Uncovering personal circadian responses to light through particle swarm optimization

被引:0
|
作者
Vicente-Martinez, Jesus [1 ,2 ]
Bonmati-Carrion, Maria Angeles [1 ,2 ]
Madrid, Juan Antonio [1 ,2 ]
Rol, Maria Angeles [1 ,2 ]
机构
[1] Univ Murcia, Dept Physiol, Coll Biol, Chronobiol Lab,Mare Nostrum Campus,IUIE,IMIB Arrix, Murcia 30100, Spain
[2] Inst Salud Carlos III, Ciber Fragilidad & Envejecimiento Saludable, Madrid 28029, Spain
关键词
Particle swarm optimization; Kronauer ' s oscillator model; Circadian personalization; Circadian response to light; Parameter optimization of ordinary differential; equations; Heuristic algorithms; CYCLE OSCILLATOR MODEL; PARAMETER-ESTIMATION; PHASE; PACEMAKER; DYNAMICS; EXPOSURE; PERIOD;
D O I
10.1016/j.cmpb.2023.107933
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Background and objectives: Kronauer's oscillator model of the human central pacemaker is one of the most commonly used approaches to study the human circadian response to light. Two sources of error when applying it to a personal light exposure have been identified: (1) as a populational model, it does not consider interindividual variability, and (2) the initial conditions needed to integrate the model are usually unknown, and thus subjectively estimated. In this work, we evaluate the ability of particle swarm optimization (PSO) algorithms to simultaneously uncover the optimal initial conditions and individual parameters of a pre-defined Kronauer's oscillator model.Methods: A Canonical PSO, a Dynamic Multi-Swarm PSO and a novel modification of the latter, namely Hierarchical Dynamic Multi-Swarm PSO, are evaluated. Two different target models (under a regular and an irregular schedule) are defined, and the same realistic light profile is fed to them. Based on their output, a fitness function is proposed, which is minimized by the algorithms to find the optimum set of parameters and initial conditions of the model. Results: We demonstrate that Dynamic Multi-Swarm and Hierarchical Dynamic Multi-Swarm algorithms can accurately uncover personal circadian parameters under both regular and irregular schedules, but as expected, optimization is easier under a regular schedule. Circadian parameters play the most important role in the optimization process and should be prioritized over initial conditions, although assessment of the impact of misestimating the latter is recommended. The log-log linear relationship between mean absolute error and computational cost shows that the number of particles to use is at the discretion of the user.Conclusions: The robustness and low errors achieved by the algorithms support their further testing, validation and systematic application to empirical data under a regular or irregular schedule. Uncovering personal circadian parameters can improve the assessment of the circadian status of a person and the applicability of personalized light therapies, as well as help to discover other factors that may lie behind the interindividual variability in the circadian response to light.
引用
收藏
页数:14
相关论文
共 50 条
  • [21] Analog circuit design optimization through the particle swarm optimization technique
    Fakhfakh, Mourad
    Cooren, Yann
    Sallem, Amin
    Loulou, Mourad
    Siarry, Patrick
    ANALOG INTEGRATED CIRCUITS AND SIGNAL PROCESSING, 2010, 63 (01) : 71 - 82
  • [22] PID based Particle Swarm Optimization in Offices Light Control
    Copot, Cosmin
    Thoa Mac Thi
    Ionescu, Clara
    IFAC PAPERSONLINE, 2018, 51 (04): : 382 - 387
  • [23] Atmospheric Light Estimation using Particle Swarm Optimization for Dehazing
    Padmini, T. N.
    Shankar, T.
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2019, 10 (11) : 553 - 563
  • [24] Particle Swarm Optimization in Swarm Robotics
    Turkler, Levent
    Akkan, L. Ozlem
    Akkan, Taner
    2ND INTERNATIONAL CONGRESS ON HUMAN-COMPUTER INTERACTION, OPTIMIZATION AND ROBOTIC APPLICATIONS (HORA 2020), 2020, : 305 - 310
  • [25] Hovering Swarm Particle Swarm Optimization
    Karim, Aasam Abdul
    Isa, Nor Ashidi Mat
    Lim, Wei Hong
    IEEE ACCESS, 2021, 9 (09): : 115719 - 115749
  • [26] Particle swarm optimization
    Venter, G
    Sobieszczanski-Sobieski, J
    AIAA JOURNAL, 2003, 41 (08) : 1583 - 1589
  • [27] Swarm Reinforcement Learning Algorithm Based on Particle Swarm Optimization Whose Personal Bests Have Lifespans
    Iima, Hitoshi
    Kuroe, Yasuaki
    NEURAL INFORMATION PROCESSING, PT 2, PROCEEDINGS, 2009, 5864 : 169 - 178
  • [28] Examination of benefits of personal fitness improvement dependent inertia for Particle Swarm Optimization
    Druzeta, Sinisa
    Ivic, Stefan
    SOFT COMPUTING, 2017, 21 (12) : 3387 - 3400
  • [29] Simulated Annealing Embedded Within Personal Velocity Update of Particle Swarm Optimization
    Heim, Ainslee
    Ferens, Ken
    ADVANCES IN ARTIFICIAL INTELLIGENCE AND APPLIED COGNITIVE COMPUTING, 2021, : 1123 - 1144
  • [30] About selecting the personal best in multi-objective particle swarm optimization
    Branke, Juergen
    Mostaghim, Sanaz
    PARALLEL PROBLEM SOLVING FROM NATURE - PPSN IX, PROCEEDINGS, 2006, 4193 : 523 - 532