Enhancing supervised classifications with metamorphic relations

Xu, Liming and Towey, Dave and French, Andrew P. and Benford, Steve and Zhou, Zhi Quan and Chen, Tsong Yueh (2018) Enhancing supervised classifications with metamorphic relations. In: 3rd International Workshop on Metamorphic Testing - MET '18, 27 May 2018, Gothenburg, Sweden.

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (2MB) | Preview
[img] PDF - Repository staff only - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB)

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.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published in: Proceedings of the 3rd International Workshop on Metamorphic Testing - MET '18, Gothenburg, Sweden, 27 May 2018. ACM Press, 2018, p. 46-53. doi:10.1145/3193977.3193978
Schools/Departments: University of Nottingham, UK > Faculty of Science > School of Biosciences
University of Nottingham, UK > Faculty of Science > School of Computer Science
Depositing User: Eprints, Support
Date Deposited: 06 Sep 2018 09:51
Last Modified: 06 Sep 2018 09:59
URI: http://eprints.nottingham.ac.uk/id/eprint/53764

Actions (Archive Staff Only)

Edit View Edit View