Invited session IS73:

"Signal Processing Techniques for Knowledge Extraction and Information Fusion"

All papers were printed in:

Knowledge-Based Intelligent Information and Engineering Systems, 10th International Conference, KES 2006, Bournemouth, UK, October 9-11, 2006. Proceedings, Part III, Lecture Notes in Computer Science, Springer Berlin / Heidelberg, 2006
ISSN: 0302-9743,
DOI:   10.1007/11893011
ISBN: 978-3-540-46542-3
Online Date: Wednesday, October 18, 2006

Signal Reconstruction by Projection Filter with Preservation of Preferential Components Akira Hirabayashi Yamaguchi University, Japan Naito Takeshi Omron Corporation, Japan pp. 1272-1279, link

Sensor Network Localization Using Least Squares Kernel Regression Anthony Kuh University of Hawaii, USA Chaopin Zhu University of Hawaii, USA Danilo P. Mandic Imperial College London, UK pp. 1280-1287, link

Acoustic Parameter Extraction from Occupied Rooms Utilizing Blind Source Separation Yonggang Zhang Cardiff University, UK Jonathon A. Chambers Cardiff University, UK Paul Kendrick University of Salford, UK Trevor J. Cox University of Salford, UK Francis F. Li Manchester Metropolitan University, UK pp. 1208-1215, link

An Online Method for Detecting Nonlinearity Within a Signal Beth Jelfs Imperial College London, UK Phebe Vayanos Imperial College London, UK Mo Chen Imperial College London, UK Su Lee Goh Imperial College London, UK Christos Boukis AIT, Greece Temujin Gautama Phillips Leuven, Belgium Tomasz M. Rutkowski Brain Science Institute, RIKEN, Japan Anthony Kuh University of Hawaii, USA Danilo P. Mandic Imperial College London, UK pp. 1216-1223, link

Using Hierarchical Filters to Detect Sparseness in Unknown Channels C. Boukis AIT, Greece L.C. Polymenakos AIT, Greece pp. 1224-1231, link

Auditory Feedback for Brain Computer Interface Management - An EEG Data Sonification Approach - Tomasz M. Rutkowski Brain Science Institute, RIKEN, Japan Francois Vialatte Brain Science Institute, RIKEN, Japan Andrzej Cichocki Brain Science Institute, RIKEN, Japan Danilo P. Mandic Imperial College London, UK Allan Kardec Barros Universidade Federal do Maranhao, Brazil pp. 1232-1239, link

Analysis of the Quasi-Brain-Death EEG Data Based on a Robust ICA Approach Jianting Cao Saitama Institute of Technology, Japan Brain Science Institute, RIKEN, Japan pp. 1240-1247, link

A Flexible Method for Envelope Estimation in Empirical Mode Decomposition Yoshikazu Washizawa Brain Science Institute, RIKEN, Japan Toshihisa Tanaka Tokyo University of Agriculture and Technology, Japan Brain Science Institute, RIKEN, Japan Danilo P. Mandic Imperial College London, UK Andrzej Cichocki Brain Science Institute, RIKEN, Japan pp. 1248-1255, link

The Performance of LVQ Based Automatic Relevance Determination Applied to Spontaneous Biosignals Martin Golz University of Applied Sciences Schmalkalden, Germany David Sommer University of Applied Sciences Schmalkalden, Germany pp. 1256-1263, link

Alertness Assessment using Data Fusion and Discrimination Ability of LVQ-Networks Udo Trutschel Circadian Technologies, MA, USA David Sommer University of Applied Sciences Schmalkalden, Germany Acacia Aguirre Circadian Technologies, MA, USA Todd Dawson Circadian Technologies, MA, USA Bill Sirois Circadian Technologies, MA, USA pp. 1264-1271, link

Scope

Knowledge extraction and information fusion have long be studied in various areas of computer science, and the number of applications for this class of techniques has been steadily growing. Since features and other parameters that describe a process under consideration are extracted directly from the data, it is natural to ask ourselves whether we can use signal processing techniques for this purpose. This has tremendous potential, since DSP techniques are well equipped for problems where noise, uncertainty and complexity play major roles.

This special section therefore aims at  bringing together researchers working in various fields of  signal processing and related disciplines in order to consolidate the existing and propose new directions in SP based knowledge extraction and information fusion.  We encourage contributions presenting both novel algorithms and existing applications, especially those (but not restricted to) on-line processing of real world data.

The key areas of interest are

• DSP based knowledge extraction
• Sparseness as an information fusion criterion
• Data and sensor fusion
• Signal extraction based on their fundamental properties (nonlinearity, smoothness)
• Blind source extraction
• Transform domain and subspace techniques
• Advanced classification and clustering
• Information theoretical approaches
• Biomedical applications
• Industrial and environmental applications