𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Choice of Optimum Model Parameters in Artificial Neural Networks and Application to X-ray Fluorescence Analysis

✍ Scribed by Liqiang Luo; Changlin Guo; Guangzu Ma; Ang Ji

Publisher
John Wiley and Sons
Year
1997
Tongue
English
Weight
314 KB
Volume
26
Category
Article
ISSN
0049-8246

No coin nor oath required. For personal study only.

✦ Synopsis

The model parameters in artiÐcial neural networks have a great inÑuence on the training speed. It can be increased after choosing the optimum parameters, which was performed by a stepping technique. The training speed using the method is usually faster than that when adopting random or empirical parameters. An artiÐcial neural network model was used in multivariate matrix calibration and compared with cross-validation and partial least-squares methods, which were combined with the fundamental-parameters in x-ray Ñuorescence analysis. The results show that the artiÐcial neural network model produced the highest accuracy.

📜 SIMILAR VOLUMES

Focusing on one component each time—comp
Focusing on one component each time—comparison of single and multiple component prediction algorithms in artificial neural networks for x-ray fluorescence analysis
✍ Liqiang Luo; Ang Ji; Guangzu Ma; Changlin Guo 📂 Article 📅 1998 🏛 John Wiley and Sons 🌐 English ⚖ 438 KB 👁 2 views

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 si

Correction of Line Interference in X-Ray
Correction of Line Interference in X-Ray Fluorescence Trace Analysis. Application to Yttrium Determination in Silicate Rocks
✍ José Antonio Gásquez; Ernesto Perino; Eduardo Marchevsky; Roberto Olsina; Albert 📂 Article 📅 1997 🏛 John Wiley and Sons 🌐 English ⚖ 225 KB 👁 2 views

An empirical method is proposed for the correction of spectral interference between characteristic lines in XRF. The procedure is based on a coefficient which includes instrumental parameters and atomic properties and is obtained with the same standards as those used in calibration. This method has