Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen: https://doi.org/10.21256/zhaw-3823
Titel: A model based two-stage classifier for airborne particles analyzed with computer controlled scanning electron microscopy
Autoren: Meier, Mario Federico
Mildenberger, Thoralf
Locher, René
Rausch, Juanita
Zünd, Thomas
Neururer, Christoph
Ruckstuhl, Andreas
Grobéty, Bernard
Erschienen in: Journal of Aerosol Science
Band(Heft): 123
Seiten: 1
Seiten bis: 16
Herausgeber des übergeordneten Werkes: Biswas, Pratim
Choi, Mansoo
Weber, Alfred
Verlag / Hrsg. Institution: Elsevier
Erscheinungsdatum: 22-Mai-2018
Lizenz (gemäss Verlagsvertrag): CC BY 4.0: Namensnennung 4.0 International
Art der Begutachtung: Peer review (Publikation)
Sprache: Englisch
Schlagwörter: Cluster analysis; Two-stage classifier; Rule based classifier; Model based classifier; Compositional data; Isometrical log-ratio transform; Aerosol measurement; Single particle analysis; Source apportionment
Fachgebiet (DDC): 540: Chemie
570: Biologie
Zusammenfassung: Computer 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.
Departement: School of Engineering
Organisationseinheit: Institut für Datenanalyse und Prozessdesign (IDP)
Publikationstyp: Beitrag in wissenschaftlicher Zeitschrift
DOI: 10.1016/j.jaerosci.2018.05.012
10.21256/zhaw-3823
ISSN: 0021-8502
URI: https://digitalcollection.zhaw.ch/handle/11475/7549
Publiziert im Rahmen des ZHAW-Projekts: Ein Modell basierter Zweistufenklassifikator für Schwebestaub
Enthalten in den Sammlungen:Publikationen School of Engineering

Dateien zu dieser Ressource:
Datei Beschreibung GrößeFormat 
JAS-2-stage-classifier.pdfPaper2.81 MBAdobe PDFMiniaturbild
Öffnen/Anzeigen
JAS-Supplement1.pdfBiplots of Si-Ca-Na-Cl main class431.58 kBAdobe PDFMiniaturbild
Öffnen/Anzeigen
JAS-Supplement2-TrainingData.pdfClassification of all particles in training set1.84 MBAdobe PDFMiniaturbild
Öffnen/Anzeigen
JAS-Supplement3.xlsxCenters of all main classes55.68 kBMicrosoft Excel XMLÖffnen/Anzeigen


Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.