A comparative study of the classification of skin burn depth in human

Kuan, Pei Nei and Li, Stephanie Chua Hui and Ehfa, binti Bujang Safawi and Wang, Hui Hui and Tiong, Wei King (2017) A comparative study of the classification of skin burn depth in human. Journal of Telecommunication, Electronic and Computer Engineering, 9 (2-10). pp. 15-23. ISSN 21801843

[img] PDF
A comparative.pdf

Download (927kB)
Official URL: https://www.scopus.com/inward/record.uri?eid=2-s2....


A correct first evaluation of skin burn injury is essential as it is an important step in providing the first treatment to the patient by determining the burn depths. The objective of this paper is to conduct a comparative study of different types of classification algorithms on the classification of different burn depths by using an image mining approach. 20 classification algorithms were compared on a skin burn dataset comprising skin burn images categorized into three classes by medical experts. The dataset was evaluated using both a supplied test set and 10-fold cross validation methods. Empirical results showed that the best classification algorithms that were able to classify most of the burn depths using a supplied test set were Logistic, Simple Logistic, MultiClassClassifier, OneR, and LMT, with an average accuracy of 68.9% whereas for 10-fold cross validation evaluation, the best result was obtained through the Simple Logistic algorithm with an average accuracy of 73.2%. It can be concluded that Simple Logistic has the potential to provide the best classification for the degree of skin burn depth.

Item Type: Article
Additional Information: Information, Communication and Creative Technology
Uncontrolled Keywords: Classification, Image Mining Approach, Segmentation, Skin Burn, unimas, university, universiti, Borneo, Malaysia, Sarawak, Kuching, Samarahan, ipta, education, research, Universiti Malaysia Sarawak.
Subjects: Q Science > Q Science (General)
R Medicine > R Medicine (General)
Divisions: Academic Faculties, Institutes and Centres > Faculty of Computer Science and Information Technology
Depositing User: Ibrahim
Date Deposited: 01 Mar 2018 03:41
Last Modified: 29 Sep 2022 03:31
URI: http://ir.unimas.my/id/eprint/19717

Actions (For repository members only: login required)

View Item View Item