Unsupervised Weight Parameter Estimation Method for Ensemble Learning

When there are multiple trained predictors, one may want to integrate them into one predictor. However, this is challenging if the performances of the trained predictors are unknown and labeled data for evaluating their performances are not given. In this paper, a method is described that uses unlabeled data to estimate the weight parameters needed to build an ensemble predictor integrating multiple trained component predictors. It is readily derived from a mathematical model of ensemble learning based on a generalized mixture of probability density functions and corresponding information divergence measures. Numerical experiments demonstrated that the performance of our method is much better than that of simple average-based ensemble learning, even when the assumption placed on the performances of the component predictors does not hold exactly.     

Preparation and anticoagulant surface properties of glucoside- or sulfated glucoside-bearing polymer grafted poly(ethylene) films

Poly(GEMA) or poly(GEMA)-sulfate grafted surfaces were prepared for the purpose of developing biomaterials with anticoagulant surfaces. Their functionalities were investigated as anticoagulant activity, proteins and cells adhesion activity, and complement activation activity. These results revealed that the adhesion of blood cells onto a GEMA-sulfate grafted surface was due to protein adsorption and that complement activation onto a GEMA-sulfate grafted surface was larger than that on a GEMA grafted surface. A GEMA-sulfate grafted surface, however, exhibited good anticoagulant activity. These functions seemed to be due to the specific functionality of the SO₃ groups in a GEMA-sulfate.