Abstract
dc:descriptionThe pandemic outbreak situation has become more serious in the 21st century. Diseases have become more likely to spread across borders and pose a greater threat than before. In order to handle this new situation, the ability to predict the risk of pandemic outbreaks is a necessary. Existing prediction tools include machine learning-based tools and mathematical tools, which do not use machine learning. They both have disadvantages and advantages. My research goal is to develop an ideal outbreak prediction tool that has all the advantages at the same time and overcomes their disadvantages. To achieve this, I used an existing tool, EPIRISK, to implement three machine learning iterations and developed an automated outbreak risk prediction tool. My tool has strong data processing capabilities, it can use variables from multiple aspects to make universal risk predictions for multiple diseases and countries at around 80% to 90% accuracy. At the same time, it combines Automated machine learning and machine learning, which makes it flexible and easy to use and understand. It can allow non-machine learning experts to utilize their expert knowledge and conduct custom model building and improvement on a visual page. My predictive tool fills the research gap in current studies, it can help governments take rapid control measures in the early stages of disease outbreaks, as well as assist international cooperation.
Degree
thesis:*- Grantor dc:publisher
- UNSW, Sydney
- Year dc:date
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Zhang, Tianyu ; https://orcid.org/0000-0001-6332-3921
Subjects
dc:subject × 7Rights
dc:rights- Statement dc:rights
-
- open access
- CC BY 4.0
- free_to_read
Identifiers
dc:identifier.*- Identifier
- https://doi.org/10.26190/unsworks/30434
- OAI identifier oai:identifier
- oai:unsworks.library.unsw.edu.au:1959.4/102855