AIRBORNE PARTICLE CLASSIFICATION WITH A COMBINATION OF CHEMICAL-COMPOSITION AND SHAPE INDEX UTILIZING AN ADAPTIVE RESONANCE ARTIFICIAL NEURAL-NETWORK

Airborne particle classification that leads to particle source identification is important to both the improvement of the environment and the protection of public health. In this study, individual airborne particles were analyzed using a computer-controlled scanning electron microscope (CCSEM). It was found that a more accurate particle classification can be obtained when it is based on both the chemical compositions and a shape index of the individual particles compared to one that is based only on the chemical compositions. This study also demonstrated that a newly developed adaptive resonance artificial neural network system (ART2A) has a high potential value in particle classification. The ART2A system can identify new cluster(s) for the unknown particles and dynamically update the particle class library. Thus, it provides a way to both identify and further investigate new sources for the airborne particles.