Random Subspace Method for One-Class Classifiers
Veronika Cheplygina · Research Repository (Delft University of Technology) · 2010
This thesis is submitted in partial ful llment of requirements for the Master of Science degree in Media and Knowledge Engineering at the Delft University of Technology.It contains the results of my graduation project done at the Pattern Recognition Lab in collaboration with Prime Vision from March to November 2010.This document consists of a research article which highlights the most important ndings of my work, and a nal report which includes all the performed research.I would like to thank my supervisors David Tax and Theo van der Donk for all their help during this project, and the Pattern Recognition Lab and Prime Vision for making this project possible.A thank you is also in order to the people of the Pattern Recognition Lab who have sparked my interest in pattern recognition and machine learning during the last years of my study.Delft is not only a place to study.I am grateful for all the things I did next to my education: a board year and several committees at CH, the study visit to the United States and playing soccer at Ariston'80.I have learned a lot from these activities and made many friends.A thank you goes out to all these friends who have made my time here an awesome experience: 51, Wocky!, my soccer team, people from my OWee group whom I've stayed in touch with and many others.Last but not least, I would like to thank my parents and Lennert for supporting me during my whole study and especially