Multi-layer Extreme Learning Machine-based Autoencoder for Hyperspectral Image Classification

Muhammad Ahmad; Adil Mehmood Khan; Manuel Mazzara; Salvatore Distefano

doi:10.5220/0007258000750082

Multi-layer Extreme Learning Machine-based Autoencoder for Hyperspectral Image Classification

Muhammad Ahmad^*, Adil Mehmood Khan, Manuel Mazzara, Salvatore Distefano

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

33 Scopus citations

Abstract

Hyperspectral imaging (HSI) has attracted the formidable interest of the scientific community and has been applied to an increasing number of real-life applications to automatically extract the meaningful information from the corresponding high dimensional datasets. However, traditional autoencoders (AE) and restricted Boltzmann machines are computationally expensive and do not perform well due to the Hughes phenomenon which is observed in HSI since the ratio of the labeled training pixels on the number of bands is usually quite small. To overcome such problems, this paper exploits a multi-layer extreme learning machine-based autoencoder (MLELM-AE) for HSI classification. MLELM-AE learns feature representations by adopting a singular value decomposition and is used as basic building block for learning machine-based autoencoder (MLELM-AE). MLELM-AE method not only maintains the fast speed of traditional ELM but also greatly improves the performance of HSI classification. The experimental results demonstrate the effectiveness of MLELM-AE on several well-known HSI dataset.

Original language	English
Title of host publication	VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Editors	Andreas Kerren, Christophe Hurter, Jose Braz
Publisher	SciTePress
Pages	75-82
Number of pages	8
ISBN (Electronic)	9789897583544
DOIs	https://doi.org/10.5220/0007258000750082
State	Published - 2019
Externally published	Yes
Event	14th International Conference on Computer Vision Theory and Applications, VISAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019 - Prague, Czech Republic Duration: 25 Feb 2019 → 27 Feb 2019

Publication series

Name	VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Volume	4

Conference

Conference	14th International Conference on Computer Vision Theory and Applications, VISAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019
Country/Territory	Czech Republic
City	Prague
Period	25/02/19 → 27/02/19

Bibliographical note

Publisher Copyright:
Copyright © 2019 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved

Keywords

Auto Encoder (AE)
Deep Neural Networks (DNN)
Extreme Learning Machine (ELM)
Hyperspectral Image Classification

ASJC Scopus subject areas

Computer Science Applications
Computer Vision and Pattern Recognition
Computer Graphics and Computer-Aided Design
Human-Computer Interaction

Access to Document

10.5220/0007258000750082

Cite this

Ahmad, M., Khan, A. M., Mazzara, M., & Distefano, S. (2019). Multi-layer Extreme Learning Machine-based Autoencoder for Hyperspectral Image Classification. In A. Kerren, C. Hurter, & J. Braz (Eds.), VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (pp. 75-82). (VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications; Vol. 4). SciTePress. https://doi.org/10.5220/0007258000750082

Ahmad, Muhammad ; Khan, Adil Mehmood ; Mazzara, Manuel et al. / Multi-layer Extreme Learning Machine-based Autoencoder for Hyperspectral Image Classification. VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. editor / Andreas Kerren ; Christophe Hurter ; Jose Braz. SciTePress, 2019. pp. 75-82 (VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications).

@inproceedings{ef8ab6c3320b440390742624ee674902,

title = "Multi-layer Extreme Learning Machine-based Autoencoder for Hyperspectral Image Classification",

abstract = "Hyperspectral imaging (HSI) has attracted the formidable interest of the scientific community and has been applied to an increasing number of real-life applications to automatically extract the meaningful information from the corresponding high dimensional datasets. However, traditional autoencoders (AE) and restricted Boltzmann machines are computationally expensive and do not perform well due to the Hughes phenomenon which is observed in HSI since the ratio of the labeled training pixels on the number of bands is usually quite small. To overcome such problems, this paper exploits a multi-layer extreme learning machine-based autoencoder (MLELM-AE) for HSI classification. MLELM-AE learns feature representations by adopting a singular value decomposition and is used as basic building block for learning machine-based autoencoder (MLELM-AE). MLELM-AE method not only maintains the fast speed of traditional ELM but also greatly improves the performance of HSI classification. The experimental results demonstrate the effectiveness of MLELM-AE on several well-known HSI dataset.",

keywords = "Auto Encoder (AE), Deep Neural Networks (DNN), Extreme Learning Machine (ELM), Hyperspectral Image Classification",

author = "Muhammad Ahmad and Khan, \{Adil Mehmood\} and Manuel Mazzara and Salvatore Distefano",

note = "Publisher Copyright: Copyright {\textcopyright} 2019 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved; 14th International Conference on Computer Vision Theory and Applications, VISAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019 ; Conference date: 25-02-2019 Through 27-02-2019",

year = "2019",

doi = "10.5220/0007258000750082",

language = "English",

series = "VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications",

publisher = "SciTePress",

pages = "75--82",

editor = "Andreas Kerren and Christophe Hurter and Jose Braz",

booktitle = "VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications",

}

Ahmad, M, Khan, AM, Mazzara, M & Distefano, S 2019, Multi-layer Extreme Learning Machine-based Autoencoder for Hyperspectral Image Classification. in A Kerren, C Hurter & J Braz (eds), VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, vol. 4, SciTePress, pp. 75-82, 14th International Conference on Computer Vision Theory and Applications, VISAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019, Prague, Czech Republic, 25/02/19. https://doi.org/10.5220/0007258000750082

Multi-layer Extreme Learning Machine-based Autoencoder for Hyperspectral Image Classification. / Ahmad, Muhammad; Khan, Adil Mehmood; Mazzara, Manuel et al.
VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. ed. / Andreas Kerren; Christophe Hurter; Jose Braz. SciTePress, 2019. p. 75-82 (VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications; Vol. 4).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Multi-layer Extreme Learning Machine-based Autoencoder for Hyperspectral Image Classification

AU - Ahmad, Muhammad

AU - Khan, Adil Mehmood

AU - Mazzara, Manuel

AU - Distefano, Salvatore

PY - 2019

Y1 - 2019

N2 - Hyperspectral imaging (HSI) has attracted the formidable interest of the scientific community and has been applied to an increasing number of real-life applications to automatically extract the meaningful information from the corresponding high dimensional datasets. However, traditional autoencoders (AE) and restricted Boltzmann machines are computationally expensive and do not perform well due to the Hughes phenomenon which is observed in HSI since the ratio of the labeled training pixels on the number of bands is usually quite small. To overcome such problems, this paper exploits a multi-layer extreme learning machine-based autoencoder (MLELM-AE) for HSI classification. MLELM-AE learns feature representations by adopting a singular value decomposition and is used as basic building block for learning machine-based autoencoder (MLELM-AE). MLELM-AE method not only maintains the fast speed of traditional ELM but also greatly improves the performance of HSI classification. The experimental results demonstrate the effectiveness of MLELM-AE on several well-known HSI dataset.

AB - Hyperspectral imaging (HSI) has attracted the formidable interest of the scientific community and has been applied to an increasing number of real-life applications to automatically extract the meaningful information from the corresponding high dimensional datasets. However, traditional autoencoders (AE) and restricted Boltzmann machines are computationally expensive and do not perform well due to the Hughes phenomenon which is observed in HSI since the ratio of the labeled training pixels on the number of bands is usually quite small. To overcome such problems, this paper exploits a multi-layer extreme learning machine-based autoencoder (MLELM-AE) for HSI classification. MLELM-AE learns feature representations by adopting a singular value decomposition and is used as basic building block for learning machine-based autoencoder (MLELM-AE). MLELM-AE method not only maintains the fast speed of traditional ELM but also greatly improves the performance of HSI classification. The experimental results demonstrate the effectiveness of MLELM-AE on several well-known HSI dataset.

KW - Auto Encoder (AE)

KW - Deep Neural Networks (DNN)

KW - Extreme Learning Machine (ELM)

KW - Hyperspectral Image Classification

UR - https://www.scopus.com/pages/publications/85065723702

U2 - 10.5220/0007258000750082

DO - 10.5220/0007258000750082

M3 - Conference contribution

AN - SCOPUS:85065723702

T3 - VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

SP - 75

EP - 82

BT - VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

A2 - Kerren, Andreas

A2 - Hurter, Christophe

A2 - Braz, Jose

PB - SciTePress

T2 - 14th International Conference on Computer Vision Theory and Applications, VISAPP 2019 - Part of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019

Y2 - 25 February 2019 through 27 February 2019

ER -

Ahmad M, Khan AM, Mazzara M, Distefano S. Multi-layer Extreme Learning Machine-based Autoencoder for Hyperspectral Image Classification. In Kerren A, Hurter C, Braz J, editors, VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. SciTePress. 2019. p. 75-82. (VISIGRAPP 2019 - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications). doi: 10.5220/0007258000750082

Multi-layer Extreme Learning Machine-based Autoencoder for Hyperspectral Image Classification

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this