Artificial intelligence techniques for tongue color detection
Files
(Published version)
Date
2024
Authors
Hassoon, A.R.
Khalid, G.A.
Al Shafeay, A.H.
Al Naj, A.
Editors
Hatem, W.A.
Obed, A.A.
Mosleh, M.F.
Gharghan, S.K.
Al-Naji, A.
Obed, A.A.
Mosleh, M.F.
Gharghan, S.K.
Al-Naji, A.
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
AIP Conference Proceedings, 2024 / Hatem, W.A., Obed, A.A., Mosleh, M.F., Gharghan, S.K., Al-Naji, A. (ed./s), vol.3232, iss.1, pp.1-8
Statement of Responsibility
Conference Name
The Fifth Scientific Conference for Electrical Engineering Techniques Research (EETR 2024) (15 Jun 2024 - 16 Jun 2024 : Baghdad, Iraq)
Abstract
Tongue color analysis has recently been enhanced to gain insights into health by incorporating artificial intelligence, especially machine learning classification models, such as K Nearest Neighbor (KNN), Decision Trees (DT), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). This approach involves using these models to classify and interpret tongue color patterns, allowing subtle differences in tongue color to be explored and providing advanced tools for healthcare professionals for early detection and diagnosis purposes. By using these machine learning models, the scope of examination is expanded, which enhances the detection of health problems and supports effective management of health care. The results demonstrate the high accuracy and comprehensiveness of clinical assessments, with the XGBoost model providing the highest accuracy in detecting tongue color at 98.71%, and the technology (KNN) giving the lowest accuracy, which is still a commendable 96.77%. Thus, this study reflects the evolving nature of medical care, enhancing the accuracy and comprehensiveness of clinical assessments.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
Copyright 2024 The Author(s)
Access Condition Notes: Accepted manuscript available on Open Access