On line estimation of color values (B*) in pet process using gaussian process regression

With improvement of PET quality, the color of PET is required to be controlled. But the mechanism model of PET color is uot so clear. Iu this paper, a modeling method of color values (B*) is introduced. It is based on sparse pseudo-input gaussiau process. Online correction is added to the modeling based on sliding time window. Comparing to support vector regression, the model using gaussiau process gives both prediction and predictive variance. The results show that B* value model using gaussiau process is more flexible and can be used in real process.