Gaussian process model based multi-source labeled data transfer learning for reducing cost of modeling target chemical processes with unlabeled data

2021 ◽  
Vol 117 ◽  
pp. 104941
Author(s):  
Lester Lik Teck Chan ◽  
Junghui Chen
Author(s):  
Nicolas H. Nbonsou Tegang ◽  
Jean-Rassaire Fouefack ◽  
Bhushan Borotikar ◽  
Valérie Burdin ◽  
Tania S. Douglas ◽  
...  

2013 ◽  
Vol 671-674 ◽  
pp. 3100-3106
Author(s):  
Xin Liang Liu ◽  
Tao Yin ◽  
Guo Dong Wu

Early understanding of construction cost represents a critical factor of a feasibility study in the early design phase of a project. A new project cost estimation model based on Gaussian Process was proposed. Gaussian Process model theory was introduced, and project cost estimation model based on Gaussian Process’ flow chart was analyzed in detail. Through example analysis, project cost estimation model based on Gaussian Process using Nelder-Mead and genetic algorithms algorithm was proven feasible for this problem and represented accuracy than BP neural network.


Sign in / Sign up

Export Citation Format

Share Document