Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-3823
Full metadata record
DC FieldValueLanguage
dc.contributor.authorMeier, Mario Federico-
dc.contributor.authorMildenberger, Thoralf-
dc.contributor.authorLocher, René-
dc.contributor.authorRausch, Juanita-
dc.contributor.authorZünd, Thomas-
dc.contributor.authorNeururer, Christoph-
dc.contributor.authorRuckstuhl, Andreas-
dc.contributor.authorGrobéty, Bernard-
dc.date.accessioned2018-07-03T14:22:59Z-
dc.date.available2018-07-03T14:22:59Z-
dc.date.issued2018-05-22-
dc.identifier.issn0021-8502de_CH
dc.identifier.urihttps://digitalcollection.zhaw.ch/handle/11475/7549-
dc.description.abstractComputer controlled scanning electron microscopy (CCSEM) is a widely-used method for single airborne particle analysis. It produces extensive chemical and morphological data sets, whose processing and interpretation can be very time consuming. We propose an automated two-stage particle classification procedure based on elemental compositions of individual particles. A rule-based classifier is applied in the first stage to form the main classes consisting of particles containing the same elements. Only elements with concentrations above a threshold of 5 wt% are considered. In the second stage, data of each main class are isometrically log-ratio transformed and then clustered into subclasses, using a robust, model-based method. Single particles which are too far away from any more densely populated region are excluded during training, preventing these particles from distorting the definition of the sufficiently populated subclasses. The classifier was trained with over 55,000 single particles from 83 samples of manifold environments, resulting in 227 main classes and 465 subclasses in total. All these classes are checked manually by inspecting the ternary plot matrix of each main class. Regardless of the size of training data, some particles might belong to still undefined classes. Therefore, a classifier was chosen which can declare particles as unknown when they are too far away from all classes defined during training.de_CH
dc.language.isoende_CH
dc.publisherElsevierde_CH
dc.relation.ispartofJournal of Aerosol Sciencede_CH
dc.rightshttp://creativecommons.org/licenses/by/4.0/de_CH
dc.subjectCluster analysisde_CH
dc.subjectTwo-stage classifierde_CH
dc.subjectRule based classifierde_CH
dc.subjectModel based classifierde_CH
dc.subjectCompositional datade_CH
dc.subjectIsometrical log-ratio transformde_CH
dc.subjectAerosol measurementde_CH
dc.subjectSingle particle analysisde_CH
dc.subjectSource apportionmentde_CH
dc.subject.ddc540: Chemiede_CH
dc.subject.ddc570: Biologiede_CH
dc.titleA model based two-stage classifier for airborne particles analyzed with computer controlled scanning electron microscopyde_CH
dc.typeBeitrag in wissenschaftlicher Zeitschriftde_CH
dcterms.typeTextde_CH
zhaw.departementSchool of Engineeringde_CH
zhaw.organisationalunitInstitut für Datenanalyse und Prozessdesign (IDP)de_CH
dc.identifier.doi10.21256/zhaw-3823-
dc.identifier.doi10.1016/j.jaerosci.2018.05.012de_CH
zhaw.funding.euNode_CH
zhaw.originated.zhawYesde_CH
zhaw.pages.end16de_CH
zhaw.pages.start1de_CH
zhaw.parentwork.editorBiswas, Pratim-
zhaw.parentwork.editorChoi, Mansoo-
zhaw.parentwork.editorWeber, Alfred-
zhaw.publication.statuspublishedVersionde_CH
zhaw.volume123de_CH
zhaw.publication.reviewPeer review (Publikation)de_CH
zhaw.webfeedDatalabde_CH
zhaw.funding.zhawEin Modell basierter Zweistufenklassifikator für Schwebestaubde_CH
Appears in collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
JAS-2-stage-classifier.pdfPaper2.81 MBAdobe PDFThumbnail
View/Open
JAS-Supplement1.pdfBiplots of Si-Ca-Na-Cl main class431.58 kBAdobe PDFThumbnail
View/Open
JAS-Supplement2-TrainingData.pdfClassification of all particles in training set1.84 MBAdobe PDFThumbnail
View/Open
JAS-Supplement3.xlsxCenters of all main classes55.68 kBMicrosoft Excel XMLView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.