Use of pattern recognition tools for classifying particles into homogeneous groups

Abstract

Computer-controlled scanning electron microscopy (CCSEM) permits the characterization of size, shape, and composition of individual particles and thus provides a rich source of data to identify the origin of ambient airborne particles. The problem is how to make best use of this information. The general procedure has been to assign each particle to a class of similar particles based on its x-ray fluorescence spectrum. The initial efforts developed the class characteristics and classification rules in an empirical fashion. Recent studies have suggested that greater specificity and precision in the subsequent class balance analysis can be obtained if particle classes are more homogeneous.Data screening and transformation are the initial steps in the analysis procedure. Noise reduction is the first step in analyzing the CCSEM data. Determination of elemental chemistry for individual particles is accomplished by collection of characteristic X-rays. The X-ray fluorescence peaks are obtained as a result of a photon counting process having a Poissonian distribution.