Back to Search
Start Over
Predicting the onset temperature (T g ) of Ge x Se 1- x glass transition: a feature selection based two-stage support vector regression method.
- Source :
-
Science bulletin [Sci Bull (Beijing)] 2019 Aug 30; Vol. 64 (16), pp. 1195-1203. Date of Electronic Publication: 2019 Jul 02. - Publication Year :
- 2019
-
Abstract
- Despite the usage of both experimental and topological methods, realizing a rapid and accurate measurement of the onset temperature (T <subscript>g</subscript> ) of Ge <subscript>x</subscript> Se <subscript>1-</subscript> <subscript>x</subscript> glass transition remains an open challenge. In this paper, a predictive model for the T <subscript>g</subscript> in Ge <subscript>x</subscript> Se <subscript>1-</subscript> <subscript>x</subscript> glass system is presented by a machine learning method named feature selection based two-stage support vector regression (FSTS-SVR). Firstly, Pearson correlation coefficient (PCC) is used to select features highly correlated with T <subscript>g</subscript> from the candidate features of Ge <subscript>x</subscript> Se <subscript>1-</subscript> <subscript>x</subscript> glass system. Secondly, in order to simulate the two-stage characteristic of T <subscript>g</subscript> which is caused by structural variation with a turning point at x = 0.33 via the structural analysis, SVR is utilized to build predictive models for two stages separately and then the two achieved models are synthesized using a minimum error based model for T <subscript>g</subscript> prediction. Compared with the topological and other methods based on SVR, the FSTS-SVR gives the highest predictive accuracy with the root mean square error (RMSE) and mean absolute percentage error (MAPE) of 10.64 K and 2.38%, respectively. This method is also expected to be more efficient for the prediction of T <subscript>g</subscript> of other glass systems with the multi-stage characteristic.<br /> (Copyright © 2019 Science China Press. Published by Elsevier B.V. All rights reserved.)
Details
- Language :
- English
- ISSN :
- 2095-9281
- Volume :
- 64
- Issue :
- 16
- Database :
- MEDLINE
- Journal :
- Science bulletin
- Publication Type :
- Academic Journal
- Accession number :
- 36659690
- Full Text :
- https://doi.org/10.1016/j.scib.2019.06.026