Analisis Perbandingan Optimizer Pada Model Convolutional Neural Network Untuk Deteksi Kanker Paru-Paru

Abstract

This research emphasizes the importance of early detection of lung cancer, which is the leading cause of cancer-related deaths globally. This paper underscores the challenges of manual analysis due to limited medical resources and proposes the use of CNNs to automate the detection process. This research compares the effectiveness of various optimizers in training CNN models for lung cancer detection. The methodology used includes data collection, preprocessing, CNN architecture formation, training, and validation. The results show that the selection of optimizer has a significant impact on model accuracy and convergence speed. The conclusion of this study states that although both SGD and RMSprop produce high training accuracy, RMSprop shows better validation accuracy.

Keywords: lung cancer, Convolutional Neural Networks (CNN), Model Accuracy