TY - GEN
T1 - The applicability of temperature correction to chemoresistive sensors in an e-NOSE-ANN system
AU - Hobson, Rosalyn
AU - Guiseppi-Elie, Anthony
PY - 2001
Y1 - 2001
N2 - The influence of the temperature sensitivity of chemoresistive, inherently-conductive-polymer (ICP) sensors on the performance of an artificial neural network (ANN) e-NOSE system is evaluated Temperature was found to strongly influence the responses of the chemoresistors. An e-NOSE array of eight ICP sensor elements, a relative humidity (RH) sensor and a resistance temperature device (RTD) was tested at five different RH levels while the temperature was allowed to vary naturally. A temperature correction algorithm based on the temperature coefficient of resistance, β, for each material was independently determined and applied to raw sensor data prior to input to the ANN. Conversely, uncorrected data was passed to the ANN. The performance of the ANN was evaluated by determining the error found between the actual humidity versus the calculated humidity. The error obtained using raw input data was 10.5% and using temperature corrected data 9.3%. This negligible difference demonstrates that the ANN was capable of adequately addressing the temperature dependence of the chemoresistive sensors.
AB - The influence of the temperature sensitivity of chemoresistive, inherently-conductive-polymer (ICP) sensors on the performance of an artificial neural network (ANN) e-NOSE system is evaluated Temperature was found to strongly influence the responses of the chemoresistors. An e-NOSE array of eight ICP sensor elements, a relative humidity (RH) sensor and a resistance temperature device (RTD) was tested at five different RH levels while the temperature was allowed to vary naturally. A temperature correction algorithm based on the temperature coefficient of resistance, β, for each material was independently determined and applied to raw sensor data prior to input to the ANN. Conversely, uncorrected data was passed to the ANN. The performance of the ANN was evaluated by determining the error found between the actual humidity versus the calculated humidity. The error obtained using raw input data was 10.5% and using temperature corrected data 9.3%. This negligible difference demonstrates that the ANN was capable of adequately addressing the temperature dependence of the chemoresistive sensors.
KW - ANN
KW - Chemoresistive sensors
KW - Temperature dependence
KW - e-NOSE
UR - http://www.scopus.com/inward/record.url?scp=3042767120&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=3042767120&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:3042767120
SN - 0970827504
T3 - 2001 International Conference on Modeling and Simulation of Microsystems - MSM 2001
SP - 314
EP - 317
BT - 2001 International Conference on Modeling and Simulation of Microsystems - MSM 2001
A2 - Laudon, M.
A2 - Romanowicz, B.
T2 - 2001 International Conference on Modeling and Simulation of Microsystems - MSM 2001
Y2 - 19 March 2001 through 21 March 2001
ER -