Conference Paper


Deep oversampling technique for 4-level acne classification in imbalanced data

Abstract

The current technological horizon in the Internet of Things, computer vision, deep learning and healthcare systems makes it possible to monitor some pre-existing conditions as acne vulgaris, automate the assessment of the acne severity by photo and monitor the skin health by specialists. Remote analysis of the skin condition and automatic image classification has several challenges. One of the most critical problems is imbalanced data raised because the number of clinical cases for each acne grade differs. This paper proposes a deep oversampling technique for 4-level acne classification that enables to deal with imbalanced datasets. The method was validated using several criteria. The experimental results obtained for imbalanced data sets revealed that the acne classification via proposed deep oversampling outperforms benchmark approaches.



The fulltext files of this resource are currently embargoed.
Embargo end: 2023-04-21

Authors

Biloborodova, Tetiana
Koverha, Mark
Skarga-Bandurova, Inna
Yevsieieva, Yelzaveta
Skarha-Bandurov, Illia

Oxford Brookes departments

School of Engineering, Computing and Mathematics

Dates

Year of publication: 2022
Date of RADAR deposit: 2022-07-01



“Copyright © 2022, Springer Nature. Users may view, print, copy, download and text and data-mine the content, for the purposes of non-commercial academic research, subject always to the full conditions of use. See: https://www.springernature.com/gp/open-research/policies/accepted-manuscript-terms.”


Related resources

This RADAR resource is the Accepted Manuscript of Deep oversampling technique for 4-level acne classification in imbalanced data

Details

  • Owner: Joseph Ripp
  • Collection: Outputs
  • Version: 1 (show all)
  • Status: Live
  • Views (since Sept 2022): 38