Show simple item record  

dc.contributor.authorHolmes, Geoffrey
dc.contributor.authorFletcher, Dale
dc.contributor.authorReutemann, Peter
dc.contributor.authorFrank, Eibe
dc.coverage.spatialConference held at Thessaloniki, Greeceen_NZ
dc.date.accessioned2009-06-24T22:22:05Z
dc.date.available2009-06-24T22:22:05Z
dc.date.issued2009
dc.identifier.citationHolems, G., Fletcher, D., Reutemann, P. & Frank, E. (2009). Analysing chromatographic data using data mining to monitor petroleum content in water. In Proceedings of 4th International ICSC Symposium on Information Thessaloniki, Greece, May 28-29, 2009 (pp. 278-290). Berlin: Springer.en
dc.identifier.urihttps://hdl.handle.net/10289/2204
dc.description.abstractChromatography is an important analytical technique that has widespread use in environmental applications. A typical application is the monitoring of water samples to determine if they contain petroleum. These tests are mandated in many countries to enable environmental agencies to determine if tanks used to store petrol are leaking into local water systems. Chromatographic techniques, typically using gas or liquid chromatography coupled with mass spectrometry, allow an analyst to detect a vast array of compounds—potentially in the order of thousands. Accurate analysis relies heavily on the skills of a limited pool of experienced analysts utilising semi-automatic techniques to analyse these datasets—making the outcomes subjective. The focus of current laboratory data analysis systems has been on refinements of existing approaches. The work described here represents a paradigm shift achieved through applying data mining techniques to tackle the problem. These techniques are compelling because the efficacy of preprocessing methods, which are essential in this application area, can be objectively evaluated. This paper presents preliminary results using a data mining framework to predict the concentrations of petroleum compounds in water samples. Experiments demonstrate that the framework can be used to produce models of sufficient accuracy—measured in terms of root mean squared error and correlation coefficients—to offer the potential for significantly reducing the time spent by analysts on this task.en
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherSpringeren
dc.relation.urihttp://www.springerlink.com/content/h12653026k05x710/?p=a60420529ddf45dab9c20555146b2565&pi=20en
dc.rightsThis is an author’s version of an article published in the Proceedings of 4th International ICSC Symposium on Information Thessaloniki, Greece, May 28-29, 2009. ©2009 Springer-Verlag Berlin Heidelberg.en
dc.source4th International ICSC Symposium on Information Technologies in Environmental Engineeringen_NZ
dc.subjectcomputer scienceen
dc.subjectgas chromatography mass spectrometryen
dc.subjectGC-MSen
dc.subjectBTEXen
dc.subjectdata miningen
dc.subjectmodel treesen
dc.subjectregressionen
dc.subjectdata preprocessingen
dc.subjectcorrelation optimized warpingen
dc.subjectpetroleum monitoringen
dc.subjectMachine learning
dc.titleAnalysing chromatographic data using data mining to monitor petroleum content in wateren
dc.typeConference Contributionen
dc.identifier.doi10.1007/978-3-540-88351-7_21en
dc.relation.isPartOfProc Fourth International ICSC Symposium on Information Technologies in Environmental Engineeringen_NZ
pubs.begin-page278en_NZ
pubs.elements-id18691
pubs.end-page290en_NZ
pubs.finish-date2009-05-29en_NZ
pubs.place-of-publicationBerlinen_NZ
pubs.start-date2009-05-28en_NZ
pubs.volumeInformation Technologies in Environmental Engineeringen_NZ


Files in this item

This item appears in the following Collection(s)

Show simple item record