Overview
- Editors:
-
-
Simeon J. Simoff
-
Michael H. Böhlen
-
Arturas Mazeika
Access this book
Other ways to access
Table of contents (22 chapters)
-
-
Visual Data Mining: An Introduction and Overview
-
- Simeon J. Simoff, Michael H. Böhlen, Arturas Mazeika
Pages 1-12
-
Part 1 – Theory and Methodologies
-
- Michael H. Böhlen, Linas Bukauskas, Arturas Mazeika, Peer Mylov
Pages 13-29
-
-
- Alipio Jorge, João Poças, Paulo J. Azevedo
Pages 46-59
-
-
- Daniel A. Keim, Florian Mansmann, Jörn Schneidewind, Jim Thomas, Hartmut Ziegler
Pages 76-90
-
Part 2 – Techniques
-
- Arturas Mazeika, Michael H. Böhlen, Peer Mylov
Pages 91-102
-
- Dario Bruzzese, Cristina Davino
Pages 103-122
-
- François Poulet, Thanh-Nghi Do
Pages 123-135
-
- Doina Caragea, Dianne Cook, Hadley Wickham, Vasant Honavar
Pages 136-153
-
- John Risch, Anne Kao, Stephen R. Poteet, Y. -J. Jason Wu
Pages 154-171
-
- Simeon J. Simoff, John Galloway
Pages 172-195
-
- José F. Rodrigues Jr., Agma J. M. Traina, Caetano Traina Jr.
Pages 196-214
-
- Daniel Trivellato, Arturas Mazeika, Michael H. Böhlen
Pages 215-235
-
- Monique Noirhomme-Fraiture, Olivier Schöller, Christophe Demoulin, Simeon J. Simoff
Pages 236-247
-
- Mao Lin Huang, Quang Vinh Nguyen
Pages 248-263
-
- Simeon J. Simoff, Michael H. Böhlen, Arturas Mazeika
Pages 264-280
-
Part 3 – Tools and Applications
-
- Henrik R. Nagel, Erik Granum, Søren Bovbjerg, Michael Vittrup
Pages 281-311
-
- Mihael Ankerst, Anne Kao, Rodney Tjoelker, Changzhou Wang
Pages 312-330
About this book
Visual Data Mining—Opening the Black Box Knowledge discovery holds the promise of insight into large, otherwise opaque datasets. Thenatureofwhatmakesaruleinterestingtoauserhasbeendiscussed 1 widely but most agree that it is a subjective quality based on the practical u- fulness of the information. Being subjective, the user needs to provide feedback to the system and, as is the case for all systems, the sooner the feedback is given the quicker it can in?uence the behavior of the system. There have been some impressive research activities over the past few years but the question to be asked is why is visual data mining only now being - vestigated commercially? Certainly, there have been arguments for visual data 2 mining for a number of years – Ankerst and others argued in 2002 that current (autonomous and opaque) analysis techniques are ine?cient, as they fail to - rectly embed the user in dataset exploration and that a better solution involves the user and algorithm being more tightly coupled. Grinstein stated that the “current state of the art data mining tools are automated, but the perfect data mining tool is interactive and highly participatory,” while Han has suggested that the “data selection and viewing of mining results should be fully inter- tive, the mining process should be more interactive than the current state of the 2 art and embedded applications should be fairly automated . ” A good survey on 3 techniques until 2003 was published by de Oliveira and Levkowitz .