A new automated spectral feature extraction method and its application in spectral classification and defective spectra recovery

A new automated spectral feature extraction method and its application in spectral classification and defective spectra recovery
复制标题

一种新的自动化光谱特征提取方法及其在光谱分类和缺陷光谱恢复中的应用

DOI:
10.1093/mnras/stw2894
复制
发表时间:
2017-03
影响因子:
4.8
通讯作者:
Luo A-Li
Luo A-Li
中科院分区:
物理与天体物理2区
文献类型:
--
作者:
Wang Ke;Guo Ping;Luo A-Li

文献摘要

参考文献

被引文献

相似文献

光谱特征提取是自动光谱分析的关键步骤。这一程序从光谱数据开始,产生信息量大且无冗余的特征,便于随后利用机器学习和数据挖掘技术进行自动化处理和分析。本文提出了一种新的天文光谱自动特征提取方法,并将其应用于光谱分类和缺陷光谱恢复中。该方法的基本思想是训练一个深度神经网络,在不同的层次上提取不同抽象程度的光谱特征。用一种快速的分层学习算法以解析的方式训练深度神经网络,而不需要任何迭代优化过程。我们在真实世界的光谱数据上对该方案的性能进行了评估。结果表明,该方法在综合性能上优于其他方法,且计算量明显低于其他方法。该方法为光谱数据分析中的各种任务提供了一种新的有效的通用特征提取方法。
Spectral feature extraction is a crucial procedure in automated spectral analysis. This procedure starts from the spectral data and produces informative and non-redundant features, facilitating the subsequent automated processing and analysis with machine-learning and data-mining techniques. In this paper, we present a new automated feature extraction method for astronomical spectra, with application in spectral classification and defective spectra recovery. The basic idea of our approach is to train a deep neural network to extract features of spectra with different levels of abstraction in different layers. The deep neural network is trained with a fast layer-wise learning algorithm in an analytical way without any iterative optimization procedure. We evaluate the performance of the proposed scheme on real-world spectral data. The results demonstrate that our method is superior regarding its comprehensive performance, and the computational cost is significantly lower than that for other methods. The proposed method can be regarded as a new valid alternative general-purpose feature extraction method for various tasks in spectral data analysis.
DOI: 10.1093/mnras/stu642
发表时间: 2014-06-01
影响因子: 4.8
作者:
Graff, Philip;Feroz, Farhan;Lasenby, Anthony
通讯作者: Lasenby, Anthony
DOI: 10.5555/1756006.1953039
发表时间: 2010-03
期刊: J. Mach. Learn. Res.
影响因子: --
作者:
Pascal Vincent;H. Larochelle;Isabelle Lajoie;Yoshua Bengio;Pierre-Antoine Manzagol
通讯作者: Pascal Vincent;H. Larochelle;Isabelle Lajoie;Yoshua Bengio;Pierre-Antoine Manzagol
郭守敬望远镜(LAMOST)的相对通量校准
DOI: 10.1088/1674-4527/12/4/009
发表时间: 2012-01
影响因子: 1.8
作者:
Song, Yi-Han;Zhao, Yong-Heng;Luo, A-Li;Comte, Georges;Bai, Zhong-Rui;Zhang, Jian-Nan;Du, Wei;Zhang, Hao-Tong;Chen, Jian-Jun;Zuo, Fang
通讯作者: Zuo, Fang
DOI: --
发表时间: 2011
期刊: --
影响因子: --
作者:
A. Krizhevsky;Geoffrey E. Hinton
通讯作者: A. Krizhevsky;Geoffrey E. Hinton
DOI: 10.1051/0004-6361/201016422
发表时间: 2012-02
影响因子: 6.5
作者:
S. Navarro;R. Corradi;A. Mampaso
通讯作者: S. Navarro;R. Corradi;A. Mampaso