Discovery Science

1. Front Matter

   PDF

2. Invited Papers

   1. e-Science and the Semantic Web: A Symbiotic Relationship

      • Carole Goble, Oscar Corcho, Pinar Alper, David De Roure

      Pages 1-12

   2. Data-Driven Discovery Using Probabilistic Hidden Variable Models

      • Padhraic Smyth

      Pages 13-13

   3. Reinforcement Learning and Apprenticeship Learning for Robotic Control

      • Andrew Ng

      Pages 14-14

   4. The Solution of Semi-Infinite Linear Programs Using Boosting-Like Methods

      • Gunnar Rätsch

      Pages 15-15

   5. Spectral Norm in Learning Theory: Some Selected Topics

      • Hans Ulrich Simon

      Pages 16-16

3. Long Papers

   1. Classification of Changing Regions Based on Temporal Context in Local Spatial Association

      • Jae-Seong Ahn, Yang-Won Lee, Key-Ho Park

      Pages 17-28

   2. Kalman Filters and Adaptive Windows for Learning in Data Streams

      • Albert Bifet, Ricard Gavaldà

      Pages 29-40

   3. Scientific Discovery: A View from the Trenches

      • Catherine Blake, Meredith Rendall

      Pages 41-52

   4. Optimal Bayesian 2D-Discretization for Variable Ranking in Regression

      • Marc Boullé, Carine Hue

      Pages 53-64

   5. Text Data Clustering by Contextual Graphs

      • Krzysztof Ciesielski, Mieczysław A. Kłopotek

      Pages 65-76

   6. Automatic Water Eddy Detection in SST Maps Using Random Ellipse Fitting and Vectorial Fields for Image Segmentation

      • Armando Fernandes, Susana Nascimento

      Pages 77-88

   7. Mining Approximate Motifs in Time Series

      • Pedro G. Ferreira, Paulo J. Azevedo, Cândida G. Silva, Rui M. M. Brito

      Pages 89-101

   8. Identifying Historical Period and Ethnic Origin of Documents Using Stylistic Feature Sets

      • Yaakov HaCohen-Kerner, Hananya Beck, Elchai Yehudai, Dror Mughaz

      Pages 102-113

   9. A New Family of String Classifiers Based on Local Relatedness

      • Yasuto Higa, Shunsuke Inenaga, Hideo Bannai, Masayuki Takeda

      Pages 114-124

   10. On Class Visualisation for High Dimensional Data: Exploring Scientific Data Sets

       • Ata Kabán, Jianyong Sun, Somak Raychaudhury, Louisa Nolan

       Pages 125-136

   11. Mining Sectorial Episodes from Event Sequences

       • Takashi Katoh, Kouichi Hirata, Masateru Harao

       Pages 137-148

   12. A Voronoi Diagram Approach to Autonomous Clustering

       • Heidi Koivistoinen, Minna Ruuska, Tapio Elomaa

       Pages 149-160

   13. Itemset Support Queries Using Frequent Itemsets and Their Condensed Representations

       • Taneli Mielikäinen, Panče Panov, Sašo Džeroski

       Pages 161-172

   14. Strategy Diagram for Identifying Play Strategies in Multi-view Soccer Video Data

       • Yukihiro Nakamura, Shin Ando, Kenji Aoki, Hiroyuki Mano, Einoshin Suzuki

       Pages 173-184

The 9th International Conference on Discovery Science (DS 2006) was held in Barcelona, Spain, on 7–10 October 2006. The conference was collocated with the 17th International Conference on Algorithmic Learning Theory (ALT 2006). The two conferences shared the invited talks. This LNAI volume, containing the proceedings of the 9th International C- ference onDiscoveryScience, is structured in three parts. The ?rstpart contains the papers/abstracts of the invited talks, the second part contains the accepted long papers, and the third part the accepted regular (short) papers. Out of 87 submitted papers, 23 were accepted for publication as long papers, and 18 as regular papers. All the submitted papers were reviewed by two or three ref- ees. In addition to the presentations of accepted papers, the DS 2006 conference program consisted of three invited talks, two tutorials, the collocated ALT 2006 conference and the Pascal Dialogues workshop. We wish to express our gratitude to – the authors of submitted papers, – the program committee and other referees for their thorough and timely paper evaluation, – DS 2006 invited speakers Carole Goble and Padhraic Smyth, as well as - drew Ng as joint DS 2006 and ALT 2006 invited speaker, – invited tutorial speakers Luis Torgo and Michael May, – the local organization committee chaired by Ricard Gavalda, ` – DS 2006 conference chair Klaus P.

• algorithms
• knowledge discovery
• learning
• learning theory
• machine learning
• science
• scientific discovery

• Jozef Stefan Institute, Ljubljana, Slovenia

  Ljupčo Todorovski

• University of Nova Gorica, Nova Gorica, Slovenia

  Nada Lavrač

• Meme Media Laboratory, Hokkaido University Sapporo, Sapporo, Japan

  Klaus P. Jantke

Policies and ethics