LatinPSO

An algorithm for simultaneously inferring structure and parameters of ordinary differential equations models

Xinliang Tian, Wei Pang, Yizhang Wang, Kaimin Guo, You Zhou (Corresponding Author)

Research output: Contribution to journalArticle

Abstract

Simultaneously inferring both the structure and parameters of Ordinary Differential Equations (ODEs) for a complex dynamic system is more practical in many systems identification problems, but it remains challenging due to the complexity of the underlying search space. In this research, we propose a novel algorithm based on Particle Swarm Optimization (PSO) and Latin Hypercube Sampling (LHS) to address the above problem. The proposed algorithm is termed LatinPSO, and it can be effectively used for inferring the structure and parameters of ODE models through time course data. To start with, the real Human Immunodeficiency Virus (HIV) model and several synthetic models are used for evaluating the performance of LatinPSO. Experimental results demonstrated that LatinPSO could find satisfactory candidate ODE models with appropriate structure and parameters.
Original languageEnglish
Pages (from-to)8-16
Number of pages9
JournalBioSystems
Volume182
Early online date2 Jun 2019
DOIs
Publication statusPublished - Aug 2019

Fingerprint

Ordinary differential equations
Ordinary differential equation
HIV
Latin Hypercube Sampling
Identification Problem
Complex Dynamics
System Identification
Viruses
Research
Model
Particle swarm optimization (PSO)
Search Space
Virus
Particle Swarm Optimization
Dynamic Systems
Complex Systems
Identification (control systems)
Dynamical systems
Sampling
Experimental Results

Keywords

  • Ordinary Differential Equations
  • Particle Swarm Optimization
  • Latin Hypercube Sampling
  • Structure and parameters optimization

ASJC Scopus subject areas

  • Statistics and Probability
  • Modelling and Simulation
  • Biochemistry, Genetics and Molecular Biology(all)
  • Applied Mathematics

Cite this

LatinPSO : An algorithm for simultaneously inferring structure and parameters of ordinary differential equations models . / Tian, Xinliang; Pang, Wei; Wang, Yizhang; Guo, Kaimin; Zhou, You (Corresponding Author).

In: BioSystems, Vol. 182, 08.2019, p. 8-16.

Research output: Contribution to journalArticle

@article{1ff1ff815c3c4014bb04abf0c9cbaa7b,
title = "LatinPSO: An algorithm for simultaneously inferring structure and parameters of ordinary differential equations models",
abstract = "Simultaneously inferring both the structure and parameters of Ordinary Differential Equations (ODEs) for a complex dynamic system is more practical in many systems identification problems, but it remains challenging due to the complexity of the underlying search space. In this research, we propose a novel algorithm based on Particle Swarm Optimization (PSO) and Latin Hypercube Sampling (LHS) to address the above problem. The proposed algorithm is termed LatinPSO, and it can be effectively used for inferring the structure and parameters of ODE models through time course data. To start with, the real Human Immunodeficiency Virus (HIV) model and several synthetic models are used for evaluating the performance of LatinPSO. Experimental results demonstrated that LatinPSO could find satisfactory candidate ODE models with appropriate structure and parameters.",
keywords = "Ordinary Differential Equations, Particle Swarm Optimization, Latin Hypercube Sampling, Structure and parameters optimization",
author = "Xinliang Tian and Wei Pang and Yizhang Wang and Kaimin Guo and You Zhou",
note = "This research is supported by the National Natural Science Foundation of China (Grants Nos.61772227, 61572227), the Science & Technology Development Foundation of Jilin Province (Grants No. 20180201045GX), the Science Foundation of Education Department of Guangdong Province (Grants Nos. 2017KQNCX251, 2018XJCQSQ026) and the Social Science Foundation of Education Department of Jilin Province (Grants No. JJKH20181315SK). WP was supported by the 2015 Scottish Crucible award funded by Royal Society of Edinburgh.",
year = "2019",
month = "8",
doi = "10.1016/j.biosystems.2019.05.006",
language = "English",
volume = "182",
pages = "8--16",
journal = "BioSystems",
issn = "0303-2647",
publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - LatinPSO

T2 - An algorithm for simultaneously inferring structure and parameters of ordinary differential equations models

AU - Tian, Xinliang

AU - Pang, Wei

AU - Wang, Yizhang

AU - Guo, Kaimin

AU - Zhou, You

N1 - This research is supported by the National Natural Science Foundation of China (Grants Nos.61772227, 61572227), the Science & Technology Development Foundation of Jilin Province (Grants No. 20180201045GX), the Science Foundation of Education Department of Guangdong Province (Grants Nos. 2017KQNCX251, 2018XJCQSQ026) and the Social Science Foundation of Education Department of Jilin Province (Grants No. JJKH20181315SK). WP was supported by the 2015 Scottish Crucible award funded by Royal Society of Edinburgh.

PY - 2019/8

Y1 - 2019/8

N2 - Simultaneously inferring both the structure and parameters of Ordinary Differential Equations (ODEs) for a complex dynamic system is more practical in many systems identification problems, but it remains challenging due to the complexity of the underlying search space. In this research, we propose a novel algorithm based on Particle Swarm Optimization (PSO) and Latin Hypercube Sampling (LHS) to address the above problem. The proposed algorithm is termed LatinPSO, and it can be effectively used for inferring the structure and parameters of ODE models through time course data. To start with, the real Human Immunodeficiency Virus (HIV) model and several synthetic models are used for evaluating the performance of LatinPSO. Experimental results demonstrated that LatinPSO could find satisfactory candidate ODE models with appropriate structure and parameters.

AB - Simultaneously inferring both the structure and parameters of Ordinary Differential Equations (ODEs) for a complex dynamic system is more practical in many systems identification problems, but it remains challenging due to the complexity of the underlying search space. In this research, we propose a novel algorithm based on Particle Swarm Optimization (PSO) and Latin Hypercube Sampling (LHS) to address the above problem. The proposed algorithm is termed LatinPSO, and it can be effectively used for inferring the structure and parameters of ODE models through time course data. To start with, the real Human Immunodeficiency Virus (HIV) model and several synthetic models are used for evaluating the performance of LatinPSO. Experimental results demonstrated that LatinPSO could find satisfactory candidate ODE models with appropriate structure and parameters.

KW - Ordinary Differential Equations

KW - Particle Swarm Optimization

KW - Latin Hypercube Sampling

KW - Structure and parameters optimization

UR - http://www.mendeley.com/research/latinpso-algorithm-simultaneously-inferring-structure-parameters-ordinary-differential-equations-mod

U2 - 10.1016/j.biosystems.2019.05.006

DO - 10.1016/j.biosystems.2019.05.006

M3 - Article

VL - 182

SP - 8

EP - 16

JO - BioSystems

JF - BioSystems

SN - 0303-2647

ER -