<![CDATA[This study examines the impact of hyperparameter tuning on the performance of Convolutional Neural Networks (CNN) in classifying brain tumors using MRI images. The dataset, sourced from Kaggle, underwent preprocessing techniques such as normalization, augmentation, and resizing to enhance consistency and diversity. The study evaluates five hyperparameter configurations, analyzing their effects on classification accuracy, precision, recall, and F1-score. The optimal configuration (batch size: 16, epochs: 10, learning rate: 0.001) achieved an accuracy of 86%, precision of 81%, recall of 85%, and an F1-score of 0.83. Other configurations showed trade-offs, where larger batch sizes increased recall but reduced precision. These findings emphasize the importance of careful hyperparameter tuning to optimize medical imaging classification performance.]]>
Copyrights © 2025
