Intelligent Data Analysis Group

[ research areas | publications | resources | people | contact | imprint / Impressum ]

The IDA group is concerned with theoretical concepts and algorithms for machine learning and their practical application to real-world data analysis problems. In particular, we are developing tools for high-dimensional multivariate statistics based on methods originally developed in the field of statistics and, more recently, in the neural networks and machine learning community. Our major objective is to pursue our research all the way from theory to application. To this end, we are contributing to the theoretical development of new data analysis techniques, to their implementation according to software-engineering standards, and, finally, to their industrial or academic application.

Research areas

• Machine learning methods for analysis and prediction of complex systems
• The Brain-Computer Interface (BCI): the Speed Cap and Brain2Robot project
• Intrusion Detection: the ReMIND project
• Support Vector Machines (SVM) and kernel-based learning methods
• Neural networks for segmentation and analysis of non-stationary time series
• Blind Source Separation (BSS) and Independent Component Analysis (ICA) of multi-channel data
• Applications to all kinds of data, e.g., physiological data, audio, video, images and financial data

Publications

[ all | 2009 | 2008 | 2007 | 2006 | 2005 | 2004 | 2003 | 2002 | 2001 | 2000 | 1999 | 1998 and before ]

Resources (only for scientific use)

• The IDA Benchmark Datasets Repository

People at the IDA group

(former members: here)

Contact:

Dr. Guido Nolte
Fraunhofer FIRST
Kekuléstr. 7
D-12489 Berlin, Germany
Phone: +49 30 6392-1861
Fax: +49 30 6392-1805
E-Mail: guido.nolte@first.fraunhofer.de