Abstract: A tumor is one of the most dangerous malignancies that may affect human beings. The traditional approach of recognition and categorization of brain tumors by radiologists or clinical experts is by human inspection of medical resonant images (MRI). This type of approach is time-consuming and tedious and most of the time the result is not accurate. When handling human life, accuracy is highly required, hence the need for the automation of brain tumor detection and classification with better accuracy. In the past, various researchers have proposed different traditional classifiers for detecting brain tumors. In this research paper, our model intends to increase the effectiveness of traditional machine learning algorithms by using the stacking method to combine a set of support vector machines, decision trees, and k-nearest neighbors. These base learners are proposed because of their low computational time complexity. The proposed methodology is divided into modules. Module 1: MRI Image dataset Acquisition from Kaggle.com, Module 2: Preprocessing and Extraction of Features using GLCM, Module 3: ensemble approach for classification, and finally, Module4 is the evaluation of the results from the classifiers using standard performance evaluation metrics
Keywords: Ensemble, benign, malignant, support vector machines, decision trees, and k-nearest neighbors.
Title: Framework on an Intelligent Ensemble Technique for Brain Tumor Detection and Classification
Author: Abiodun Ipaye, Prof. O. O. Obe, Prof. Thompson
International Journal of Computer Science and Information Technology Research
ISSN 2348-1196 (print), ISSN 2348-120X (online)
Vol. 11, Issue 1, January 2023 - March 2023
Page No: 91-100
Research Publish Journals
Website: www.researchpublish.com
Published Date: 25-March-2023
