cqu_3877+SOURCE1+SOURCE1.4.pdf (73.18 kB)
Download fileArtificial neural network techniques for analysis of ion backscattering spectra
conference contribution
posted on 2017-12-06, 00:00 authored by Minmei LiMinmei Li, Xiaolong FanXiaolong Fan, Brijesh Verma, Ronald BalsysRonald Balsys, D O'ConnorIon backscattering spectrometry is an analysis technology that is dedicated to the compositional analysis of samples with the thickness of μm level. The problem of spectral data analysis, which is to determine the sample structure from the measured spectra, is generally ill-posed. In this study, artificial neural network (ANN) techniques have been developed for spectral data analysis. A multilayer feedforward neural network was constructed and applied to the specific case of SiGe thin films on a silicon substrate. The network was trained by the resilient backpropagation algorithm with hundreds of simulated spectra of samples for which the structures are known. Then the trained network was applied to analyse spectra with unknown structure of samples. The ANN prediction results are excellent. The constructed neural network can handle properly redundancies, which were caused by the constraint of output variables.
Funding
Category 1 - Australian Competitive Grants (this includes ARC, NHMRC)
History
Start Page
1End Page
7Number of Pages
7Start Date
2005-01-01ISBN-10
1932415661Location
Las Vegas, USAPublisher
CSREA PressPlace of Publication
Las VegasPeer Reviewed
- Yes
Open Access
- No
Era Eligible
- Yes