Date of Award

5-2024

Document Type

Project

Degree Name

Master of Science in Information Systems and Technology

Department

Information and Decision Sciences

First Reader/Committee Chair

Conrad Shayo

Abstract

Technological advancements in deep learning and machine learning have greatly improved the diagnosis and analysis of medical images. This culminating experience project utilized the EfficientNetV2B3 model to predict brain tumors. The research questions are: (Q1) Does the study's deep learning model perform better than current methods when it comes to predicting brain tumor? (Q2) How much does the model's performance change when using different optimizers such as Adagrad, Adam, and SGD? (Q3) Can the regularization method, such as dropout, enhance the neural network model's generalization? The findings are as follows: (Q1) Yes; the EfficientNetV2B3 model performs better than current methods. (Q2) Based on optimizer value, accuracy is varied: the Adam optimizer provides a higher performance compared to Adagrad and SGD optimizers. (Q3) (a) Yes, using regularization methods helps improve model generalization; (b) model performance is improved from 98% to 99% after using the dropout layer. Finally, the conclusion is that the EfficientNetV2B3 model performs well on brain tumor prediction.

Share

COinS