全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

萤火虫算法优化的高光谱遥感影像极限学习机分类方法

DOI: 10.3724/SP.J.1047.2015.00986, PP. 986-994

Keywords: 极限学习机,高光谱遥感,参数优化,分类

Full-Text   Cite this paper   Add to My Lib

Abstract:

机器学习方法在高光谱遥感影像分类中广泛应用,本文使用新型的极限学习机(ExtremeLearningMachine,ELM)进行高光谱遥感影像分类,针对ELM中正则化参数C和核参数σ,提出以萤火虫算法(FireflyAlgorithm,FA)进行优化。首先,采用萤火虫算法进行高光谱遥感影像的波段选择,以便降低维数;然后,利用萤火虫算法以分类精度最大化为准则对ELM的参数组合(C,σ)进行寻优;最后,利用参数优化后的ELM分类器,对3个不同传感器的高光谱遥感影像进行分类。实验中将新型的萤火虫算法与遗传算法(GeneticAlgorithm,GA)和粒子群算法(ParticleSwarmOptimization,PSO)进行了对比,并将ELM的性能与支持向量机(SupportVectorMachine,SVM)方法作对比。结果表明,FA优化方法优于传统的GA和PSO优化方法,ELM方法的效果在训练时间和分类准确率2个方面都优于SVM方法。实验说明,本文提出的方法具有较好的适用性和较优的分类效果。

References

[1]  Huang G B, Zhou H M, Ding X J, et al . Extreme learning machine for regression and multiclass classification[J]. IEEE Transactions on Systems, Man and Cybernetics - Part B, 2011,42(2):513-529.
[2]  马彩虹,戴芹,刘士彬.一种融合PSO和Isodata的遥感图像分割新方法[J].武汉大学学报(信息科学版),2012,37(1):35-38.
[3]  郑肇葆,郑宏,潘励.纹理分类中遗传算法参数的选择[J].测绘学报,2000,29(1):36-39.
[4]  Bora T C, Schauenburg F, Alotto P. A multiobjective firefly approach using beta probability distribution for electromagnetic optimization problems[J]. IEEE Magnetics Society, 2013,49(5):2085-2088.
[5]  Bai X P, Sun B H. An application of firefly algorithm in beamforming optimization of linear antenna arrays[C]. Proceedings of 2012 2nd IEEE International Conference on Cloud Computing and Intelligence Systems, Hangzhou, China, 2012,2:1141-1144.
[6]  Hu Z W, Liao J X, Xu T. A firefly algorithm for distributed power optimization of macrocell base station[C]. Proceedings of 2013 5th IEEE International Conference on Broadband Network and Multimedia Technology, Guilin, China, 2013:248-252.
[7]  童庆禧,张兵,郑兰芬.高光谱遥感[M].北京:高等教育出版社,2006.
[8]  张兵,高连如.高光谱图像分类与目标探测[M].北京:科学出版社,2011.
[9]  王静,何挺,李玉环.基于高光谱遥感技术的土地质量信息挖掘研究[J].遥感学报,2005,9(4):438-445.
[10]  Vapnik V N. The Nature of Statistical Learning Theory [M], New York: Springer Verlag Press, 1995.
[11]  何挺,王静,程烨.高光谱遥感技术在土地质量监测中的应用[J].长江流域资源与环境学报,2002(11):79-83.
[12]  熊桢,郑兰芬,童庆禧.分层神经网络分类算法[J].测绘学报,2000,29(3):229-234.
[13]  Chong C C, Jia J C, Mital D P. Classification of multispectral images using BP-nerual network classifier-input codings assessment[C]. IEEE Internatinal Conference on Frontiers of Computer Technology, Los Alamitos, CA, USA, 1994,2:867-871.
[14]  Chapelle O, Vapnik V, Bousquet O, et al . Choosing multiple parameters for support vector machines[J]. Machine Learning, 2002,46(1-3):131-159.
[15]  邓乃扬,田英杰.数据挖掘中的新方法——支持向量机[M].北京:科学出版社,2004.
[16]  Melgani F, Bruzzone L. Classification of hyperspectral remote-sensing images with support vector machines[J]. IEEE Transactions on Geoscience and Remote Sensing, 2004,42(8):1178-1790.
[17]  Camps-Valls G, Gomez-Chova L, Munoz-Mari J, et al . Composite kernels for hyperspectral image classification[J]. IEEE Geoscience and Remote Sensing Letters, 2006,3(1):93-97.
[18]  黄昕,张良培,李平湘.基于多尺度特征融合和支持向量机的高分辨率遥感影像分类[J].遥感学报,2007,11(1):48-54.
[19]  Alajlan N, Melgani F, AlHichri H, et al . Differential evolution extreme learning machine for the classification of hyperspectral images[J]. IEEE Geoscience and Remote Sensing Letters, 2014,11(6):1066-1070.
[20]  Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: Theory and applications[J]. Neurocomputing, 2006,70:489-501.
[21]  Huang G B, Wang D H, Lan Y. Extreme learning machines: A survey[J]. International Journal of Machine Learning and Cybernetics, 2011,2(2):107-122.
[22]  Huang G B, Ding X, Zhou H. Optimization method based extreme learning machine for classification[J]. Neurocomputing, 2010,74:155-163.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133