Convolutional Neural Networks (CNN) have been widely used for image classification tasks, including human skin disease detection. In recent years, various improvements have been made to CNN architectures, with the aim of increasing the accuracy and efficiency of these networks. However, to achieve optimal performance on a specific task, it is essential to select the best combination of hyperparameters that can significantly impact the performance of the CNN. In this study, we investigate the effects of different hyperparameter combinations on the accuracy of CNN-based human skin disease detection models. Our research employs popular CNN architectures, such as VGG16, InceptionV3, and ResNet50, and explores various hyperparameter tuning approaches, including grid search, random search, and Bayesian optimization. We also assess the benefits of data augmentation and transfer learning in enhancing the performance of the CNN models. Through our experiments, we aim to identify the best hyperparameter configurations for human skin disease detection and provide insights into the performance of different tuning approaches.

Convolutional Neural Networks (CNN), Hyperparameter Tuning, Human Skin Disease Detection.