Visual Data Mining

1. Front Matter

   PDF

2. Visual Data Mining: An Introduction and Overview

   1. Visual Data Mining: An Introduction and Overview

      • Simeon J. Simoff, Michael H. Böhlen, Arturas Mazeika

      Pages 1-12

3. Part 1 – Theory and Methodologies

   1. The 3DVDM Approach: A Case Study with Clickstream Data

      • Michael H. Böhlen, Linas Bukauskas, Arturas Mazeika, Peer Mylov

      Pages 13-29

   2. Form-Semantics-Function – A Framework for Designing Visual Data Representations for Visual Data Mining

      • Simeon J. Simoff

      Pages 30-45

   3. A Methodology for Exploring Association Models

      • Alipio Jorge, João Poças, Paulo J. Azevedo

      Pages 46-59

   4. Visual Exploration of Frequent Itemsets and Association Rules

      • Li Yang

      Pages 60-75

   5. Visual Analytics: Scope and Challenges

      • Daniel A. Keim, Florian Mansmann, Jörn Schneidewind, Jim Thomas, Hartmut Ziegler

      Pages 76-90

4. Part 2 – Techniques

   1. Using Nested Surfaces for Visual Detection of Structures in Databases

      • Arturas Mazeika, Michael H. Böhlen, Peer Mylov

      Pages 91-102

   2. Visual Mining of Association Rules

      • Dario Bruzzese, Cristina Davino

      Pages 103-122

   3. Interactive Decision Tree Construction for Interval and Taxonomical Data

      • François Poulet, Thanh-Nghi Do

      Pages 123-135

   4. Visual Methods for Examining SVM Classifiers

      • Doina Caragea, Dianne Cook, Hadley Wickham, Vasant Honavar

      Pages 136-153

   5. Text Visualization for Visual Text Analytics

      • John Risch, Anne Kao, Stephen R. Poteet, Y. -J. Jason Wu

      Pages 154-171

   6. Visual Discovery of Network Patterns of Interaction between Attributes

      • Simeon J. Simoff, John Galloway

      Pages 172-195

   7. Mining Patterns for Visual Interpretation in a Multiple-Views Environment

      • José F. Rodrigues Jr., Agma J. M. Traina, Caetano Traina Jr.

      Pages 196-214

   8. Using 2D Hierarchical Heavy Hitters to Investigate Binary Relationships

      • Daniel Trivellato, Arturas Mazeika, Michael H. Böhlen

      Pages 215-235

   9. Complementing Visual Data Mining with the Sound Dimension: Sonification of Time Dependent Data

      • Monique Noirhomme-Fraiture, Olivier Schöller, Christophe Demoulin, Simeon J. Simoff

      Pages 236-247

   10. Context Visualization for Visual Data Mining

       • Mao Lin Huang, Quang Vinh Nguyen

       Pages 248-263

   11. Assisting Human Cognition in Visual Data Mining

       • Simeon J. Simoff, Michael H. Böhlen, Arturas Mazeika

       Pages 264-280

5. Part 3 – Tools and Applications

   1. Immersive Visual Data Mining: The 3DVDM Approach

      • Henrik R. Nagel, Erik Granum, Søren Bovbjerg, Michael Vittrup

      Pages 281-311

   2. DataJewel: Integrating Visualization with Temporal Data Mining

      • Mihael Ankerst, Anne Kao, Rodney Tjoelker, Changzhou Wang

      Pages 312-330

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 .

• SVM classifiers
• association rules mining
• clusterin
• context visualizations
• data mining
• decision trees
• density surfaces
• multiple views
• pattern mining
• text visualizations
• visual analytics
• visual exploration
• visual hierarchical heavy hitters
• visual interpretation
• visualization

Policies and ethics