P1.0.18 Fusing the Diagnostic Information Provided by a Gas Sensor Temperature-Modulated with Different Power Waveforms
- Event
- 14th International Meeting on Chemical Sensors - IMCS 2012
2012-05-20 - 2012-05-23
Nürnberg/Nuremberg, Germany - Chapter
- P1.0 Metal Oxide-based Sensors
- Author(s)
- A. Amini - Sama Technical and Vocational Training College, Islamic Azad University (Iran), M. Bagheri, G. Montazer - Department of Information Technology, School of Engineering, Tarbiat Modares University (Iran), F. Hossein-Babaein - Electronic Materials Laboratory, Electrical Engineering Department, K. N. Toosi University of Technology (Iran)
- Pages
- 789 - 801
- DOI
- 10.5162/IMCS2012/P1.0.18
- ISBN
- 978-3-9813484-2-2
- Price
- free
Abstract
Numerous voltage waveforms have been used for the operating temperature modulation of chemoresistors resulting in different amounts of analyte-related information. The massive amount of numerical information and high level of data redundancy increases the computation cost and complicates the signal pr°Cessing algorithm. Here, we fuse the information contents of the responses recorded using different temperature-modulating waveforms with an ensemble classification strategy for obtaining higher rates in analyte recognition. 100% classification rates were achieved in the classification of three different target analytes each examined at different concentrations in air by combining the outputs of nine base classifiers each trained individually with different feature subsets.