HYPERSPECTRAL DATA FEATURE EXTRACTION USING DEEP BELIEF NETWORK

Publications

Share / Export Citation / Email / Print / Text size:

International Journal on Smart Sensing and Intelligent Systems

Professor Subhas Chandra Mukhopadhyay

Exeley Inc. (New York)

Subject: Computational Science & Engineering, Engineering, Electrical & Electronic

GET ALERTS

eISSN: 1178-5608

DESCRIPTION

8
Reader(s)
18
Visit(s)
0
Comment(s)
0
Share(s)

VOLUME 9 , ISSUE 4 (December 2016) > List of articles

HYPERSPECTRAL DATA FEATURE EXTRACTION USING DEEP BELIEF NETWORK

Jiang Xinhua / Xue Heru / Zhang Lina / Zhou Yanqing

Keywords : Hyperspectral, Feature extraction, Deep learning, Deep belief network, Restricted boltzman machines

Citation Information : International Journal on Smart Sensing and Intelligent Systems. Volume 9, Issue 4, Pages 1,991-2,009, DOI: https://doi.org/10.21307/ijssis-2017-949

License : (CC BY-NC-ND 4.0)

Received Date : 15-July-2016 / Accepted: 26-October-2016 / Published Online: 01-December-2016

ARTICLE

ABSTRACT

Hyperspectral data has rich spectrum information, strong correlation between bands and
high data redundancy. Feature band extraction of hyperspectral data is a prerequisite and an important
basis for the subsequent study of classification and target recognition. Deep belief network is a kind of
deep learning model, the paper proposed a deep belief network to realize the characteristics band
extraction of hyperspectral data, and use the advantages of unsupervised and supervised learning of
deep belief network, and to extract feature bands of spectral data from low level to high-level gradually.
The extracted feature band has a stronger discriminant performance, so that it can better to classify
hyperspectral data. Finally, the AVIRIS data is used to extract the feature band, and the SVM classifier
is used to classify the data, which verifies the effectiveness of the method.

Content not available PDF Share

FIGURES & TABLES

REFERENCES

[1] JIA X, KUO B C, and CRAWFORD M M. Feature mining for Hyper-spectral image
classification[J]. Proceedings of the IEEE, 2013, 101(3):676-697.
[2] Wang Liping. FEATURE SELECTION ALGORITHM BASED ON CONDITIONAL
DYNAMIC MUTUAL INFORMATION [J].INTERNATIONAL JOURNAL ON SMART
SENSING AND INTELLIGENT SYSTEMS, 2015, 8(1):316-337
[3] HUO LEI-GANG, FENG XIANG-CHU. Denoising of Hyperspectral Remote Sensing Image
Based on Principal Component Analysis and Dictionary Learning[J]. Journal of Electronics &
Information Technology,2014,36(11):2723-2729.
[4] CHENG SHU-XI, XIE CHUAN-QI, WANG QIAO-NAN, et al. Different Wavelengths
Selection Methods for Identification of Early Blight on Tomato Leaves By Using Hyperspectral
Imaging Technique[J]. Spectroscopy and Spectral Analysis,2014,34(5):1362-1366.
[5] FAN LIHENG, LV JUNWEI, and DENG JIANGSHENG. Classification of Hyperspectral
Remote Sensing Images Based on Bands Grouping and Classification Ensembles[J]. ACTA
OPTICA SINICA,2014,VOl.34,No.9:1-11.
[6] CHERIYADAT A, BRUCE L. Why principal component analysis is not an appropriate
feature extraction method for hyperspectral data[J].Proceeding of IEEE Geoscience and Remote
Sensing Symposium(IGARSS),2003,104(2):3420-3422.
[7] SUN KANG, GENG XIURUI, TANG HAIRONG, et al. A New Target Detection Method
Using Nonlinear PCA for Hyperspectral Imagery [J].Bulletin of Surveying and Mapping,
2015(1):105-108.
[8] LIU JING. Kernel Direct LDA Subspace Hyperspectral Image Terrain
Classification[J].Computer Science,2012,39(6): 274-277.
[9] DC FENG, F CHEN, and XU WEN-LI. Detecting Local Manifold Structure for Unsupervised
Feature Selection [J]. Acta Automatica Sinica, 2014, 40(10):2253-2261.
[10] S ZHOU, K TAN, and L WU. Hyperspectral Image Classification based on ISOMAP
Algorithm using Neighborhood Distance[J].Remote Sensing Technology & Application, 2014,
29(4):695-700.
[11] L YAN, DP ROY. Improved time series land cover classification by missing-observationadaptive
nonlinear dimensionality reduction[J].Remote Sensing of Environment, 2015, 158:478-
491.
[12] W SUN, C LIU, B SHI, et al. Dimensionality Reduction with Improved Local Tangent
Space Alignment for Hyperspectral Imagery Classification [J].Journal of Tongji University, 2014,
42(1):0124-0130.
[13] HINTON G, OSINDERO S, and TEH Y W. A fast learning algorithm for deep belief nets
[J].Neural computation, 2006, 18(7):1527-1554.
[14] HINTON, GEOFFREY E, and RUSLAN R. Reducing the Dimensionality of Data with
Neural Networks [J].Science, 2006, 313(5786):504-507.
[15] YANGYAN LI, HAO SU, CHARLES RUIZHONGTAI QI, et al. Joint embeddings of
shapes and images via CNN image purification [J]. Acm Transactions on Graphics, 2015,
34(6):1-12.
[16]HINTON G, DENG L, YU D, et al. Deep Neural Networks for Acoustic Modeling in Speech
Recognition [J]. IEEE Signal Processing Magazine, 2012, 29(6): 82-97.
[17]DAHL G E, YU D, DENG L, et al. Context-Dependent Pre-trained Deep Neural Networks
for Large-Vocabulary Speech Recognition [J]. IEEE Trans on Audio, Speech and Language
Processing, 2012,20(1):30-42.
[18] J XIE, L ZHANG, J YOU, et al. Effective texture classification by texton encoding induced
statistical features [J]. Pattern Recognition, 2015, 48(2):447–457.
[19]MNIH V, HINTON G E. Learning to Detect Roads in High-Resolution Aerial Images [J].
Lecture Notes in Computer Science, 2010, 6316:210-223.
[20] HINTON G E,SEJNOWSKI T J. Optimal perceptual inference[C].Proceedings of the
IEEE conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 1983:
448-453.
[21] RD HJELM, VD CALHOUN, R SALAKHUTDINOV, et al. Restricted Boltzmann
machines for neuroimaging: an application in identifying intrinsic networks[J]. Neuroimage,
2014, 96(8):245-260.
[22] LE ROUX, NICOLAS, YOSHUA BENGIO. Representational power of restricted
boltzmann machines and deep belief networks[J]. Neural Computation, 2008, 20(6): 1631-1649.
[23] J BA, R GROSSE, R SALAKHUTDINOV, et al. Learning Wake-Sleep Recurrent Attention
Models[J]. Conference on Neural Information Processing Systems, Canada, 2015:1-9.
[24] YOSHUA BENGIO, PASCAL LAMBLIN, DAN POPOVICI, et al. Greedy layer-wise
training of deep networks[C]. Advances in Neural Information Processing Systems 19 (NIPS
2006).Vancouver, 2007: 153-160.
[25] HINTON G E. A Practical Guide to Training Restricted Boltzmann Machines[R], Montreal:
Department of Computer Science, University of Toronto, 2010
[26] HINTON G E. Training products of experts by minimizing contrastive divergence[J]. Neural
Computation, 2002, 14(8):1771-1800.
[27] LE ROUX, NICOLAS, YOSHUA BENGIO. Representational power of restricted
boltzmann machines and deep belief networks [J]. Neural Computation, 2008, 20(6): 1631-1649.
[28] ZHANG CHUN-XIA, JI NAN-NAN, and WANG GUAN-WEI. Restricted Boltzmann
Machines[J]. Chinese Journal of Engineering Mathematics, 2015, 32(2):159-173.
[29] RN LE, Y BENGIO. Representational power of restricted boltzmann machines and deep
belief networks [J]. Neural Computation, 2008, 20(6):1631-1649.
[30] H LAROCHELLE, Y BENGIO, LOURADOUR, et al. Exploring Strategies for Training
Deep Neural Networks [J]. Journal of Machine Learning Research, 2009, 10(6):1-40.
[31] Yongqing Wang,Yanzhou Zhang. NOVEL MULTI-CLASS SVM ALGORITHM FOR
MULTIPLE OBJECT RECOGNITION[J].INTERNATIONAL JOURNAL ON SMART
SENSING AND INTELLIGENT SYSTEMS,2015,8(2):1203-1224
[32] Yongqing Wang, Xiling Liu. FACE RECOGNITION BASED ON IMPROVED SUPPORT
VECTOR CLUSTERING[J].INTERNATIONAL JOURNAL ON SMART SENSING AND
INTELLIGENT SYSTEMS,2014,7(4):1807-1829

EXTRA FILES

COMMENTS