Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-3823
Publication type: | Article in scientific journal |
Type of review: | Peer review (publication) |
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 |
DOI: | 10.21256/zhaw-3823 10.1016/j.jaerosci.2018.05.012 |
Published in: | Journal of Aerosol Science |
Editors of the parent work: | Biswas, Pratim Choi, Mansoo Weber, Alfred |
Volume(Issue): | 123 |
Page(s): | 1 |
Pages to: | 16 |
Issue Date: | 22-May-2018 |
Publisher / Ed. Institution: | Elsevier |
ISSN: | 0021-8502 |
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. |
URI: | https://digitalcollection.zhaw.ch/handle/11475/7549 |
Fulltext version: | Published version |
License (according to publishing contract): | CC BY 4.0: Attribution 4.0 International |
Departement: | School of Engineering |
Organisational Unit: | Institute of Data Analysis and Process Design (IDP) |
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 | Size | Format | |
---|---|---|---|---|
JAS-2-stage-classifier.pdf | Paper | 2.81 MB | Adobe PDF | View/Open |
JAS-Supplement1.pdf | Biplots of Si-Ca-Na-Cl main class | 431.58 kB | Adobe PDF | View/Open |
JAS-Supplement2-TrainingData.pdf | Classification of all particles in training set | 1.84 MB | Adobe PDF | View/Open |
JAS-Supplement3.xlsx | Centers of all main classes | 55.68 kB | Microsoft Excel XML | View/Open |
Show full item record
Meier, M. F., Mildenberger, T., Locher, R., Rausch, J., Zünd, T., Neururer, C., Ruckstuhl, A., & Grobéty, B. (2018). A model based two-stage classifier for airborne particles analyzed with computer controlled scanning electron microscopy. Journal of Aerosol Science, 123, 1–16. https://doi.org/10.21256/zhaw-3823
Meier, M.F. et al. (2018) ‘A model based two-stage classifier for airborne particles analyzed with computer controlled scanning electron microscopy’, Journal of Aerosol Science. Edited by P. Biswas, M. Choi, and A. Weber, 123, pp. 1–16. Available at: https://doi.org/10.21256/zhaw-3823.
M. F. Meier et al., “A model based two-stage classifier for airborne particles analyzed with computer controlled scanning electron microscopy,” Journal of Aerosol Science, vol. 123, pp. 1–16, May 2018, doi: 10.21256/zhaw-3823.
MEIER, Mario Federico, Thoralf MILDENBERGER, René LOCHER, Juanita RAUSCH, Thomas ZÜND, Christoph NEURURER, Andreas RUCKSTUHL und Bernard GROBÉTY, 2018. A model based two-stage classifier for airborne particles analyzed with computer controlled scanning electron microscopy. Pratim BISWAS, Mansoo CHOI und Alfred WEBER (Hrsg.), Journal of Aerosol Science. 22 Mai 2018. Bd. 123, S. 1–16. DOI 10.21256/zhaw-3823
Meier, Mario Federico, Thoralf Mildenberger, René Locher, Juanita Rausch, Thomas Zünd, Christoph Neururer, Andreas Ruckstuhl, and Bernard Grobéty. 2018. “A Model Based Two-Stage Classifier for Airborne Particles Analyzed with Computer Controlled Scanning Electron Microscopy.” Edited by Pratim Biswas, Mansoo Choi, and Alfred Weber. Journal of Aerosol Science 123 (May): 1–16. https://doi.org/10.21256/zhaw-3823.
Meier, Mario Federico, et al. “A Model Based Two-Stage Classifier for Airborne Particles Analyzed with Computer Controlled Scanning Electron Microscopy.” Journal of Aerosol Science, edited by Pratim Biswas et al., vol. 123, May 2018, pp. 1–16, https://doi.org/10.21256/zhaw-3823.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.