Page principale | Projets | Publications | Thèses | Présentations | Membres | Cours | Gallerie | Intérêt local Home | Projects | Publications | Theses | Presentations | People | Courses | Gallery | Local interest

Abstract

Design anomalies, introduced during software evolution, are frequent causes of low maintainability and low flexibility to future changes. Because of the required knowledge, an important subset of design anomalies is difficult to detect automatically, and therefore, the code of anomaly candidates must be inspected manually to validate them. However, this task is time- and resource-consuming. We propose a visualization-based approach to detect design anomalies for cases where the detection effort already includes the validation of candidates. We introduce a general detection strategy that we apply to three types of design anomaly. These strategies are illustrated on concrete examples. Finally we evaluate our approach through a case study. It shows that performance variability against manual detection is reduced and that our semi-automatic detection has good recall for some anomaly types.

Keywords

BibTeX entry

@inproceedings{dhambri-csmr2008,
  title     = "Visual Detection of Design Anomalies",
  author    = "Karim Dhambri and Houari A. Sahraoui and Pierre Poulin",
  booktitle = "12th European Conference on Software Maintenance and Reengineering 2008",
  year      = "2008",
  month     = apr,
  pages     = "279--283"
}

Online version