Premium
Focusing on one component each time—comparison of single and multiple component prediction algorithms in artificial neural networks for x‐ray fluorescence analysis
Author(s) -
Luo Liqiang,
Ji Ang,
Ma Guangzu,
Guo Changlin
Publication year - 1998
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(199801/02)27:1<17::aid-xrs240>3.0.co;2-z
Subject(s) - overfitting , component (thermodynamics) , principal component analysis , algorithm , artificial neural network , computer science , component analysis , multivariate statistics , mean squared prediction error , artificial intelligence , independent component analysis , pattern recognition (psychology) , machine learning , physics , thermodynamics
An algorithm of single component prediction based on backward error propagation is proposed, in which only one component concentration in a multivariate system is predicted each time. The algorithm was compared with a multiple component prediction model. In general, the predictive accuracy of the single component prediction algorithm was superior to that of the multiple component prediction model. The effects of overfitting, standard samples and model parameters on the predictive accuracy were also examined. © 1998 John Wiley & Sons, Ltd.