A Differential Evolution-Based Optimized Ensemble for Balanced and Imbalanced Medical Datasets

Key Points

Improvements in minority class detection indicate a significant advancement in imbalanced datasets.
The OEDE framework offers robust design features with effective performance on healthcare risk prediction tasks.
Differential evolution methods optimize ensemble techniques, enhancing accuracy in identifying minority class groups.
This approach highlights the potential for tailored solutions to address challenges in data imbalances.

Abstract

The proposed OEDE framework effectively improves minority class detection in imbalance medical datasets. Its robust and flexible design makes it a promising tool for healthcare risk prediction tasks where minority class groups need to be well identified.

Read Full Paperexternally

Bookmark

View Full Paper

Cite This Study

Das et al. (Tue,) studied this question.

synapsesocial.com/papers/69a75b1dc6e9836116a21d55 https://doi.org/https://doi.org/10.12688/f1000research.169456.2

Bookmark

View Full Paper