Exploration of Approach to Mining WDMS Spectra based on Laplacian Eigenmap and Neural Network

DOI

10.2991/icecee-15.2015.187How to use a DOI?

Keywords

Laplacian Eigenmap; Data mining; BPNN

Abstract

For the purpose of discovering White Dwarf +Main Sequence (WDMS) from massive spectra, in this paper, an unsupervised learning algorithm for Nonlinear Dimensionality Reduction named Laplacian Eigenmap is discussed. It turns out that, comparing with Principle Component Analysis (PCA), Laplacian Eigenmap maintains the information of nonlinear structure of high dimensional spectral data, which leads to a higher classification accuracy. In the feature space, backpropagation neural network is used to classify WDMS and non-WDMS spectra. Furthermore, Particle Swarm Optimization (PSO) is implemented to increase the classification accuracy via optimizing the parameters of the network. The results shows that the method in this paper can discover WDMS efficiently and accurately after training the neural network with low-dimensional data from Sloan Digital Sky Survey Data Release 10 (SDSS-DR10).

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Bin Jiang
AU  - Zixuan Li
AU  - Wenyu Wang
AU  - Meixia Qu
PY  - 2015/06
DA  - 2015/06
TI  - Exploration of Approach to Mining WDMS Spectra based on Laplacian Eigenmap and Neural Network
BT  - Proceedings of the 2015 International Conference on Electrical, Computer Engineering and Electronics
PB  - Atlantis Press
SP  - 986
EP  - 991
SN  - 2352-538X
UR  - https://doi.org/10.2991/icecee-15.2015.187
DO  - 10.2991/icecee-15.2015.187
ID  - Jiang2015/06
ER  -