局部信息保持极限学习机的遥感图像分类
|
摘要
极限学习机ELM(Extreme learning machine)以其简单快速和良好的泛化能力在模式识别和机器学习领域得到了广泛的应用。近年来,研究人员将其应用到高光谱遥感图像分类问题中。然而,由于数据样本有限,极限学习机及其相关技术在遥感图像中存在数据学习不充分的问题。流形学习算法揭示了数据内在的几何结构信息。根据遥感图像的特点,基于流形学习的思想,将遥感图像数据样本的流行结构引入到ELM模型中,提出一种基于局部信息保持极限学习机LPKELM(locality information preserving extreme learning machine)。为了验证所提算法的有效性,使用两个高光谱遥感图像数据集进行实验。实验结果表明,LPKELM的分类性能优于SVM、KELM、KCRT-CK和MLR算法。
Extreme learning machine( ELM) has been widely used in pattern recognition and machine learning with its simple,fast,and good generalization abilities. In recent years,researchers have applied ELM to the area of hyperspectral remote sensing image classification. However,due to the limited data samples,ELM and its related technology have insufficient data learning in remote sensing images. Manifold learning method reveals the inherent geometric structure of data. According to the characteristics of remote sensing images and the idea of manifold learning,we introduced the manifold structure of remote sensing image data samples into ELM model,and proposed a local information preservation extreme learning machine( LPKELM). In order to verify the effectiveness of the proposed algorithm,two hyperspectral remote sensing image datasets were used to conduct experiment. Experimental results show that LPKELM is better than SVM,KELM,KCRT-CK and MLR algorithms in classification.
Extreme learning machine( ELM) has been widely used in pattern recognition and machine learning with its simple,fast,and good generalization abilities. In recent years,researchers have applied ELM to the area of hyperspectral remote sensing image classification. However,due to the limited data samples,ELM and its related technology have insufficient data learning in remote sensing images. Manifold learning method reveals the inherent geometric structure of data. According to the characteristics of remote sensing images and the idea of manifold learning,we introduced the manifold structure of remote sensing image data samples into ELM model,and proposed a local information preservation extreme learning machine( LPKELM). In order to verify the effectiveness of the proposed algorithm,two hyperspectral remote sensing image datasets were used to conduct experiment. Experimental results show that LPKELM is better than SVM,KELM,KCRT-CK and MLR algorithms in classification.
引文
[1]Yue Q,Ma C.Hyperspectral data classification based on flexible momentum deep convolution neural network[J].Multimedia Tools and Applications,2018,77(4):4417-4429.
[2]Li J,Marpu P R.Generalized Composite Kernel Framework for Hyperspectral Image Classification[J].IEEE Transactions on Geoscience and Remote Sensing,2013,51(9):4816-4829.
[3]Melgani F,Bruzzone L.Classification of hyperspectral remote sensing images with support vector machines[J].IEEETransactions on Geoscience and Remote Sensing,2004,42(8):1778-1790.
[4]Xie L,Li G Y,Xiao M,et al.Hyperspectral Image Classification Using Discrete Space Model and Support Vector Machines[J].IEEE Geoscience and Remote Sensing Letters,2017,14(3):374-378.
[5]Tarabalka Y,Benediktsson J A,Chanussot J.Spectral-spatial classification of hyperspectral imagery based on partitional clustering techniques[J].IEEE Transactions on Geoscience and Remote Sensing,2009,47(8):2973-2987.
[6]Quesada-Barriuso P,Arguello F.Spectral-Spatial Classification of Hyperspectral Images Using Wavelets and Extended Morphological Profiles[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(4):1177-1185.
[7]Gu Y F,Liu T Z,Jia X P.Nonlinear Multiple Kernel Learning With Multiple-Structure-Element Extended Morphological Profiles for Hyperspectral Image Classification[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(6):3235-3247.
[8]Pan L,Li H C,Meng H.Hyperspectral Image Classification via Low-Rank and Sparse Representation With Spectral Consistency Constraint[J].IEEE Geoscience and Remote Sensing Letters,2017,14(11):2117-2121.
[9]Yuan Y,Lin J Z,Wang Q.Hyperspectral Image Classification via Multitask Joint Sparse Representation and Stepwise MRF Optimization[J].IEEE Transactions on Cybernetics,2016,46(12):2966-2977.
[10]Wang Q,Lin J Z,Yuan Y.Salient Band Selection for Hyperspectral Image Classification via Manifold Ranking[J].IEEE Transactions on Neural Networks and Learning Systems,2016,27(6):1279-1289.
[11]Huang G B,Zhu Q Y,Siew C K.Extreme learning machine:theory and applications[J].Neurocomputing,2006,70(1):489-501.
[12]Tang J,Deng C,Huang G B.Extreme learning machine for multilayer perceptron[J].IEEE Transactions on Neural Networks and Learning Systems,2016,27(4):809-821.
[13]Huang G B,Zhou H M,Ding X J,et al.Extreme learning machine for regression and multiclass classification[J].IEEETransactions on Systems,Man,and Cybernetics,Part B:Cybernetics,2012,42(2):513-529.
[14]Wang Z,Wu D,Gravina R,et al.Kernel fusion based extreme learning machine for cross-location activity recognition[J].Information Fusion,2017,37(C):1-9.
[15]Huang G B,Zhu Q Y,Siew C K.Extreme learning machine:a new learning scheme of feedforward neural networks[C]//Proceedings of the IJCNN,Budapest,Hungary,2004,2:985-990.
[16]Pal M,Maxwell A,Warner T A.Kernel-based extreme learning machine for remote-sensing image classification[J].Remote Sensing Letters,2013,4(9):853-862.
[17]Moreno R,Corona F,Lendasse A,et al.Extreme learning machines for soybean classification in remote sensing hyperspectral images[J].Neurocomputing,2014,128:207-216.
[18]Bazi Y,Alajlan N,Melgani F,et al.Differential Evolution Extreme Learning Machine for the Classification of Hyperspectral Images[J].IEEE Geoscience&Remote Sensing Letters,2014,11(6):1066-1070.
[19]Samat A,Du P,Liu S,et al.E2ELM:Ensemble Extreme Learning Machines for Hyperspectral Image Classification[J].IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2014,7(4):1060-1069.
[20]Li L,Wang C Y,Li W.Hyperspectral image classification by Ada Boost weighted composite kernel extreme learning machines[J].Neurocomputing,2018,275:1725-1733.
[21]LüQ,Niu X,Dou Y.Classification of Hyperspectral Remote Sensing Image Using Hierarchical Local-ReceptiveField-Based Extreme Learning Machine[J].IEEE Geoscience and Remote Sensing Letters,2016,13(3):434-438.
[22]Li W,Du Q,Xiong M M.Kernel Collaborative Representation With Tikhonov Regularization for Hyperspectral Image Classification[J].IEEE Geoscience and Remote Sensing Letters,2015,12(1):48-52.
[23]Hong D,Yokoya N,Zhu X X.Learning a Robust Local Manifold Representation for Hyperspectral Dimensionality Reduction[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2017,10(6):2960-2975.
[24]Tan Y,Yuan H,Li L.Manifold-based sparse representation for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(12):7606-7618.
[25]Argyriou A,Micchelli C A,Pontil M.When Is There a Representer Theorem?Vector Versus Matrix Regularizers[J].Journal of Machine Learning Research,2008,10(4):2507-2529.
[26]Zhou Y C,Wei Y T.Learning Hierarchical Spectral-Spatial Features for Hyperspectral Image Classification[J].IEEE Transactions on Cyberentics,2016,46(7):1667-1678.
[27]Pu H,Chen Z,Wang B.A novel spatial-spectral similarity measure for dimensionality reduction and classification of hyperspectral imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(11):7008-7002.
[2]Li J,Marpu P R.Generalized Composite Kernel Framework for Hyperspectral Image Classification[J].IEEE Transactions on Geoscience and Remote Sensing,2013,51(9):4816-4829.
[3]Melgani F,Bruzzone L.Classification of hyperspectral remote sensing images with support vector machines[J].IEEETransactions on Geoscience and Remote Sensing,2004,42(8):1778-1790.
[4]Xie L,Li G Y,Xiao M,et al.Hyperspectral Image Classification Using Discrete Space Model and Support Vector Machines[J].IEEE Geoscience and Remote Sensing Letters,2017,14(3):374-378.
[5]Tarabalka Y,Benediktsson J A,Chanussot J.Spectral-spatial classification of hyperspectral imagery based on partitional clustering techniques[J].IEEE Transactions on Geoscience and Remote Sensing,2009,47(8):2973-2987.
[6]Quesada-Barriuso P,Arguello F.Spectral-Spatial Classification of Hyperspectral Images Using Wavelets and Extended Morphological Profiles[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(4):1177-1185.
[7]Gu Y F,Liu T Z,Jia X P.Nonlinear Multiple Kernel Learning With Multiple-Structure-Element Extended Morphological Profiles for Hyperspectral Image Classification[J].IEEE Transactions on Geoscience and Remote Sensing,2016,54(6):3235-3247.
[8]Pan L,Li H C,Meng H.Hyperspectral Image Classification via Low-Rank and Sparse Representation With Spectral Consistency Constraint[J].IEEE Geoscience and Remote Sensing Letters,2017,14(11):2117-2121.
[9]Yuan Y,Lin J Z,Wang Q.Hyperspectral Image Classification via Multitask Joint Sparse Representation and Stepwise MRF Optimization[J].IEEE Transactions on Cybernetics,2016,46(12):2966-2977.
[10]Wang Q,Lin J Z,Yuan Y.Salient Band Selection for Hyperspectral Image Classification via Manifold Ranking[J].IEEE Transactions on Neural Networks and Learning Systems,2016,27(6):1279-1289.
[11]Huang G B,Zhu Q Y,Siew C K.Extreme learning machine:theory and applications[J].Neurocomputing,2006,70(1):489-501.
[12]Tang J,Deng C,Huang G B.Extreme learning machine for multilayer perceptron[J].IEEE Transactions on Neural Networks and Learning Systems,2016,27(4):809-821.
[13]Huang G B,Zhou H M,Ding X J,et al.Extreme learning machine for regression and multiclass classification[J].IEEETransactions on Systems,Man,and Cybernetics,Part B:Cybernetics,2012,42(2):513-529.
[14]Wang Z,Wu D,Gravina R,et al.Kernel fusion based extreme learning machine for cross-location activity recognition[J].Information Fusion,2017,37(C):1-9.
[15]Huang G B,Zhu Q Y,Siew C K.Extreme learning machine:a new learning scheme of feedforward neural networks[C]//Proceedings of the IJCNN,Budapest,Hungary,2004,2:985-990.
[16]Pal M,Maxwell A,Warner T A.Kernel-based extreme learning machine for remote-sensing image classification[J].Remote Sensing Letters,2013,4(9):853-862.
[17]Moreno R,Corona F,Lendasse A,et al.Extreme learning machines for soybean classification in remote sensing hyperspectral images[J].Neurocomputing,2014,128:207-216.
[18]Bazi Y,Alajlan N,Melgani F,et al.Differential Evolution Extreme Learning Machine for the Classification of Hyperspectral Images[J].IEEE Geoscience&Remote Sensing Letters,2014,11(6):1066-1070.
[19]Samat A,Du P,Liu S,et al.E2ELM:Ensemble Extreme Learning Machines for Hyperspectral Image Classification[J].IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2014,7(4):1060-1069.
[20]Li L,Wang C Y,Li W.Hyperspectral image classification by Ada Boost weighted composite kernel extreme learning machines[J].Neurocomputing,2018,275:1725-1733.
[21]LüQ,Niu X,Dou Y.Classification of Hyperspectral Remote Sensing Image Using Hierarchical Local-ReceptiveField-Based Extreme Learning Machine[J].IEEE Geoscience and Remote Sensing Letters,2016,13(3):434-438.
[22]Li W,Du Q,Xiong M M.Kernel Collaborative Representation With Tikhonov Regularization for Hyperspectral Image Classification[J].IEEE Geoscience and Remote Sensing Letters,2015,12(1):48-52.
[23]Hong D,Yokoya N,Zhu X X.Learning a Robust Local Manifold Representation for Hyperspectral Dimensionality Reduction[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2017,10(6):2960-2975.
[24]Tan Y,Yuan H,Li L.Manifold-based sparse representation for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(12):7606-7618.
[25]Argyriou A,Micchelli C A,Pontil M.When Is There a Representer Theorem?Vector Versus Matrix Regularizers[J].Journal of Machine Learning Research,2008,10(4):2507-2529.
[26]Zhou Y C,Wei Y T.Learning Hierarchical Spectral-Spatial Features for Hyperspectral Image Classification[J].IEEE Transactions on Cyberentics,2016,46(7):1667-1678.
[27]Pu H,Chen Z,Wang B.A novel spatial-spectral similarity measure for dimensionality reduction and classification of hyperspectral imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(11):7008-7002.