Abstract
In order to improve the classification of hyperspectral image, we propose a novel hyperspectral image classification model using ensemble extreme learning machine based on fuzzy entropy weights and auto-adapted spatial-spectral features (FEW-ASSELM). To be specific, the fuzzy entropy weight of the band is proposed as a new metric to measure the importance of each band, which can optimize the grouping strategy of the effective bands. With the change of grouping strategy and random training set, the method of auto-adapted spatial-spectral features extraction is proposed to extract the more effective features. According to the characteristics of the suboptimal grouping strategy and auto-adapted spatial-spectral features, the matching framework of ensemble extreme learning machine can be proposed to perform classification operation. Experimental results on the typical hyperspectral image datasets illustrate that the proposed FEW-ASSELM has few adjustable parameters to make the operation simple, and outperforms a variety of the image classification counterparts in terms of the calculation cost and classification accuracy.
Similar content being viewed by others
References
Abbasi M, Khosravi MR (2020) A robust and accurate particle filter-based pupil detection method for big datasets of eye video. J Grid Comput 18(2):305–325
Abbasi M, Yaghoobikia M, Rafiee M, Jolfaei A, Khosravi M (2020) Energy-efficient workload allocation in fog-cloud based services of intelligent transportation systems using a learning classifier system. IET Intell Transp Syst 14(11):1484–1490
Abbasi M, Pasand EM, Khosravi MR (2020) Workload allocation in iot-fog-cloud architecture using a multi-objective genetic algorithm. J Grid Comput 18:43–56
Cai YM, Zhang ZJ, Yan Q et al (2021) Densely connected convolutional extreme learning machine for hyperspectral image classifification. Neurocomputing 434(2021):21–32
Cao F, Yang Z, Ren J, Jiang M, Ling WK (2017) linear vs nonlinear extreme learning machine for spectral-spatial classification of hyperspectral image [J]. Sensors 17(11):2603
Cervellera C, Maccio D (2017, 47) An extreme learning machine approach to density estimation problems [J]. IEEE Trans Cybern (10):3254–3265 Oct
Chen HY, Miao F, Chen YJ et al (2021) Hyperspectral image Classifification method using multifeature vectors and Optimized KELM[J]. IEEE J selected top appl earth observa remote sensing 14:2781–2795
Du PJ, Xue ZH, Li J, Plaza A (2015) Learning discriminative sparse representations for hyperspectral image classification. IEEE J Select Top Sign Proces 9(6):1089–1104
Fauvel JC, Benediktsson JA (2012) A spatial-spectral kernel-based approach for the classification of remote sensing images. Pattern Recogn 45(1):381–392
Gu Y, Xu Y, Guo BF (2018) Hyperspectral image classification by combination oI spatial-spectral features and ensemble extreme Learning Machines [J]. Acta Ueodaetica et C’artographica Sinica 47(9):1238–1249
Jiang MY, Cao FX, Lu YM (2018) Extreme learning machine with Enh- anced composite feature for spectral-spatial hyperspectral Image Classification [J]. IEEE Access:22645–22654
Jiang Q, Dong YF, Peng JT, Yan M, Sun Y (2021) Maximum likelihood estimation based nonnegative matrix factorization for hyperspectral Unmixing [J]. Remote Sensing 13(13):2637–2637
Li JJ, Du Q, Li W et al (2015) optimizing extreme learning machine for hyperspectral image classification [J]. J Appl Remote Sens 9(1):097296
Liu YX, Fang JJ, Zhang XJ, Sun J (2015) application of extreme learning machine in the nonlinear error compensation of magnetic compass [J]. Chin J Sci Instrum 36(09):1921–1927
Lv F, Han M (2018) hyperspectral remote sensing image classification based on deep extreme learning machine [J]. J Dalian Univ Technol 58(02):166–173
Minchao Y, Chenxi J, Hong Ch, Ling L, Hui JL, Yun TQ (2019) Residual deep PCA-based feature extraction for h-yperspectral image classification. Neural Computing and Applications
Neal LC, Wilkinson JJ, Mason PJ et al (2018) Spectral characteristics of propylitic alteration minerals as a vectoring tool for porphyry copper deposits. J Geochem Explor 184:179–198
Okwuashi O, Ndehedehe CE (2020) Deep support vector machine for hyperspectral image classification. Pattern Recogn 103
Paoletti ME, Haut JM, Plaza J, Plaza A (2018) A new deep convolutio- nal neural network for fast hyperspectral image classification [J]. ISPRS J Photogramm Remote Sens 145:120–147
Pour AB, Zoheir B, Pradhan B, Hashim M (2021) Editorial for the special issue: multispectral and hyperspectral remote sensing data for mineral exploration and environmental monitoring of mined areas [J]. Remote Sensing 13(3):519–519
Qing YY, Zeng YJ, Li Y et al (2020) Deep and wide feature based extreme learning machine for image classification. Neurocomputing 412:426–436
Samat DP, Sicong L et al (2014) E2LMs:Ensemble extreme learning machines for Hyperspertral image Classification [J]. IEEE J Selec Top App Earth Observ Remote Sens 07(4):1060–1069
Schlkopf B, Smola A (2018) learning with kernels: Support vector machines, regularization, optimization, and beyond Cambridge. MIT Press, MA, USA
Sun WW, Zhang DF, Yang G, Li WY (2018) Band selection for hyperspectral imagery based on weighted probabilistic archetypal analysis. J Remote Sensing 22(1):110–118
Tang YD, Huang SC, Xue Ai J (2017) Sparse representation based band selection for hyperspectral imagery target detection [J]. Acta Electron Sin 45(10):2368–2374
Wang C, Liu B, Liu L, Zhu Y, Hou J, Lium P, Li X (2021) A review of deep learning used in the hyperspectral image analysis for agriculture [J]. Artif Intell Rev. pp 1–49
Yin YP, Wei L (2020) Hyperspectral image classification using comprehensive evaluation model of extreme learning machine based on cumulative variation weights. IEEE Access 8:187991–188003
Zhou YC, Peng JT, Philip CL (2015) extreme learning machine with composite kernels for hyperspectral image classifification, IEEE J. Sel Top Appl Earth Observ Remote Sens 8:2351–2360
Acknowledgments
This work was supported in part by the Science and Technology Research Project of the Education Department of Liaoning under Grant No. LJ2020QNL013, in part by the Doctoral Initiation Foundation of Liaoning Technical University under Grant No. 19-1026 and Grant No. 21-1050.
Conflict of interest
The authors declare that there are no conflicts of interest regarding the publication of this paper.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yin, Y., Wei, L. Hyperspectral image classification using ensemble extreme learning machine based on fuzzy entropy weights and auto-adapted spatial-spectral features. Multimed Tools Appl 82, 217–238 (2023). https://doi.org/10.1007/s11042-022-13255-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-13255-7