Open AccessSkin Cancer Detection Using Support Vector Machine Learning Classification based on Particle Swarm Optimization Capabilities
Author(s) -
Ding–Yu Fei,
osamah A Almasiri,
Azhar Rafig
Publication year - 2020
Publication title -
transactions on machine learning and artificial intelligence
Language(s) - English
Resource type - Journals
ISSN - 2054-7390
DOI - 10.14738/tmlai.84.8415
Subject(s) - support vector machine , particle swarm optimization , computer science , artificial intelligence , skin lesion , analytics , skin cancer , pattern recognition (psychology) , machine learning , contextual image classification , image (mathematics) , cancer , data mining , medicine , pathology
Skin cancer continues to be a common malignancy that has steadily increased each year. The need for early detection of such skin lesions is critical to preventing further medical complications. The main method for detection of skin cancer is by microscopic examination of skin lesions. Great efforts have been placed to use computer aided technologies for the analysis of skin lesions. In this study, we present a method for an algorithm design using Support Vector Machine (SVM) learning classification based on Particle swarm optimization (PSO) principles in order to improve the accuracy of skin lesion image analysis and classification for further diagnosis. Hospital Pedro Hispano (PH²) dataset with 200 images is used for this study. The method presented here incorporates 46 texture features in order to complete comprehensive image analytics and classification. The proposed method demonstrates an opportunity to explore best possible criteria in image analytics for clinical decision support.