Subscribe by RSS

Graduate Seminar Series

Mon., Mar. 27, 2023 3:30 p.m.

Location: CK 185 and Live Stream

Speaker: W. Madusha De Silva

Title: On Stacking-based Ensemble Learning Modelling with Applications to Breast Cancer Diagnosis (500 kB)

Abstract:

According to the high variability among various breast cancer datasets, widely-used machine learning models are applied to breast cancer diagnosis. However, the robustness and generalization of these models to assist clinical diagnosis have been debated recently. Therefore, a stacking-based ensemble learning model is proposed in this study. This model consists of a two-layer learning structure, and its classifier combination is determined by the proposed stacking method. This model is applied to three different breast cancer datasets including Breast Cancer Ultrasound (BCU), Wisconsin Breast Cancer (WBC), and Mammographic Mass (MM), and evaluated by classification accuracy and robustness in this study. In this seminar, I will perform the proposed model with a 10-fold cross-validation strategy over 10 repetitions has shown the highest accuracy in three datasets compared with the widely used machine learning models and traditional stacking model.

Live Stream: