DOI: 10.1039/A608166E
(Paper)
Reference Section for: J. Anal. At. Spectrom., 1997, 12, 827-831
Pattern Recognition for Sample Classification Using Elemental Composition—Application for Inductively Coupled Plasma Atomic Emission Spectrometry
(Note: The full text of this document is currently only available in the PDF Version )
CHRISTINE SARTOROS and ERIC D. SALIN
Abstract
Three pattern recognition techniques were investigated as tools for automatic recognition of samples:k-Nearest Neighbors, Bayesian Classification and the C4.5 inductive learning algorithm. Their abilities to classify 20 geological reference materials were compared. Each training and test example used 13 elemental concentrations. The data set was composed of 2582 examples obtained from CANMET in the form of results of analyses performed on these reference materials by different laboratories. It was found that all three pattern recognition techniques performed extremely well with a large data set of real samples. Bayesian Classification and k-Nearest Neighbors worked very well with small data sets.
References
- D. P. Webb, J. Hamier and E. D. Salin, Trends Anal. Chem., 1994, 13, 44 CrossRef CAS.
- D. P. Webb and E. D. Salin, Intelligent Instruments and Computers, 1992, 5, 185 Search PubMed.
- W. Branagh, H. Yu and E. D. Salin, Appl. Spectrosc., 1995, 49(7), 964 CAS.
- W. Branagh and E. D. Salin, Spectroscopy, 1995, 10, 20 Search PubMed.
- M. A. Sharaf, D. L. Illman and B. R. Kowalski, Chemometrics, John Wiley, New York, 1986 Search PubMed.
- R. O. Duda and P. E. Hart, Pattern Classification and Scene Analysis, John Wiley, Toronto, 1973 Search PubMed.
- J. R. Quinlan, C4.5 Algorithms for Machine Learning, Morgan Kaufmann Publishers, San Mateo, 1993 Search PubMed.
- E. D. Salin and P. H. Winston, Anal. Chem., 1992, 64, 49A.