Organic vapour sensing using a coated piezoelectric quartz crystal sensor array

Zulfiqur Ali, W. T. Liam O'Hare, Thompson Sarkodie-Gyan, Brenden J Theaker, Elsdon Watson

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearch

13 Downloads (Pure)

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.
Original languageEnglish
Title of host publication Environmental Monitoring and Remediation Technologies II
EditorsTuan Vo-Dinh, Robert L Spellicy
PublisherSPIE Society of Photo-Optical Instrumentation Engineers
Pages116-120
DOIs
Publication statusPublished - Dec 1999
Event1999 Environmental Monitoring and Remediation Technologies II - Boston, United States
Duration: 20 Sep 199922 Sep 1999

Conference

Conference1999 Environmental Monitoring and Remediation Technologies II
CountryUnited States
CityBoston
Period20/09/9922/09/99

Fingerprint

Sensor arrays
Quartz
Vapors
Crystals
Membership functions
Heptane
Propanol
Hexane
Butenes
Backpropagation
Fuzzy logic
Pattern recognition
Artificial intelligence
Toluene
Momentum
Methanol
Sensors

Bibliographical note

Author can archive publisher's version/PDF.

Cite this

Ali, Z., O'Hare, W. T. L., Sarkodie-Gyan, T., Theaker, B. J., & Watson, E. (1999). Organic vapour sensing using a coated piezoelectric quartz crystal sensor array. In T. Vo-Dinh, & R. L. Spellicy (Eds.), Environmental Monitoring and Remediation Technologies II (pp. 116-120). SPIE Society of Photo-Optical Instrumentation Engineers . https://doi.org/10.1117/12.372882
Ali, Zulfiqur ; O'Hare, W. T. Liam ; Sarkodie-Gyan, Thompson ; Theaker, Brenden J ; Watson, Elsdon. / Organic vapour sensing using a coated piezoelectric quartz crystal sensor array. Environmental Monitoring and Remediation Technologies II. editor / Tuan Vo-Dinh ; Robert L Spellicy. SPIE Society of Photo-Optical Instrumentation Engineers , 1999. pp. 116-120
@inproceedings{42445807de8346669fc1f710cbeadf3a,
title = "Organic vapour sensing using a coated piezoelectric quartz crystal sensor array",
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.",
author = "Zulfiqur Ali and O'Hare, {W. T. Liam} and Thompson Sarkodie-Gyan and Theaker, {Brenden J} and Elsdon Watson",
note = "Author can archive publisher's version/PDF.",
year = "1999",
month = "12",
doi = "10.1117/12.372882",
language = "English",
pages = "116--120",
editor = "Tuan Vo-Dinh and Spellicy, {Robert L}",
booktitle = "Environmental Monitoring and Remediation Technologies II",
publisher = "SPIE Society of Photo-Optical Instrumentation Engineers",

}

Ali, Z, O'Hare, WTL, Sarkodie-Gyan, T, Theaker, BJ & Watson, E 1999, Organic vapour sensing using a coated piezoelectric quartz crystal sensor array. in T Vo-Dinh & RL Spellicy (eds), Environmental Monitoring and Remediation Technologies II. SPIE Society of Photo-Optical Instrumentation Engineers , pp. 116-120, 1999 Environmental Monitoring and Remediation Technologies II, Boston, United States, 20/09/99. https://doi.org/10.1117/12.372882

Organic vapour sensing using a coated piezoelectric quartz crystal sensor array. / Ali, Zulfiqur; O'Hare, W. T. Liam; Sarkodie-Gyan, Thompson; Theaker, Brenden J; Watson, Elsdon.

Environmental Monitoring and Remediation Technologies II. ed. / Tuan Vo-Dinh; Robert L Spellicy. SPIE Society of Photo-Optical Instrumentation Engineers , 1999. p. 116-120.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearch

TY - GEN

T1 - Organic vapour sensing using a coated piezoelectric quartz crystal sensor array

AU - Ali, Zulfiqur

AU - O'Hare, W. T. Liam

AU - Sarkodie-Gyan, Thompson

AU - Theaker, Brenden J

AU - Watson, Elsdon

N1 - Author can archive publisher's version/PDF.

PY - 1999/12

Y1 - 1999/12

N2 - 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.

AB - 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.

U2 - 10.1117/12.372882

DO - 10.1117/12.372882

M3 - Conference contribution

SP - 116

EP - 120

BT - Environmental Monitoring and Remediation Technologies II

A2 - Vo-Dinh, Tuan

A2 - Spellicy, Robert L

PB - SPIE Society of Photo-Optical Instrumentation Engineers

ER -

Ali Z, O'Hare WTL, Sarkodie-Gyan T, Theaker BJ, Watson E. Organic vapour sensing using a coated piezoelectric quartz crystal sensor array. In Vo-Dinh T, Spellicy RL, editors, Environmental Monitoring and Remediation Technologies II. SPIE Society of Photo-Optical Instrumentation Engineers . 1999. p. 116-120 https://doi.org/10.1117/12.372882