Organic vapour sensing using a coated piezoelectric quartz crystal sensor array

Hdl Handle:
http://hdl.handle.net/10149/98018
Title:
Organic vapour sensing using a coated piezoelectric quartz crystal sensor array
Book Title:
Environmental Monitoring and Remediation Technologies II
Authors:
Ali, Z. (Zulfiqur); O'Hare, W. T. (Liam); Sarkodie-Gyan, T. (Thompson); Theaker, B. J. (Brenden); Watson, E. (Elsdon)
Editors:
Vo-Dinh, T. (Tuan); Spellicy, R. L. (Robert)
Affiliation:
University of Teesside
Citation:
Ali, Z. et. al. (1999) 'Organic vapour sensing using a coated piezoelectric quartz crystal sensor array', Environmental monitoring and remediation technologies II; Boston, USA, September 20 - 22, in Vo-Dinh, T. and Spellicy, R. L. (eds) Environmental Monitoring and Remediation Technologies II. SPIE Society of Photo-Optical Instrumentation Engineers, pp.116-120.
Publisher:
SPIE Society of Photo-Optical Instrumentation Engineers
Conference:
1999 environmental monitoring and remediation technologies II; Boston, USA, September 20 - 22, 1999.
Issue Date:
Dec-1999
URI:
http://hdl.handle.net/10149/98018
DOI:
10.1117/12.372882
Abstract:
The pattern of responses from a four sensor array have been used for the classification of methanol, propanol, butanol, hexane, heptane and toluene using artificial intelligence (AI) based pattern recognition methods. A feedforward forward network with backpropagation was trained using sensor array data with approximately 300 training vectors and 100 test cases and covering a period of four months. The network consisting of four input nodes, six output nodes, learning rate of 0.1 and momentum of 0 was built using a commercial package (NeuroShell). A classification success rate of 75% was achieved. The bulk of the mis-classifications arose from propanol being classified as butanol and hexane being classified as heptane. These mis-classifications are rational since the respective compounds are very similar in nature. A fuzzy logic algorithm where class membership functions are developed using the mean frequency change and standard deviation of individual sensors was developed for classification of the vapours. In this particular case, classification using the developed fuzzy logic gaussian algorithm was not as good as the feedforward network with backpropagation, but the guassian membership function offers a more rational approach than the previously published trapezoidal membership function.
Type:
Meetings and Proceedings; Book Chapter
Language:
en
Keywords:
Piezoelectric quartz crystal; sensor array; artificial intelligence; pattern recognition; fuzzy logic
Series/Report no.:
3853
ISSN:
0277-786X
ISBN:
9780819434463
Rights:
Author can archive publisher's version/PDF. For full details see http://www.sherpa.ac.uk/romeo/ [Accessed 24/06/2010]
Citation Count:
0 [Scopus, 06/05/2010]

Full metadata record

DC FieldValue Language
dc.contributor.authorAli, Z. (Zulfiqur)en
dc.contributor.authorO'Hare, W. T. (Liam)en
dc.contributor.authorSarkodie-Gyan, T. (Thompson)en
dc.contributor.authorTheaker, B. J. (Brenden)en
dc.contributor.authorWatson, E. (Elsdon)en
dc.contributor.editorVo-Dinh, T. (Tuan)en
dc.contributor.editorSpellicy, R. L. (Robert)en
dc.date.accessioned2010-05-06T08:40:36Z-
dc.date.available2010-05-06T08:40:36Z-
dc.date.issued1999-12-
dc.identifier.isbn9780819434463-
dc.identifier.issn0277-786X-
dc.identifier.doi10.1117/12.372882-
dc.identifier.urihttp://hdl.handle.net/10149/98018-
dc.description.abstractThe pattern of responses from a four sensor array have been used for the classification of methanol, propanol, butanol, hexane, heptane and toluene using artificial intelligence (AI) based pattern recognition methods. A feedforward forward network with backpropagation was trained using sensor array data with approximately 300 training vectors and 100 test cases and covering a period of four months. The network consisting of four input nodes, six output nodes, learning rate of 0.1 and momentum of 0 was built using a commercial package (NeuroShell). A classification success rate of 75% was achieved. The bulk of the mis-classifications arose from propanol being classified as butanol and hexane being classified as heptane. These mis-classifications are rational since the respective compounds are very similar in nature. A fuzzy logic algorithm where class membership functions are developed using the mean frequency change and standard deviation of individual sensors was developed for classification of the vapours. In this particular case, classification using the developed fuzzy logic gaussian algorithm was not as good as the feedforward network with backpropagation, but the guassian membership function offers a more rational approach than the previously published trapezoidal membership function.en
dc.language.isoenen
dc.publisherSPIE Society of Photo-Optical Instrumentation Engineersen
dc.relation.ispartofseries3853en
dc.rightsAuthor can archive publisher's version/PDF. For full details see http://www.sherpa.ac.uk/romeo/ [Accessed 24/06/2010]en
dc.subjectPiezoelectric quartz crystalen
dc.subjectsensor arrayen
dc.subjectartificial intelligenceen
dc.subjectpattern recognitionen
dc.subjectfuzzy logicen
dc.titleOrganic vapour sensing using a coated piezoelectric quartz crystal sensor arrayen
dc.typeMeetings and Proceedingsen
dc.typeBook Chapteren
dc.contributor.departmentUniversity of Teessideen
dc.title.bookEnvironmental Monitoring and Remediation Technologies IIen
dc.identifier.conference1999 environmental monitoring and remediation technologies II; Boston, USA, September 20 - 22, 1999.en
ref.citationcount0 [Scopus, 06/05/2010]en
or.citation.harvardAli, Z. et. al. (1999) 'Organic vapour sensing using a coated piezoelectric quartz crystal sensor array', Environmental monitoring and remediation technologies II; Boston, USA, September 20 - 22, in Vo-Dinh, T. and Spellicy, R. L. (eds) Environmental Monitoring and Remediation Technologies II. SPIE Society of Photo-Optical Instrumentation Engineers, pp.116-120.-
prism.startingPage116-
prism.endingPage120-
All Items in TeesRep are protected by copyright, with all rights reserved, unless otherwise indicated.