Please wait a minute...
Shopping Cart Email List Chinese
Advanced Search Fig/Tab
Frontiers of Earth Science

ISSN 2095-0195

ISSN 2095-0209(Online)

CN 11-5982/P

Postal Subscription Code 80-963

2018 Impact Factor: 1.205

Featured Articles  |  Most Downloaded  |  Most Reading
Online Submission Subscribe to Our RSS Content Feed
Front. Earth Sci.    2017, Vol. 11 Issue (4) : 765-773    https://doi.org/10.1007/s11707-016-0603-2
RESEARCH ARTICLE
Optimized extreme learning machine for urban land cover classification using hyperspectral imagery
Hongjun SU1(), Shufang TIAN2(), Yue CAI1, Yehua SHENG3,4, Chen CHEN5, Maryam NAJAFIAN5
1. School of Earth Sciences and Engineering, Hohai University, Nanjing 210098, China
2. School of Earth Sciences and Resources, China University of Geosciences (Beijing), Beijing 100083, China
3. Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing 210023, China
4. Key Laboratory of Virtual Geographic Environment (Ministry of Education), Nanjing Normal University, Nanjing 210023, China
5. Department of Electrical Engineering, University of Texas at Dallas, Richardson, TX 75080-3021, USA
 Download: PDF(1149 KB)   HTML
 Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Abstract

This work presents a new urban land cover classification framework using the firefly algorithm (FA) optimized extreme learning machine (ELM). FA is adopted to optimize the regularization coefficientC and Gaussian kernel s for kernel ELM. Additionally, effectiveness of spectral features derived from an FA-based band selection algorithm is studied for the proposed classification task. Three sets of hyperspectral databases were recorded using different sensors, namely HYDICE, HyMap, and AVIRIS. Our study shows that the proposed method outperforms traditional classification algorithms such as SVM and reduces computational cost significantly.
Keywords extreme learning machine      firefly algorithm      parameters optimization      hyperspectral image classification     
Corresponding Author(s): Hongjun SU,Shufang TIAN   
Just Accepted Date: 12 October 2016   Online First Date: 04 November 2016    Issue Date: 10 November 2017
 Cite this article:   
Hongjun SU,Shufang TIAN,Yue CAI, et al. Optimized extreme learning machine for urban land cover classification using hyperspectral imagery[J]. Front. Earth Sci., 2017, 11(4): 765-773.
 URL:  
https://academic.hep.com.cn/fesci/EN/10.1007/s11707-016-0603-2
https://academic.hep.com.cn/fesci/EN/Y2017/V11/I4/765
Fig.1  Proposed FA-inspired classification framework.
ELM SVM FA GA PSO
Para.1 C=[10 ?5,105] C=[10 ?5,105] Maximum iterations=100 Maximum iterations=100 Maximum iterations=100
Para.2 s=(0,1] s=[10?5,105] Population size=10 Population size=10 Population size=10
Para.3 Light absorbance=1 Crossover probability=0.9 Inertia weight=1
Para.4 Maximum attractiveness=1 Mutation probability=0.07 Accelerating factor C1=1.7
Para.5 Step size=0.2 Accelerating factor c2=1.5
Tab.1  Optimal parameters of different algorithms for ELM and SVM classifier
HYDICE DC MALL HyMap Purdue Campus Salinas-A scene
Class Name Training No. Test No. Name Training No. Test No. Name Sample No.
1 Road 55 892 Road 55 892 Brocoli_green_weeds_1 391
2 Grass 57 910 Grass 57 910 Corn_senesced_green_weeds 1343
3 Shadow 50 567 Shadow 50 567 Lettuce_romaine_4wk 616
4 Trail 46 623 Trail 46 623 Lettuce_romaine_5wk 1525
5 Tree 49 656 Tree 49 656 Lettuce_romaine_6wk 674
6 Roof 52 1123 Roof 52 1123 Lettuce_romaine_7wk 799
Total 309 4772 Total 309 4772 Total 5348
Tab.2  Training and testing samples for hyperspectral data
Fig.2  Hyperspectral datasets used in the experiments. (a) HYDICE DC MALL; (b) HyMap Purdue Campus; (c) Salinas-A scene.
Fig.3  Classification accuracy of different algorithms. (a) HYDICE DC MALL. (b) HyMap Purdue Campus. (c) Salinas-A scene.
Fig.4  Classification accuracy of before and after FA optimization algorithm. (a) HYDICE DC MALL. (b) HyMap Purdue Campus. (c) Salinas-A scene.
Datasets 5 15 All bands
ELM SVM ELM SVM ELM SVM
HYDICE 0.009 0.041 0.012 0.198 0.014 0.573
HyMap 0.018 0.080 0.020 0.086 0.026 0.205
Salinas-A 0.028 0.133 0.036 0.145 0.043 0.970
Tab.3  Running times of ELM and SVM(seconds)
1 Bao Y, Tian  Q, Chen M  (2015a). A weighted algorithm based on normalized mutual information for estimating the chlorophyll-a concentration in inland waters using geostationary ocean color imager(GOCI) data. Remote Sens, 7(9): 11731–11752
https://doi.org/10.3390/rs70911731
2 Bao Y, Tian  Q, Chen M ,  Lin H (2015b). An automatic extraction method for individual tree crowns based on self-adaptive mutual information and tile computing. Int J Digit Earth, 8(6): 495–516
https://doi.org/10.1080/17538947.2014.912683
3 Bazi Y, Alajlan  N, Melgani F ,  AlHichri H ,  Malek S ,  Yager R R  (2014). Differential evolution extreme learning machine for the classification of hyperspectral images. IEEE Geosci Remote Sens Lett, 11(6): 1066–1070
https://doi.org/10.1109/LGRS.2013.2286078
4 Bioucas-Dias J, Plaza  A, Camps-Valls G ,  Scheunders P ,  Nasrabadi N ,  Chanussot J  (2013). Hyperspectral remote sensing data analysis and future challenges. IEEE Geosci Remote Sens Mag, 1(2): 6–36
https://doi.org/10.1109/MGRS.2013.2244672
5 Camps-Valls G, Tuia  D, Bruzzone L ,  Benediktsson J A  (2014). Advances in hyperspectral image classification: earth monitoring withstatistical learning methods. IEEE Signal Process Mag, 31(1): 45–54
https://doi.org/10.1109/MSP.2013.2279179
6 Chang C I (2003). Hyperspectral Imaging: Techniques for Spectral Detection and Classification. New York: Kluwer Academic/Plenum Publishers, 13–15
7 Chen C, Li  W, Su H ,  Liu K (2014). Spectral-spatial classification of hyperspectral image based on kernel extreme learning machine. Remote Sens, 6(6): 5795–5814
https://doi.org/10.3390/rs6065795
8 Cheng G, Zhu  F, Xiang S ,  Wang Y, Pan  C (2016). Semisupervised hyperspectral image classification via discriminant analysis and robust regression. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(2): 595–608 doi:10.1109/JSTARS.2015.2471176
9 Cortes C, Vapnik  V (1995). Support vector networks. Mach Learn, 20(3): 273–297
https://doi.org/10.1007/BF00994018
10 de Morsier F, Borgeaud  M, Gass V ,  Thiran J-P ,  Tuia, D (2016). Kernel low-rank and sparse graph for unsupervised and semi-supervised classification of hyperspectral images. IEEE Trans Geosci Remote Sens, 54(6):1–11
11 Hu F, Xia  G, Wang Z ,  Huang X ,  Zhang L ,  Sun H (2015). Unsupervised feature learning via spectral clustering of multi-dimensional patches for remotely sensed scene classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(5): 2015–2030
https://doi.org/10.1109/JSTARS.2015.2444405
12 Huang G B, Ding  X, Zhou H  (2010). Optimization method based extreme learning machine for classification. Neurocomputing, 74(1‒3): 155–163
https://doi.org/10.1016/j.neucom.2010.02.019
13 Huang G B, Wang  D, Lan Y  (2011). Extreme learning machines: a survey. Int J Mach Learn & Cyber, 2(2): 107–122
https://doi.org/10.1007/s13042-011-0019-y
14 Huang G B, Zhu  Q Y, Siew  C K (2006). Extreme learning machine: theory and applications. Neurocomputing, 70(1‒3): 489–501
https://doi.org/10.1016/j.neucom.2005.12.126
15 Li W, Du  Q, Zhang F ,  Hu W (2015). Collaborative representation based nearest neighbor classifier for hyperspectral imagery. IEEE Geosci Remote Sens Lett, 12(2): 389–393
https://doi.org/10.1109/LGRS.2014.2343956
16 Lin J, Huang  B, Chen M ,  Huang Z  (2014). Modeling urban vertical growth using cellular automata-Guangzhou as a case study. Appl Geogr, 53: 172–186
https://doi.org/10.1016/j.apgeog.2014.06.007
17 Liu Q, He  Q, Shi Z  (2008). Extreme support vector machine classifier. Lect Notes Comput Sci, 5012: 222–233
https://doi.org/10.1007/978-3-540-68125-0_21
18 Lv Q, Niu  X, Dou Y ,  Xu J, Lei  Y(2016). Classification of hyperspectral remote sensing image using hierarchical local-receptive-field-based extreme learning machine. IEEE Geoscience and Remote Sensing Letters, 13(3):1–5
19 Melgani F, Bruzzone  L (2004). Classification of hyperspectral remote sensing images with support vector machines. IEEE Trans Geosci Rem Sens, 42(8): 1778–1790
https://doi.org/10.1109/TGRS.2004.831865
20 Pal M, Maxwell  A E, Warner  T A (2013). Kernel-based extreme learning machine for remote-sensing image classification. Remote Sens Lett, 4(9): 853–862
https://doi.org/10.1080/2150704X.2013.805279
21 Ratle F, Camps-Valls  G, Weston J  (2010). Semisupervised neural networks for efficient hyperspectral image classification. IEEE Trans Geosci Rem Sens, 48(5): 2271–2282
https://doi.org/10.1109/TGRS.2009.2037898
22 Samat A, Du  P, Liu S ,  Li J, Cheng  L (2014). E2LMs: ensemble extreme learning machines for hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(4): 1060–1069
https://doi.org/10.1109/JSTARS.2014.2301775
23 Senthilnath J, Omkar  S N, Mani  V (2011). Clustering using firefly algorithm: performance study. Swarm Evol Comput, 1(3): 164–171
https://doi.org/10.1016/j.swevo.2011.06.003
24 Su H, Yong  B, Du Q  (2016). Hyperspectral band selection using improved firefly algorithm. IEEE Geosci Remote Sens Lett, 13(1): 68–72
https://doi.org/10.1109/LGRS.2015.2497085
25 Tan K, Zhou  S, Du Q  (2015). Semi-supervised discriminant analysis for hyperspectral imagery with block-sparse graph. IEEE Geosci Remote Sens Lett, 12(8): 1765–1769
https://doi.org/10.1109/LGRS.2015.2424963
26 Xue Z, Du  P, Su H  (2014). Harmonic analysis for hyperspectral image classification integrated with PSO optimized SVM. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(6): 2131–2146
https://doi.org/10.1109/JSTARS.2014.2307091
27 Yang X, He  X (2013). Firefly algorithm: recent advances and applications. Int J Swarm Intelligence, 1(1): 36–50 doi:10.1504/IJSI.2013.055801
28 Yang X S (2009). Firefly Algorithms for Multimodal Optimization. Stochastic Algorithms: Foundations and Applications. Berlin Heidelberg: Springer-Verlag, 169–178
29 Zhang L, Zhang  L, Tao D ,  Huang X  (2012). On combining multiple features for hyperspectral remote sensing image classification. IEEE Trans Geosci Rem Sens, 50(3): 879–893
https://doi.org/10.1109/TGRS.2011.2162339
30 Zhang L, Zhang  Q, Zhang L ,  Tao D, Huang  X, Du B  (2015). Ensemble manifold regularized sparse low-rank approximation for multiview feature embedding. Pattern Recognit, 48(10): 3102–3112
https://doi.org/10.1016/j.patcog.2014.12.016
31 Zhen Z, Zhen  H, Li P  (2000). The parameters selection of genetic algorithms in texture classification. Acta Geodaetica et Cartographica Sinica, 29(1): 36–39
[1] Changqing YAO, Zhifeng YANG. Parameters optimization on DHSVM model based on a genetic algorithm[J]. Front Earth Sci Chin, 2009, 3(3): 374-380.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed