<![CDATA[This study aims to improve the accuracy of brain tumor classification using Convolutional Neural Network (CNN) method on MRI images. In this study, various experiments were conducted using the original dataset and data that had undergone augmentation to increase the amount and variety of data. This study shows that data augmentation, such as flipping, scaling, and rotation, significantly improves model accuracy. The best model was obtained using flip and scale augmentation techniques with an average accuracy of 92.97%. These results show that the use of data augmentation techniques can improve the performance of CNN models in classifying brain tumors, and reduce the risk of overfitting. This research makes an important contribution to the field of medical diagnosis by providing a more accurate and efficient model for detecting brain tumors.]]>
Copyrights © 2024
