Accurate classification of burn injuries using support vector machines and the wavelet Shannon entropy of the THz-TDS waveforms

  • Mahmoud E. Khani
  • , Zachery B. Harris
  • , Omar B. Osman
  • , Juin Wan Zhou
  • , Adam J. Singer
  • , M. Hassan Arbab

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

Abstract

The accuracy of clinical assessment of partial-thickness burn injuries has remained as low as 60% in the first few days post burn induction. Here, we present the implementation of a wavelet Shannon entropy technique for noninvasive characterization of burn injuries in an in vivo porcine burn study. Supervised machine learning using the support vector machines (SVM) based on the energy to Shannon entropy ratio (ESER) in the wavelet packet transform of the THz-TDS waveform yielded accuracy rates above 91% in differentiation between superficial, intermediate, and full-thickness burn categories.

Original languageEnglish
Title of host publication2021 46th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2021
PublisherInstitute of Electrical and Electronics Engineers
ISBN (Electronic)9781728194240
DOIs
StatePublished - 1 Jan 2021
Externally publishedYes
Event46th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2021 - Chengdu, China
Duration: 30 Aug 20213 Sep 2021

Publication series

NameInternational Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz
Volume2021-August
ISSN (Print)2162-2027
ISSN (Electronic)2162-2035

Conference

Conference46th International Conference on Infrared, Millimeter, and Terahertz Waves, IRMMW-THz 2021
Country/TerritoryChina
CityChengdu
Period30/08/213/09/21

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Accurate classification of burn injuries using support vector machines and the wavelet Shannon entropy of the THz-TDS waveforms'. Together they form a unique fingerprint.

Cite this