. Four cases of different scales are used to evaluate the effectiveness of the approach. The experimental results show that not only the approach gets high precision and recall but also the resulting diagram satisfies the properties of minimization and information preservation and can support the requirements traceability.

Report this publication

Statistics

Seen <100 times