Human Skin Diseases Identification and Treatment Suggestion by Sri Lankan Ayurveda Medicine Using Machine Learning

Human Skin Diseases Identification and Treatment Suggestion by Sri Lankan Ayurveda Medicine Using Machine Learning

The field of dermatology faces significant challenges in accurately diagnosing and treating human skin diseases. This research paper proposes a novel approach that combines Sri Lankan Ayurvedic medicine and machine learning techniques to address these challenges. Specifically, it uses deep learning...

Full description

Saved in:
Bibliographic Details
Published in:2023 5th International Conference on Advancements in Computing (ICAC) pp. 65 - 70
Main Authors: Gomes, M.P.O.M, Jayasekara, Y.N, Kariyapperuma, K.M.K.R, Gunawardhna, H.P.M.N, Suwarnakantha, N.H.P Ravi Supunya, Wimalarathne, Geethanjali
Format: Conference Proceeding
Language:English
Published: IEEE 07-12-2023
Subjects:
CNN
deep learning
Dermatology
Diseases
machine learning
Machine learning algorithms
Medical diagnostic imaging
Random forests
Safety
Skin
skin diseases
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The field of dermatology faces significant challenges in accurately diagnosing and treating human skin diseases. This research paper proposes a novel approach that combines Sri Lankan Ayurvedic medicine and machine learning techniques to address these challenges. Specifically, it uses deep learning models Inception, InceptionV3, and VGG16 to improve the accuracy of skin type detection, skin disease detection, and disease severity classification. The experimental results here show that the Inception Resnet model achieves an accuracy of 86% in identifying skin types, while the InceptionV3 model achieves an impressive 97% accuracy in identifying different skin diseases. Additionally, the VGG16 model achieves a remarkable 96% accuracy in classifying the severity of these diseases. utilizing the principles of ayurvedic medicine, this research further provides treatment suggestions using a random forest algorithm that demonstrates an accuracy of 94.25%. This research not only contributes to the advancement of dermatological diagnosis and treatment, but also highlights the potential of combining traditional healing practices with modern machine learning techniques for improved health outcomes.
ISSN:2837-5424
DOI:10.1109/ICAC60630.2023.10417632