Premium
AXIS: Automated XRF Interpretation of Spectra
Author(s) -
Abbott P. H.,
Adams M. J.
Publication year - 1997
Publication title -
x‐ray spectrometry
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.447
H-Index - 45
eISSN - 1097-4539
pISSN - 0049-8246
DOI - 10.1002/(sici)1097-4539(199705)26:3<125::aid-xrs222>3.0.co;2-g
Subject(s) - fuzzy logic , interpretation (philosophy) , expert system , computer science , software , table (database) , heuristic , data mining , artificial intelligence , identification (biology) , noise (video) , software system , pattern recognition (psychology) , algorithm , programming language , image (mathematics) , botany , biology
Modern x‐ray fluorescence instruments are highly sophisticated analytical tools. However, the interpretation software available with such instruments generally provides for little more than a computerized look‐up table with reliance on operator experience to provide plausible identification of spectral features. The system described (AXIS) overcomes some frequently encountered problems by appropriate application of heuristic interpretation (expert system), fuzzy logic and pattern recognition. Spectral noise and instrumental inaccuracies are handled by generation and propagation of uncertainty using fuzzy logic algorithms, and fuzzy c‐means pattern recognition furnishes the system with the ability to develop background knowledge from previously recorded similar spectra. The analytical results are presented graphically in the form of a hierarchical data tree, and the software can form the basis of a fully automated XRF interpretation system. © 1997 by John Wiley & Sons, Ltd.