Peningkatan kinerja arsitektur ResNet50 untuk Menangani Masalah Overfitting dalam Klasifikasi Penyakit Kulit

Abstract

Skin diseases are a significant global health issue, affecting millions of people worldwide. Deep learning, particularly with the transfer learning approach, has shown great potential in improving the diagnosis of skin diseases. This study aims to evaluate various techniques in the context of skin disease classification using transfer learning, focusing on the utilization of the ResNet50 architecture. The steps include data preprocessing, model design with variations in dense layers, fine-tuning, and dropout, as well as model performance evaluation. The results indicate that adding dense layers and fine-tuning significantly improve classification accuracy. Models without additional dense layers achieved an accuracy of around 90%, while fine-tuned models achieved an accuracy of about 94%, and models with added dense layers and fine-tuning achieved an accuracy of about 92%. Overall, adding dense layers and fine-tuning are effective strategies for enhancing the performance of skin disease classification models.