基于改进Kullback-Leibler散度稀疏自动编码机的战损评估

戚宗锋; 刘巧巧; 王军; 李建勋

doi:10.1631/FITEE.1601395

Your Location：

Home >

Browse articles >

基于改进Kullback-Leibler散度稀疏自动编码机的战损评估

常规文章 | Updated：2022-06-06

- 基于改进Kullback-Leibler散度稀疏自动编码机的战损评估
- Battle damage assessment based on an improved Kullback-Leibler divergence sparse autoencoder
- 信息与电子工程前沿（英文） 2017年18卷第12期页码：1991-2000
- Affiliations：
  
  State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, Luoyang 471003, China
  MOE Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai 200240, China
  Luoyang Electronic Equipment Test Center of China, Luoyang 471000, China
- Author bio：
  
  Jian-xun LI, E-mail: lijx@sjtu.edu.cn
- Funds：
  
  Project supported by the National Basic Research Program (973) of China (No. 61331903) and the National Natural Science Foundation of China (Nos. 61175008 and 61673265)
- DOI：10.1631/FITEE.1601395
  中图分类号： TP391.4;E917
- 收稿：2016-07-04，
  
  修回：2017-12-20，
  
  纸质出版：2017-12
- Accepted：
Scan QR Code
戚宗锋, 刘巧巧, 王军, 等. 基于改进Kullback-Leibler散度稀疏自动编码机的战损评估[J]. 信息与电子工程前沿（英文）, 2017,18(12):1991-2000.

QI Zong-feng, LIU Qiao-qiao, WANG Jun, et al. Battle damage assessment based on an improved Kullback-Leibler divergence sparse autoencoder[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(12): 1991-2000.
戚宗锋, 刘巧巧, 王军, 等. 基于改进Kullback-Leibler散度稀疏自动编码机的战损评估[J]. 信息与电子工程前沿（英文）, 2017,18(12):1991-2000. DOI： 10.1631/FITEE.1601395.

QI Zong-feng, LIU Qiao-qiao, WANG Jun, et al. Battle damage assessment based on an improved Kullback-Leibler divergence sparse autoencoder[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(12): 1991-2000. DOI： 10.1631/FITEE.1601395.

摘要

为解决深度学习网络中隐藏层节点数难以确定的问题，文中提出一种改进的KL（Kullback-Leibler）散度稀疏自动编码机，并将该方法应用到战斗损伤评估中。该方法能够自动筛选出对数据重建贡献大的隐层特征，舍弃贡献小的隐层特征，从而优化网络结构。在网络预测精度不受影响的前提下，该方法自动筛选隐层特征，提升了计算速度。基于UCI（University of California

Irvine）数据集和BDA（battle damage assessment）战争破坏数据的实验表明，该方法优于其他数据驱动的方法。改进的KL稀疏自动编码机回归网络在保证预测精度的前提下，能提升网络的训练和预测速度，并自动筛选隐层有效特征，优化隐层节点数，优化网络结构。

Abstract

The nodes number of the hidden layer in a deep learning network is quite difficult to determine with traditional methods. To solve this problem

an improved Kullback-Leibler divergence sparse autoencoder (KL-SAE) is proposed in this paper

which can be applied to battle damage assessment (BDA). This method can select automatically the hidden layer feature which contributes most to data reconstruction

and abandon the hidden layer feature which contributes least. Therefore

the structure of the network can be modified. In addition

the method can select automatically hidden layer feature without loss of the network prediction accuracy and increase the computation speed. Experiments on University of California-Irvine (UCI) data sets and BDA for battle damage data demonstrate that the method outperforms other reference data-driven methods. The following results can be found from this paper. First

the improved KL-SAE regression network can guarantee the prediction accuracy and increase the speed of training networks and prediction. Second

the proposed network can select automatically hidden layer effective feature and modify the structure of the network by optimizing the nodes number of the hidden layer.

关键词

Keywords

references

S.C. Cao , F. Zhang . Review of battle damage assessment . Mil. Econ. Res. , 2014 . ( 8 ): 53 - 56 . .

X. Chen , L. Li , D. Liu . Battle damage level prediction on fuzzy theory and Bayesian method . IEEE Conf. on Robotics, Automation and Mechatronics , 2011 . p.295 - 298 . DOI: 10.1109/RAMECH.2011.6070499 http://doi.org/10.1109/RAMECH.2011.6070499 .

Y. Ding , N. Li , Y. Zhao , 等 . Image quality assessment method based on nonlinear feature extraction in kernel space . Front. Inform. Technol. Electron. Eng. , 2016 . 17 ( 10 ): 1008 - 1017 . DOI: 10.1631/FITEE.1500439 http://doi.org/10.1631/FITEE.1500439 .

T. Hastie , R. Tibshirani , J. Friedman . The Elements of Statistical Learning (2nd Ed.) , : Springer, New York, USA. 2009 . DOI: 10.1007/978-0-387-84858-7 http://doi.org/10.1007/978-0-387-84858-7 .

D.W. Hosmer , S. Lemeshow . Applied Logistic Regression (2nd Ed.) , : John Wiley & Sons, New York, USA. 2005 . DOI: 10.1002/0471722146 http://doi.org/10.1002/0471722146 .

D.H. Hubel , T.N. Wiesel . Receptive fields, binocular interaction and functional architecture in the cat's visual cortex . J. Physiol. , 1962 . 160 ( 1 ): 106 - 154 . .

F.V. Jensen , T.D. Nielsen . Bayesian Networks and Decision Graphs , : Springer, New York, USA. 2007 . DOI: 10.1007/978-0-387-68282-2 http://doi.org/10.1007/978-0-387-68282-2 .

N. Jiang , W.G. Rong , B.L. Peng , 等 . An empirical analysis of different sparse penalties for autoencoder in unsupervised feature learning . Int. Joint Conf. on Neural Networks , 2015 . p.1 - 8 . DOI: 10.1109/IJCNN.2015.7280568 http://doi.org/10.1109/IJCNN.2015.7280568 .

C.H. Li , J. Huang . The application of Bayesian network in battle damage assessment . IEEE Int. Conf. on Software Engineering and Service Science , 2014 . p.529 - 532 . DOI: 10.1109/ICSESS.2014.6933622 http://doi.org/10.1109/ICSESS.2014.6933622 .

X.M. Ma , P. Ding , W.D. Yan . Warship-damage assessment based on Bayesian networks . Ordnance Ind. Autom. , 2016 . 35 ( 6 ): 72 - 75 . DOI: 10.7690/bgzdh.2016.06.017 http://doi.org/10.7690/bgzdh.2016.06.017 .

Z.J. Ma , Q. Shi , B. Li . Battle damage assessment based on Bayesian network . 8th ACIS Int. Conf. on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing , 2007 . p.388 - 391 . DOI: 10.1109/SNPD.2007.421 http://doi.org/10.1109/SNPD.2007.421 .

F.W. Qin , L.Y. Li , S.M. Gao , 等 . A deep learning approach to the classification of 3D CAD models . J. Zhejiang Univ.-Sci. C (Comput. & Electron.) , 2014 . 15 ( 2 ): 91 - 106 . DOI: 10.1631/jzus.C1300185 http://doi.org/10.1631/jzus.C1300185 .

S. Rifai , P. Vincent , X. Muller , 等 . Contractive auto-encoders: explicit invariance during feature extraction . 28th Int. Conf. on Machine Learning , 2011 . p.833 - 840 . .

G.A.F. Seber , A.J. Lee . Linear Regression Analysis (2nd Ed.) , : John Wiley & Sons, New York, USA. 2012 . DOI: 10.1002/9780471722199 http://doi.org/10.1002/9780471722199 .

G.H. Song , X.G. Jin , G.L. Chen , 等 . Two-level hierarchical feature learning for image classification . Front. Inform. Technol. Electron. Eng. , 2016 . 17 ( 9 ): 897 - 906 . DOI: 10.1631/FITEE.1500346 http://doi.org/10.1631/FITEE.1500346 .

G.L. Sun , J. Li . Battle damage assessment based on attribute weighted Bayesian classification . Ship Electron. Eng. , 2016 . 36 ( 1 ): 29 - 32 . DOI: 10.3969/j.issn.1672-9730.2016.01.009 http://doi.org/10.3969/j.issn.1672-9730.2016.01.009 .

C. Vens , J. Struyf , L. Schietgat , 等 . Decision trees for hierarchical multi-label classification . Mach. Learn. , 2008 . 73 185 - 214 . DOI: 10.1007/s10994-008-5077-3 http://doi.org/10.1007/s10994-008-5077-3 .

P. Vincent , H. Larochelle , I. Lajoie , 等 . Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion . J. Mach. Learn. Res. , 2010 . 11 ( 12 ): 3371 - 3408 . .

M.F. Wen , C. Hu , W.R. Liu . Heterogeneous multimodal object recognition method based on deep learning . J. Cent. South Univ. (Sci. Technol.) , 2016 . 47 ( 5 ): 1580 - 1586 . DOI: 10.11817/j.issn.1672-7207.2016.05.018 http://doi.org/10.11817/j.issn.1672-7207.2016.05.018 .

L.Y. Yong . Modeling in Battle Damage Based on Multi-agen . MS Thesis, Harbin University of Science and Technology, Harbin, China , 2004 .

C. Zhang , Q. Shi , T.L. Liu , 等 . Study on battle damage level prediction using hybrid-learning algorithm . 4th Int. Conf. on Computational and Information Sciences , 2012 . p.65 - 68 . DOI: 10.1109/ICCIS.2012.298 http://doi.org/10.1109/ICCIS.2012.298 .

Z.Y. Zhao , Y.X. Li , F. Yu , 等 . Improved deep learning algorithm based on extreme learning machine . Comput. Eng. Des. , 2015 . 36 ( 4 ): 1022 - 1026 . DOI: 10.16208/j.issn1000-7024.2015.04.036 http://doi.org/10.16208/j.issn1000-7024.2015.04.036 .

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Feature selection techniques for microarray datasets: a comprehensive review, taxonomy, and future directions

A software defect prediction method with metric compensation based on feature selection and transfer learning

Unsupervised feature selection via joint local learning and group sparse regression

FAAD: an unsupervised fast and accurate anomaly detection method for a multi-dimensional sequence over data stream

A new feature selection method for handling redundant information in text classification