WANG Xuesong, KONG Yi, CHENG Yuhu. Dimensionality Reduction for Hyperspectral Data Based on Sample-Dependent Repulsion Graph Regularized Auto-encoder[J]. Chinese Journal of Electronics, 2017, 26(6): 1233-1238. doi: 10.1049/cje.2017.07.012
Citation: WANG Xuesong, KONG Yi, CHENG Yuhu. Dimensionality Reduction for Hyperspectral Data Based on Sample-Dependent Repulsion Graph Regularized Auto-encoder[J]. Chinese Journal of Electronics, 2017, 26(6): 1233-1238. doi: 10.1049/cje.2017.07.012

Dimensionality Reduction for Hyperspectral Data Based on Sample-Dependent Repulsion Graph Regularized Auto-encoder

doi: 10.1049/cje.2017.07.012
Funds:  This work is supported by National Natural Science Foundation of China (No.61273143, No.61472424).
More Information
  • Corresponding author: CHENG Yuhu (Corresponding author) received the Ph.D. degree from the Institute of Automation, Chinese Academy of Sciences in 2005. He is currently a professor in the School of Information and Control Engineering, China University of Mining and Technology.(Email:chengyuhu@163.com)
  • Received Date: 2015-08-12
  • Rev Recd Date: 2015-09-16
  • Publish Date: 2017-11-10
  • To achieve high classification accuracy of hyperspectral data, a dimensionality reduction algorithm called Sample-dependent repulsion graph regularized auto-encoder (SRGAE) is proposed. Based on the sample-dependent graph, by applying the repulsion force to the samples from different classes but nearby, a sampledependent repulsion graph is built to make the samples from the same class will be projected to samples that are close-by and the samples from different classes will be projected to samples that are far away. The sampledependent repulsion graph can avoid the neighborhood parameter selection problem existing in the nearest neighborhood graph. By integrating advantages of deep learning and graph regularization technique, the SRGAE can maintain the learned deep features are consistent with the inherent manifold structure of the original hyperspectral data. Experimental results on two real hyperspectral data show that, when compared with some popular dimensionality reduction algorithms, the proposed SRGAE can yield higher classification accuracy.
  • loading
  • G. Hughes, "On the mean accuracy of statistical pattern recognizers", IEEE Transactions on Information Theory, Vol.14, No.1, pp.55-63, 1968.
    C.I. Chang, Hyperspectral Data Exploitation:Theory and Applications, John Wiley & Sons, 2007.
    X.S. Wang, H.J. Hu and Y.H. Cheng "Dimensionality reduction of remote sensing image using semi-supervised discriminative locality alignment", Acta Electronica Sinica, Vol.42, No.1, pp.84-88, 2014. (in Chinese)
    C.I. Chang and H. Safavi, "Progressive dimensionality reduction by transform for hyperspectral imagery", Pattern Recognition, Vol.44, No.10, pp.2760-2773, 2011.
    C.L. Wen, F. Zhou, C.B. Wen, et al, "An extended multiscale principal component analysis method and application in anomaly detection", Chinese Journal of Electronics, Vol.21, No.3, pp.471-476, 2012.
    Y.W. Cheng and X.H. Han, "Classification of high-resolution satellite images using supervised locality preserving projections", Lectures Notes in Computer Science, Vol.5178, No.2, pp.149-156, 2008.
    T.V. Bandos, L. Bruzzone and G. Camps-Valls, "Classification of hyperspectral images with regularized linear discriminant analysis", IEEE Transactions on Geoscience and Remote Sensing, Vol.47, No.3, pp.862-873, 2009.
    W.K. Wong, "Discover latent discriminant information for dimensionality reduction:non-negative sparseness preserving embedding", Pattern Recognition, Vol.45, No.4, pp.1511-1523, 2012.
    Y. Bengio and O. Delalleau, "On the expressive power of deep architectures", Lectures Notes in Computer Science, Vol.6925, pp.18-36, 2011.
    Y.S. Chen, Z.H. Lin, X. Zhao, et al., "Deep learning-based classification of hyperspectral data", IEEE Journal of Selected Topics in Applied Earth Oberservations and Remote Sensing, Vol.7, No.6, pp.2094-2107, 2014.
    Y.S. Chen, X. Zhao and X.P. Jia, "Spectral-spatial classification of hyperspectral data based on deep belief network", IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol.8, No.6, pp.2381-2392, 2015.
    Y. Bengio, "Deep learning of representations for unsupervised and transfer learning", Proceedings of the International Conference on Machine Learning, Edinburgh, Scotland, pp.17-36, 2012.
    Z.J. Sun, L. Xu and Y.M. Xu "Marginal fisher feature extraction algorithm based on deep learning", Journal of Electronics & Information Technology, Vol.35, No.4, pp.805-811, 2013. (in Chinese)
    S.C. Yan, D. Xu, B.Y. Zhang, et al., "Graph embedding and extensions:a general framework for dimensionality reduction", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.29, No.1, pp.40-51, 2007.
    Y.Y. Liao, Y. Wang and Y. Liu, "Image representation learning using graph regularized auto-encoders", Proceedings of the International Conference on Learning Representations, Banff, Canada, pp.126-135, 2014.
    B. Yang and S. Chen, "Sample-dependent graph construction with application to dimensionality reduction", Neurocomputing, Vol.74, No.1, pp.301-314, 2010.
    E. Kokiopoulou and Y. Saad, "Enhanced graph-based dimensionality reduction with repulsion Laplacians", Pattern Recognition, Vol.42, No.11, pp.2392-2402, 2009.
    G.E. Hinton and R.R. Salakhutdinov, "Reducing the dimensionality of data with neural networks", Science, Vol.313, No.5786, pp.504-507, 2006.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article views (128) PDF downloads(336) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return