Abstract
Data derived from chemical vapor sensor arrays was analyzed using Fischer linear discriminant analysis (LDA) and multilayer perceptrons (MLP). Datasets produced by an e-nose based on polymer-carbon black sensors and those produced by a second e-nose based on five thin film metal oxide sensors was analyzed. The datasets were chosen to give classification problems of varying hardness: from the discrimination of two almost Gaussian distributed analytes to the discrimination of two analytes in the presents of interferents at different concentration levels. The performance of the best 5-sensors subset selected with MLP was found to be better than the performance of the LDA-selected subsets.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of IEEE Sensors |
| Pages | 606-610 |
| Number of pages | 5 |
| Volume | 2 |
| Edition | 1 |
| Publication status | Published - 2003 |
| Event | Second International Conference on Sensors: IEEE Sensors 2003 - Toronto, Ont., Canada Duration: Oct 22 2003 → Oct 24 2003 |
Other
| Other | Second International Conference on Sensors: IEEE Sensors 2003 |
|---|---|
| Country | Canada |
| City | Toronto, Ont. |
| Period | 10/22/03 → 10/24/03 |
Fingerprint
ASJC Scopus subject areas
- Engineering (miscellaneous)
- Electrical and Electronic Engineering
Cite this
Classifier comparison and sensor selection for e-noses. / Pardo, M.; Sberveglieri, G.; Sisk, B.; Lewis, Nathan S.
Proceedings of IEEE Sensors. Vol. 2 1. ed. 2003. p. 606-610.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Classifier comparison and sensor selection for e-noses
AU - Pardo, M.
AU - Sberveglieri, G.
AU - Sisk, B.
AU - Lewis, Nathan S
PY - 2003
Y1 - 2003
N2 - Data derived from chemical vapor sensor arrays was analyzed using Fischer linear discriminant analysis (LDA) and multilayer perceptrons (MLP). Datasets produced by an e-nose based on polymer-carbon black sensors and those produced by a second e-nose based on five thin film metal oxide sensors was analyzed. The datasets were chosen to give classification problems of varying hardness: from the discrimination of two almost Gaussian distributed analytes to the discrimination of two analytes in the presents of interferents at different concentration levels. The performance of the best 5-sensors subset selected with MLP was found to be better than the performance of the LDA-selected subsets.
AB - Data derived from chemical vapor sensor arrays was analyzed using Fischer linear discriminant analysis (LDA) and multilayer perceptrons (MLP). Datasets produced by an e-nose based on polymer-carbon black sensors and those produced by a second e-nose based on five thin film metal oxide sensors was analyzed. The datasets were chosen to give classification problems of varying hardness: from the discrimination of two almost Gaussian distributed analytes to the discrimination of two analytes in the presents of interferents at different concentration levels. The performance of the best 5-sensors subset selected with MLP was found to be better than the performance of the LDA-selected subsets.
UR - http://www.scopus.com/inward/record.url?scp=1542303707&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=1542303707&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:1542303707
VL - 2
SP - 606
EP - 610
BT - Proceedings of IEEE Sensors
ER -