Comparison of two cluster analysis methods using single particle mass spectra

被引：30

作者：

Zhao, Weixiang ^{[2
]}

Hopke, Philip K. ^{[1
]}

Prather, Kimberly A. ^{[3
]}

机构：

[1] Clarkson Univ, Ctr Air Resources Engn & Sci, Dept Chem & Biomol Engn, Potsdam, NY 13699 USA

[2] Univ Calif Davis, Dept Mech & Aeronaut Engn, Davis, CA 95618 USA

[3] Univ Calif San Diego, Dept Chem & Biochem, La Jolla, CA 92093 USA

来源：

ATMOSPHERIC ENVIRONMENT | 2008年 / 42卷 / 05期

关键词：

aerosol time-of-flight mass spectrometer; single particle; density-based cluster analysis; adaptive resonance theory neural networks; source identification;

D O I：

10.1016/j.atmosenv.2007.10.024

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

Cluster analysis of aerosol time-of-flight mass spectrometry (ATOFMS) data has been an effective tool for the identification of possible sources of ambient aerosols. In this study, the clustering results of two typical methods, adaptive resonance theory-based neural networks-2a (ART-2a) and density-based clustering of application with noise (DBSCAN), on ATOFMS data were investigated by employing a set of benchmark ATOFMS data. The advantages and disadvantages of these two methods are discussed and some feasible remedies proposed for problems encountered in the clustering process. The results of this study will provide promising directions for future work on ambient aerosol cluster analysis, suggesting a more effective and feasible clustering strategy based on the integration of ART-2a and DBSCAN. (c) 2007 Elsevier Ltd. All rights reserved.

引用

页码：881 / 892

页数：12

共 13 条

[1] Source apportionment of fine particulate matter by clustering single-particle data: Tests of receptor model accuracy [J].

Bhave, PV ;

Fergenson, DP ;

Prather, KA ;

Cass, GR .

ENVIRONMENTAL SCIENCE & TECHNOLOGY, 2001, 35 (10) :2060-2072

[2] ART 2-A - AN ADAPTIVE RESONANCE ALGORITHM FOR RAPID CATEGORY LEARNING AND RECOGNITION [J].

CARPENTER, GA ;

GROSSBERG, S ;

ROSEN, DB .

NEURAL NETWORKS, 1991, 4 (04) :493-504

[3] Representative subset selection [J].

Daszykowski, M ;

Walczak, B ;

Massart, DL .

ANALYTICA CHIMICA ACTA, 2002, 468 (01) :91-103

[4] Looking for natural patterns in data - Part 1. Density-based approach [J].

Daszykowski, M ;

Walczak, B ;

Massart, DL .

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2001, 56 (02) :83-92

[5] AN ASSOCIATION BETWEEN AIR-POLLUTION AND MORTALITY IN 6 UNITED-STATES CITIES [J].

DOCKERY, DW ;

POPE, CA ;

XU, XP ;

SPENGLER, JD ;

WARE, JH ;

FAY, ME ;

FERRIS, BG ;

SPEIZER, FE .

NEW ENGLAND JOURNAL OF MEDICINE, 1993, 329 (24) :1753-1759

[6]

Ester M., 1996, P 2 INT C KNOWL DISC, P226, DOI DOI 10.5555/3001460.3001507

[7] Quantification of ATOFMS data by multivariate methods [J].

Fergenson, DP ;

Song, XH ;

Ramadan, Z ;

Allen, JO ;

Hughes, LS ;

Cass, GR ;

Hopke, PK ;

Prather, KA .

ANALYTICAL CHEMISTRY, 2001, 73 (15) :3535-3541

[8] Application of the ART-2a algorithm to laser ablation aerosol mass spectrometry of particle standards [J].

Phares, DJ ;

Rhoads, KP ;

Wexler, AS ;

Kane, DB ;

Johnston, MV .

ANALYTICAL CHEMISTRY, 2001, 73 (10) :2338-2344

[9]

Sodeman DA, 2005, ENVIRON SCI TECHNOL, V39, P4569, DOI [10.1021/es0489947, 10.1021/eso0489947]

[10] Classification of single particles analyzed by ATOFMS using an artificial neural network, ART-2A [J].

Song, XH ;

Hopke, PK ;

Fergenson, DP ;

Prather, KA .

ANALYTICAL CHEMISTRY, 1999, 71 (04) :860-865

← 1 2 →