Abstract
Abstract Inductively coupled plasma-atomic emission spectrometric determination of the concentrations of aluminum, barium, calcium, iron, magnesium, managanese, sodium, strontium, and titanium in 184 colorless container and sheet glasses was used to evaluate classification procedures for these two classes of glass. Effective two-dimensional visualization of the classification results is afforded by principal components analysis of the data with correct classification of 180 of the 184 samples. Good discrimination among sources of glass within a class is provided using hierarchical, unsupervised clustering. Individual manufacturing plants of a common container glass can be distinguished in most instances.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have