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 language | English (US) |
|---|---|
| Pages (from-to) | 431-447 |
| Number of pages | 17 |
| Journal | IISE Transactions |
| Volume | 50 |
| Issue number | 5 |
| DOIs | |
| State | Published - May 4 2018 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Industrial and Manufacturing Engineering
Cite this
}
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 journal › Article
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 -