Boosting GMM and Its Two Applications

Boosting is an effecient method to improve the classification performance. Recent theoretical work has shown that the boosting technique can be viewed as a gradient descent search for a good fit in function space. Several authors have applied such viewpoint to solve the density estimation problems. In this paper we generalize such framework to a specific density model – Gaussian Mixture Model (GMM) and propose our boosting GMM algorithm. We will illustrate the applications of our algorithm to cluster ensemble and short-term traffic flow forecasting problems. Experimental results are presented showing the effectiveness of our approach.