Date of Award

2021

Publisher

North Dakota State University

Document Type

Master's Paper

Degree Awarded

Master of Science (MS)

Program

Computer Science

Department

Computer Science

College

Science and Mathematics

Faculty Advisor

Ludwig, Simone

Description

In the field of machine learning, classification is the essential task that predicts the target class or label for each sample in the data. Improving the performance of a classification model has been a challenging research problem. Researchers try to choose the proper techniques and combine several algorithms to be applied to the specific data set to get better predictions. Nowadays, researchers have used the method called super learner. The idea of super learning is that it combines multiple techniques as base learners and uses a meta-learner to get the final predictions and thus obtain more reliable results. In this paper, we investigated the super-learning techniques on various healthcare data sets. We displayed the results and compared the results with the single machine learning techniques that we choose as base learners. We observed that super learning provides more dependable performance than the individual machine learning methods in most cases.

Rights

NDSU policy 190.6.2

Rights Link

https://www.ndsu.edu/fileadmin/policy/190.pdf

Handle Identifier

https://hdl.handle.net/10365/31892

Download

Share

COinS