Enhancing Supervised Classifications with Metamorphic Relations

Liming Xu, Dave Towey, Andrew P. French, Steve Benford, Zhi Quan Zhou, Tsong Yueh Chen

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

5 Citations (Scopus)

Abstract

We report on a novel use of metamorphic relations (MRs) in machine learning: instead of conducting metamorphic testing, we use MRs for the augmentation of the machine learning algorithms themselves. In particular, we report on how MRs can enable enhancements to an image classification problem of images containing hidden visual markers (Artcodes). Working on an original classifier, and using the characteristics of two different categories of images, two MRs, based on separation and occlusion, were used to improve the performance of the classifier. Our experimental results show that the MR-augmented classifier achieves better performance than the original classifier, algorithms, and extending the use of MRs beyond the context of software testing.

Original languageEnglish
Title of host publicationProceedings 2018 ACM/IEEE 3rd International Workshop on Metamorphic Testing, MET 2018
PublisherIEEE Computer Society
Pages46-53
Number of pages8
ISBN (Electronic)9781450357296
DOIs
Publication statusPublished - 27 May 2018
Event3rd ACM/IEEE International Workshop on Metamorphic Testing, MET 2018, held in conjunction with the 40th International Conference on Software Engineering, ICSE 2018 - Gothenburg, Sweden
Duration: 27 May 2018 → …

Publication series

NameProceedings - International Conference on Software Engineering
ISSN (Print)0270-5257

Conference

Conference3rd ACM/IEEE International Workshop on Metamorphic Testing, MET 2018, held in conjunction with the 40th International Conference on Software Engineering, ICSE 2018
Country/TerritorySweden
CityGothenburg
Period27/05/18 → …

Keywords

  • Artcodes
  • Metamorphic testing
  • metamorphic relations
  • random forests
  • supervised classification

ASJC Scopus subject areas

  • Software

Fingerprint

Dive into the research topics of 'Enhancing Supervised Classifications with Metamorphic Relations'. Together they form a unique fingerprint.

Cite this