HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Veterinary Medicine / Faculty of Veterinary Medicine >
Peer-reviewed Journal Articles, etc >

Can Machines Learn Respiratory Virus Epidemiology? : A Comparative Study of Likelihood-Free Methods for the Estimation of Epidemiological Dynamics

This item is licensed under: Creative Commons Attribution 4.0 International

Files in This Item:
Frontiers in microbiology 9_343.pdf1.16 MBPDFView/Open
Please use this identifier to cite or link to this item:http://hdl.handle.net/2115/72139

Title: Can Machines Learn Respiratory Virus Epidemiology? : A Comparative Study of Likelihood-Free Methods for the Estimation of Epidemiological Dynamics
Authors: Tessmer, Heidi L. Browse this author
Ito, Kimihito Browse this author →KAKEN DB
Omori, Ryosuke Browse this author →KAKEN DB
Keywords: respiratory virus
infectious disease epidemiology
machine learning
approximate Bayesian computation
basic reproduction number
mathematical model
Issue Date: 2-Mar-2018
Publisher: Frontiers Media
Journal Title: Frontiers in microbiology
Volume: 9
Start Page: 343
Publisher DOI: 10.3389/fmicb.2018.00343
Abstract: To estimate and predict the transmission dynamics of respiratory viruses, the estimation of the basic reproduction number, R-0, is essential. Recently, approximate Bayesian computation methods have been used as likelihood free methods to estimate epidemiological model parameters, particularly R-0. In this paper, we explore various machine learning approaches, the multi-layer perceptron, convolutional neural network, and long-short term memory, to learn and estimate the parameters. Further, we compare the accuracy of the estimates and time requirements for machine learning and the approximate Bayesian computation methods on both simulated and real-world epidemiological data from outbreaks of influenza A(H1N1)pdm09, mumps, and measles. We find that the machine learning approaches can be verified and tested faster than the approximate Bayesian computation method, but that the approximate Bayesian computation method is more robust across different datasets.
Rights: https://creativecommons.org/licenses/by/4.0/
Type: article
URI: http://hdl.handle.net/2115/72139
Appears in Collections:獣医学院・獣医学研究院 (Graduate School of Veterinary Medicine / Faculty of Veterinary Medicine) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

Submitter: 大森 亮介

Export metadata:

OAI-PMH ( junii2 , jpcoar )

MathJax is now OFF:


 

 - Hokkaido University