New techniques for clustering complex objects [Elektronische Ressource] / von Karin Kailing

New Techniques for ClusteringComplex ObjectsDissertation im Fach Informatikan der Fakulatt fur Mathematik, Informatik und Statistikder Ludwig-Maximilians-Universit at MunchenvonKarin KailingTag der Einreichung: 18.08.2004Tag der mund lichen Pruf ung: 15.11.2004Berichterstatter:Prof. Dr. Hans-Peter Kriegel, Ludwig-Maximilians-Universit at MunchenProf. Dr. Johannes Gehrke, Cornell University (USA)iiAcknowledgmentA lot of people supported and encouraged me while I was working at mythesis. I am very grateful for all the help I got during this time. Unfortu-nately, I can only mention some of them here, but my dearest thanks goes,of course, to all of them.First of all, I want to express my warmest thanks to my supervisorProfessor Dr. Hans-Peter Kriegel who convinced me to come to his groupandthenmadesurethatIneverregrettedthisstep. Withouttheproductiveand inspiring working atmosphere he created, this work could never havebeen done. I also want to thank Professor Johannes Gehrke who readilyagreed to act as the second referee to this thesis.This work was inspired by many fruitful discussions and cooperationswith my colleagues. Without them this work could never have grown. I’mverygratefulforallthesupportIgotduringthepastyearsandofcourse,notto forget, for all the fun we had. A special thanks goes to my colleagues Dr.Peer Kr oger and Dr. Stefan Schonauer who were always willing to answerall my questions.