I am working in the PDDP (Principal Direction Divisive Partition) group and my advisor is Professor Boley. My primary research interests are:
A: Improving the learning process of available supervised learning algorithms using unsupervised ones. We have successfully applied this general idea in speeding up the training process of support vector machines using PDDP.
Training Support Vector Machine using
Adaptive Clustering, 2004
B: Applying kernel methods to computer vision problems, for example, human gait recognitions.
· Online Motion Classification using Support Vector Machine, IEEE 2004 International Conference on Robotics and Automation, April 26 - May 1, New Orleans, LA, USA. Here is the abstract and the full paper (ps, pdf). (Authors: D. Cao, O. Masoud, D. Boley, N. Papanikolopoulos)
The views and opinions expressed in this page are strictly those of the page author.
The contents of this page have not been reviewed or approved by the University of Minnesota.