Please use this identifier to cite or link to this item:
Title: A model based two-stage classifier for airborne particles analyzed with computer controlled scanning electron microscopy
Authors : Meier, Mario Federico
Mildenberger, Thoralf
Locher, René
Rausch, Juanita
Zünd, Thomas
Neururer, Christoph
Ruckstuhl, Andreas
Grobéty, Bernard
Published in : Journal of Aerosol Science
Volume(Issue) : 123
Pages : 1
Pages to: 16
Editors of the parent work: Biswas, Pratim
Choi, Mansoo
Weber, Alfred
Publisher / Ed. Institution : Elsevier
Issue Date: 22-May-2018
License (according to publishing contract) : CC BY 4.0: Namensnennung 4.0 International
Type of review: Peer review (Publication)
Language : English
Subjects : Cluster analysis; Two-stage classifier; Rule based classifier; Model based classifier; Compositional data; Isometrical log-ratio transform; Aerosol measurement; Single particle analysis; Source apportionment
Subject (DDC) : 540: Chemistry
570: Biology
Abstract: 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
Organisational Unit: Institute of Data Analysis and Process Design (IDP)
Publication type: Article in scientific Journal
DOI : 10.1016/j.jaerosci.2018.05.012
ISSN: 0021-8502
Published as part of the ZHAW project : Ein Modell basierter Zweistufenklassifikator für Schwebestaub
Appears in Collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
JAS-2-stage-classifier.pdfPaper2.81 MBAdobe PDFThumbnail
JAS-Supplement1.pdfBiplots of Si-Ca-Na-Cl main class431.58 kBAdobe PDFThumbnail
JAS-Supplement2-TrainingData.pdfClassification of all particles in training set1.84 MBAdobe PDFThumbnail
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.