Comparison of Data-Driven and Physics-Informed Neural Networks for Surrogate Modelling of the Huxley Muscle Model

Bogdan Milićević, Miloš Ivanović, Boban Stojanović, Miljan Milošević, Vladimir Simić, Miloš Kojić, Nenad Filipović

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Biophysical muscle models based on sliding filament and cross-bridge theory are called Huxley-type muscle models. The method of characteristics is typically used to solve Huxley’s muscle contraction equation, which describes the distribution of attached myosin heads to the actin-binding sites, called cross-bridges. Once this equation is solved, we can determine the generated force and the stiffness of the muscle fibers, which can then be used at the macro level during finite element analysis. In our paper, we present alternative approaches to finding an approximate solution of Huxley’s muscle contraction equation using neural networks. In one approach, we collect the data from simulations and train multilayer perceptrons to predict probabilities of cross-bridge formation based on the available actin site positions, time, activation, current and previous stretch. In another approach, besides using the data, we also inform the neural network with Huxley’s equation, thus improving the generalization of the neural network’s predictions.

Original languageEnglish (US)
Title of host publicationApplied Artificial Intelligence 2
Subtitle of host publicationMedicine, Biology, Chemistry, Financial, Games, Engineering - The 2nd Serbian International Conference on Applied Artificial Intelligence SICAAI
EditorsNenad Filipović
PublisherSpringer Science and Business Media Deutschland GmbH
Pages33-37
Number of pages5
ISBN (Print)9783031608391
DOIs
StatePublished - 2024
Event2nd Serbian International Conference on Applied Artificial Intelligence, SICAAI 2023 - Kragujevac, Serbia
Duration: May 19 2023May 20 2023

Publication series

NameLecture Notes in Networks and Systems
Volume999 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

Conference2nd Serbian International Conference on Applied Artificial Intelligence, SICAAI 2023
Country/TerritorySerbia
CityKragujevac
Period5/19/235/20/23

Keywords

  • Huxley muscle model
  • multi-scale modeling
  • numerical solving of partial differential equations
  • physics-informed neural networks

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Comparison of Data-Driven and Physics-Informed Neural Networks for Surrogate Modelling of the Huxley Muscle Model'. Together they form a unique fingerprint.

Cite this