Skin Disease Classification Using Iwoa-Resnet Deep Learning Architecture

Abstract

Accurate classification of skin diseases remains a significant challenge due to the wide range of conditions, image variability, and class imbalance. Conventional diagnostic systems often struggle with limited accuracy and computational inefficiency, hindering real-time clinical use. This study presents a hybrid deep learning model that integrates ResNet-50 with an Improved Whale Optimization Algorithm (IWOA) to address these issues. A diverse skin image dataset was collected and preprocessed before being passed through ResNet-50 for feature extraction. IWOA was employed to optimize key parameters, enhancing model training and convergence. Experimental results show that the proposed IWOA-ResNet model achieves 99.09% accuracy, with a 25% reduction in training time, maintaining strong performance across unbalanced and varied data. When compared to traditional CNN and machine learning models, the hybrid approach demonstrates superior accuracy and efficiency. This research highlights the potential of combining deep learning with metaheuristic optimization for automated, real-time skin disease diagnosis, offering a scalable and robust solution for clinical deployment.