<![CDATA[A brain tumor is an abnormal growth of cells in the brain that often requires an accurate diagnosis from a radiologist. This study aims to implement the Naive Bayes algorithm in improving the accuracy of brain tumor diagnosis. Naive Bayes is a popular classification algorithm in data mining that can provide accurate results even with limited datasets. The study used a dataset of MRI images of brain tumors from Kaggle consisting of 2044 image samples with three classes: meningioma tumors, pituitary tumors, and no tumors. The process starts with image preprocessing, then feature extraction using Local Binary Pattern (LBP), and classification using Naive Bayes algorithm. The test results showed the best parameters of LBP were radius 1 and neighborliness 8, while the Naive Bayes model achieved 68% accuracy, 67% precision, and 66% recall in classifying all three classes of brain tumors. The study expands knowledge of the potential of the Naive Bayes algorithm in brain tumor diagnosis and may form the basis for further research.]]>
Copyrights © 2024
