Thermal time constant: optimizing the skin temperature predictive modelling in lower limb prostheses using Gaussian processes

Research output: Contribution to journalArticle

Abstract

Elevated skin temperature at the body/device interface of lower-limb prostheses is one of the major factors that affect tissue health. The heat dissipation in prosthetic sockets is greatly influenced by the thermal conductive properties of the hard socket and liner material employed. However, monitoring of the interface temperature at skin level in lower-limb prosthesis is notoriously complicated. This is due to the flexible nature of the interface liners used impeding the required consistent positioning of the temperature sensors during donning and doffing. Predicting the in-socket residual limb temperature by monitoring the temperature between socket and liner rather than skin and liner could be an important step in alleviating complaints on increased temperature and perspiration in prosthetic sockets. To predict the residual limb temperature a machine learning algorithm - Gaussian processes is employed, which utilizes the thermal time constant values of commonly used socket and liner materials. This study highlights the relevance of thermal time constant of prosthetic materials in Gaussian Processes technique which would be useful in addressing the challenge of non-invasively monitoring the residual limb skin temperature. With the introduction of thermal time constant in the covariance function, the model can be optimized and generalized for a given prosthetic setup, thereby making the predictions more reliable.
LanguageEnglish
Pages98 – 104
Number of pages6
JournalIET Healthcare Technology Letters
Volume3
Issue number2
DOIs
Publication statusPublished - 12 Feb 2016

Fingerprint

Prosthetics
Skin
Temperature
Monitoring
Thromboplastin
Temperature sensors
Hot Temperature
Heat losses
Learning algorithms
Learning systems
Health
Tissue

Keywords

  • predictive modeling
  • Gaussian processes
  • lower limb prostheses
  • skin temperature

Cite this

@article{244c3b4424704ac4843d9b621eccf7a7,
title = "Thermal time constant: optimizing the skin temperature predictive modelling in lower limb prostheses using Gaussian processes",
abstract = "Elevated skin temperature at the body/device interface of lower-limb prostheses is one of the major factors that affect tissue health. The heat dissipation in prosthetic sockets is greatly influenced by the thermal conductive properties of the hard socket and liner material employed. However, monitoring of the interface temperature at skin level in lower-limb prosthesis is notoriously complicated. This is due to the flexible nature of the interface liners used impeding the required consistent positioning of the temperature sensors during donning and doffing. Predicting the in-socket residual limb temperature by monitoring the temperature between socket and liner rather than skin and liner could be an important step in alleviating complaints on increased temperature and perspiration in prosthetic sockets. To predict the residual limb temperature a machine learning algorithm - Gaussian processes is employed, which utilizes the thermal time constant values of commonly used socket and liner materials. This study highlights the relevance of thermal time constant of prosthetic materials in Gaussian Processes technique which would be useful in addressing the challenge of non-invasively monitoring the residual limb skin temperature. With the introduction of thermal time constant in the covariance function, the model can be optimized and generalized for a given prosthetic setup, thereby making the predictions more reliable.",
keywords = "predictive modeling, Gaussian processes, lower limb prostheses, skin temperature",
author = "Neha Mathur and Ivan Glesk and Adrianus Buis",
note = "This paper is a postprint of a paper submitted to and accepted for publication in IET Healthcare Technology Lettes and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at IET Digital Library",
year = "2016",
month = "2",
day = "12",
doi = "10.1049/htl.2015.0023",
language = "English",
volume = "3",
pages = "98 – 104",
journal = "IET Healthcare Technology Letters",
issn = "2053-3713",
number = "2",

}

TY - JOUR

T1 - Thermal time constant

T2 - IET Healthcare Technology Letters

AU - Mathur, Neha

AU - Glesk, Ivan

AU - Buis, Adrianus

N1 - This paper is a postprint of a paper submitted to and accepted for publication in IET Healthcare Technology Lettes and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at IET Digital Library

PY - 2016/2/12

Y1 - 2016/2/12

N2 - Elevated skin temperature at the body/device interface of lower-limb prostheses is one of the major factors that affect tissue health. The heat dissipation in prosthetic sockets is greatly influenced by the thermal conductive properties of the hard socket and liner material employed. However, monitoring of the interface temperature at skin level in lower-limb prosthesis is notoriously complicated. This is due to the flexible nature of the interface liners used impeding the required consistent positioning of the temperature sensors during donning and doffing. Predicting the in-socket residual limb temperature by monitoring the temperature between socket and liner rather than skin and liner could be an important step in alleviating complaints on increased temperature and perspiration in prosthetic sockets. To predict the residual limb temperature a machine learning algorithm - Gaussian processes is employed, which utilizes the thermal time constant values of commonly used socket and liner materials. This study highlights the relevance of thermal time constant of prosthetic materials in Gaussian Processes technique which would be useful in addressing the challenge of non-invasively monitoring the residual limb skin temperature. With the introduction of thermal time constant in the covariance function, the model can be optimized and generalized for a given prosthetic setup, thereby making the predictions more reliable.

AB - Elevated skin temperature at the body/device interface of lower-limb prostheses is one of the major factors that affect tissue health. The heat dissipation in prosthetic sockets is greatly influenced by the thermal conductive properties of the hard socket and liner material employed. However, monitoring of the interface temperature at skin level in lower-limb prosthesis is notoriously complicated. This is due to the flexible nature of the interface liners used impeding the required consistent positioning of the temperature sensors during donning and doffing. Predicting the in-socket residual limb temperature by monitoring the temperature between socket and liner rather than skin and liner could be an important step in alleviating complaints on increased temperature and perspiration in prosthetic sockets. To predict the residual limb temperature a machine learning algorithm - Gaussian processes is employed, which utilizes the thermal time constant values of commonly used socket and liner materials. This study highlights the relevance of thermal time constant of prosthetic materials in Gaussian Processes technique which would be useful in addressing the challenge of non-invasively monitoring the residual limb skin temperature. With the introduction of thermal time constant in the covariance function, the model can be optimized and generalized for a given prosthetic setup, thereby making the predictions more reliable.

KW - predictive modeling

KW - Gaussian processes

KW - lower limb prostheses

KW - skin temperature

UR - http://digital-library.theiet.org/content/journals/10.1049/htl.2015.0023

U2 - 10.1049/htl.2015.0023

DO - 10.1049/htl.2015.0023

M3 - Article

VL - 3

SP - 98

EP - 104

JO - IET Healthcare Technology Letters

JF - IET Healthcare Technology Letters

SN - 2053-3713

IS - 2

ER -