Department of Information Technology
Information processing research lab
GASDETECTOR - Automatic Detection and Recognition of Hazardous Chemical Agents

Poster from DSP2002 conference (500KB)

Goals of the project

Detection of hazardous chemical agents is very demanding application area for pattern recognition. No mistakes can be made. To understand and learn more about pattern recognition methods and their properties, some of the most popular methods were tested using data measured by M90 chemical agent detector developed by Environics, Ltd.

This project was done during summer 2001. The goal of the project was to gain laboratory knowledge on pattern recognition methods capable to critical and demanding problems. As a result authors introduced a new Bayesian theory based method and produced important comparison results of several popular methods in given task.


Project is finished. All the goals were met.


Scientific articles produced by this project in chronological order (contact authors for reprints).

  1. Ilonen, J., Kamarainen, J.-K., Kalviainen, H., Anttalainen, O. Automatic Detection and Recognition of Hazardous Chemical Agents, Proceedings of 14th International Conference on Digital Signal Processing DSP2002, Santorini, Greece, July 1-3, 2002.


Links to other resources

Environics, Ltd.

Contact information

Jarmo Ilonen E-mail WWW Research assistant, Lappeenranta University of Technology
Joni Kamarainen E-mail WWW researcher, Lappeenranta University of Technology
Heikki Kšlvišinen E-mail WWW Responsible author, professor, Lappeenranta University of Technology
Osmo Anttalainen E-mail WWW Vice President, Technology. Environics, Ltd.

Last changes: $Date: 2002/06/28 06:20:28 $ by $Author: jkamarai $