Constrained Gaussian process with application in tissue-engineering scaffold biodegradation

Li Zeng, Xinwei Deng, Jian Yang

Research output: Contribution to journalArticle

Abstract

In many biomanufacturing areas, such as tissue-engineering scaffold fabrication, the biodegradation performance of products is a key to producing products with desirable properties. The prediction of biodegradation often encounters the challenge of how to incorporate expert knowledge. This article proposes a Constrained Gaussian Process (CGP) method for predictive modeling with application to scaffold biodegradation. It provides a unified framework of using appropriate constraints to accommodate various types of expert knowledge in predictive modeling, including censoring, monotonicity, and bounds requirements. Efficient Bayesian sampling procedures for prediction are also developed. The performance of the proposed method is demonstrated in a case study on a novel scaffold fabrication process. Compared with the unconstrained GP and artificial neural networks, the proposed method can provide more accurate and meaningful prediction. A simulation study is also conducted to further reveal the properties of the CGP.

Original languageEnglish (US)
Pages (from-to)431-447
Number of pages17
JournalIISE Transactions
Volume50
Issue number5
DOIs
StatePublished - May 4 2018

Fingerprint

Scaffolds (biology)
Biodegradation
Tissue engineering
Scaffolds
Fabrication
Sampling
Neural networks

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering

Cite this

@article{8fbf195a2c754dd28c017f5e233365f6,
title = "Constrained Gaussian process with application in tissue-engineering scaffold biodegradation",
abstract = "In many biomanufacturing areas, such as tissue-engineering scaffold fabrication, the biodegradation performance of products is a key to producing products with desirable properties. The prediction of biodegradation often encounters the challenge of how to incorporate expert knowledge. This article proposes a Constrained Gaussian Process (CGP) method for predictive modeling with application to scaffold biodegradation. It provides a unified framework of using appropriate constraints to accommodate various types of expert knowledge in predictive modeling, including censoring, monotonicity, and bounds requirements. Efficient Bayesian sampling procedures for prediction are also developed. The performance of the proposed method is demonstrated in a case study on a novel scaffold fabrication process. Compared with the unconstrained GP and artificial neural networks, the proposed method can provide more accurate and meaningful prediction. A simulation study is also conducted to further reveal the properties of the CGP.",
author = "Li Zeng and Xinwei Deng and Jian Yang",
year = "2018",
month = "5",
day = "4",
doi = "10.1080/24725854.2017.1414973",
language = "English (US)",
volume = "50",
pages = "431--447",
journal = "IISE Transactions",
issn = "2472-5854",
publisher = "Taylor and Francis Ltd.",
number = "5",

}

Constrained Gaussian process with application in tissue-engineering scaffold biodegradation. / Zeng, Li; Deng, Xinwei; Yang, Jian.

In: IISE Transactions, Vol. 50, No. 5, 04.05.2018, p. 431-447.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Constrained Gaussian process with application in tissue-engineering scaffold biodegradation

AU - Zeng, Li

AU - Deng, Xinwei

AU - Yang, Jian

PY - 2018/5/4

Y1 - 2018/5/4

N2 - In many biomanufacturing areas, such as tissue-engineering scaffold fabrication, the biodegradation performance of products is a key to producing products with desirable properties. The prediction of biodegradation often encounters the challenge of how to incorporate expert knowledge. This article proposes a Constrained Gaussian Process (CGP) method for predictive modeling with application to scaffold biodegradation. It provides a unified framework of using appropriate constraints to accommodate various types of expert knowledge in predictive modeling, including censoring, monotonicity, and bounds requirements. Efficient Bayesian sampling procedures for prediction are also developed. The performance of the proposed method is demonstrated in a case study on a novel scaffold fabrication process. Compared with the unconstrained GP and artificial neural networks, the proposed method can provide more accurate and meaningful prediction. A simulation study is also conducted to further reveal the properties of the CGP.

AB - In many biomanufacturing areas, such as tissue-engineering scaffold fabrication, the biodegradation performance of products is a key to producing products with desirable properties. The prediction of biodegradation often encounters the challenge of how to incorporate expert knowledge. This article proposes a Constrained Gaussian Process (CGP) method for predictive modeling with application to scaffold biodegradation. It provides a unified framework of using appropriate constraints to accommodate various types of expert knowledge in predictive modeling, including censoring, monotonicity, and bounds requirements. Efficient Bayesian sampling procedures for prediction are also developed. The performance of the proposed method is demonstrated in a case study on a novel scaffold fabrication process. Compared with the unconstrained GP and artificial neural networks, the proposed method can provide more accurate and meaningful prediction. A simulation study is also conducted to further reveal the properties of the CGP.

UR - http://www.scopus.com/inward/record.url?scp=85041930826&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041930826&partnerID=8YFLogxK

U2 - 10.1080/24725854.2017.1414973

DO - 10.1080/24725854.2017.1414973

M3 - Article

AN - SCOPUS:85041930826

VL - 50

SP - 431

EP - 447

JO - IISE Transactions

JF - IISE Transactions

SN - 2472-5854

IS - 5

ER -