Advances in Data Mining - Theoretical Aspects and Applications

1. Front Matter

   PDF

2. Invited Talk

   1. Case Based Reasoning and the Search for Knowledge

      • Michael M. Richter

      Pages 1-14

3. Aspects of Classification and Prediction

   1. Subsets More Representative Than Random Ones

      • Ilia Nouretdinov

      Pages 15-20

   2. Concepts for Novelty Detection and Handling Based on a Case-Based Reasoning Process Scheme

      • Petra Perner

      Pages 21-33

   3. An Efficient Algorithm for Instance-Based Learning on Data Streams

      • Jürgen Beringer, Eyke Hüllermeier

      Pages 34-48

   4. Softening the Margin in Discrete SVM

      • Carlotta Orsenigo, Carlo Vercellis

      Pages 49-62

   5. Feature Selection Using Ant Colony Optimization (ACO): A New Method and Comparative Study in the Application of Face Recognition System

      • Hamidreza Rashidy Kanan, Karim Faez, Sayyed Mostafa Taheri

      Pages 63-76

   6. Outlier Detection with Streaming Dyadic Decomposition

      • Chetan Gupta, Robert Grossman

      Pages 77-91

   7. VISRED –Numerical Data Mining with Linear and Nonlinear Techniques

      • Antonio Dourado, Edgar Ferreira, Paulo Barbeiro

      Pages 92-106

4. Clustering

   1. Clustering by Random Projections

      • Thierry Urruty, Chabane Djeraba, Dan A. Simovici

      Pages 107-119

   2. Lightweight Clustering Technique for Distributed Data Mining Applications

      • Lamine M. Aouad, Nhien-An Le-Khac, Tahar M. Kechadi

      Pages 120-134

5. Web Mining

   1. Predicting Page Occurrence in a Click-Stream Data: Statistical and Rule-Based Approach

      • Petr Berka, Martin Labský

      Pages 135-147

   2. Improved IR in Cohesion Model for Link Detection System

      • K. Lakshmi, Saswati Mukherjee

      Pages 148-162

   3. Improving a State-of-the-Art Named Entity Recognition System Using the World Wide Web

      • Richárd Farkas, György Szarvas, Róbert Ormándi

      Pages 163-172

6. Data Mining in Medicine

   1. ISOR-2: A Case-Based Reasoning System to Explain Exceptional Dialysis Patients

      • Olga Vorobieva, Alexander Rumyantsev, Rainer Schmidt

      Pages 173-183

   2. The Role of Prototypical Cases in Biomedical Case-Based Reasoning

      • Isabelle Bichindaritz

      Pages 184-198

7. Applications of Data Mining

   1. A Search Space Reduction Methodology for Large Databases: A Case Study

      • Angel Kuri-Morales, Fátima Rodríguez

      Pages 199-213

   2. Combining Traditional and Neural-Based Techniques for Ink Feed Control in a Newspaper Printing Press

      • Cristofer Englund, Antanas Verikas

      Pages 214-227

   3. Active Learning Strategies: A Case Study for Detection of Emotions in Speech

      • Alexis Bondu, Vincent Lemaire, Barbara Poulain

      Pages 228-241

   4. Neural Business Control System

      • M. Lourdes Borrajo, Juan M. Corchado, E. S. Corchado, M. A. Pellicer

      Pages 242-254

ICDM / MLDM Medaillie (limited edition) Meissner Porcellan, the “White Gold” of King August the Strongest of Saxonia ICDM 2007 was the seventh event in the Industrial Conference on Data Mining series and was held in Leipzig (www.data-mining-forum.de). For this edition the Program Committee received 96 submissions from 24 countries (see Fig. 1). After the peer-review process, we accepted 25 high-quality papers for oral presentation that are included in this proceedings book. The topics range from aspects of classification and prediction, clustering, Web mining, data mining in medicine, applications of data mining, time series and frequent pattern mining, and association rule mining. Germany 9,30% 4,17% China 9,30% 1,04% 6,98% 3,13% South Korea Czech Republic 6,98% 3,13% USA 6,98% 2,08% 4,65% 2,08% UK Portugal 4,65% 2,08% Iran 4,65% 2,08% India 4,65% 2,08% Brazil 4,65% 1,04% Hungary 4,65% 1,04% Mexico 4,65% 1,04% Finland 2,33% 1,04% Ireland 2,33% 1,04% Slovenia 2,33% 1,04% France 2,33% 1,04% Israel 2,33% 1,04% Spain 2,33% 1,04% Greece 2,33% 1,04% Italy 2,33% 1,04% Sweden 2,33% 1,04% Netherlands 2,33% 1,04% Malaysia 2,33% 1,04% Turkey 2,33% 1,04% Fig. 1. Distribution of papers among countries Twelve papers were selected for poster presentations that are published in the ICDM Poster Proceedings Volume.

• algorithmic learning
• algorithms
• association rule mining
• classification
• clustering
• cognition
• computer vision
• feature selection
• filtering
• genetic algorithms
• inductive logic programming
• knowledge dis
• learning
• optimization
• proving

Policies and ethics