Dimensionality reduction using deep belief network in big data case study: Hyperspectral image classification

Dewa Made Sri Arsa; Grafika Jati; Aprinaldi Jasa Mantau; Ito Wasito

doi:10.1109/IWBIS.2016.7872892

Dimensionality reduction using deep belief network in big data case study: Hyperspectral image classification

Dewa Made Sri Arsa, Grafika Jati, Aprinaldi Jasa Mantau, Ito Wasito

Department of Computer Science

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

22 Citations (Scopus)

Abstract

The high dimensionality in big data need a heavy computation when the analysis needed. This research proposed a dimensionality reduction using deep belief network (DBN). We used hyperspectral images as case study. The hyperspectral image is a high dimensional image. Some researched have been proposed to reduce hyperspectral image dimension such as using LDA and PCA in spectral-spatial hyperspectral image classification. This paper proposed a dimensionality reduction using deep belief network (DBN) for hyperspectral image classification. In proposed framework, we use two DBNs. First DBN used to reduce the dimension of spectral bands and the second DBN used to extract spectral-spatial feature and as classifier. We used Indian Pines data set that consist of 16 classes and we compared DBN and PCA performance. The result indicates that by using DBN as dimensionality reduction method performed better than PCA in hyperspectral image classification.

Original language	English
Title of host publication	2016 International Workshop on Big Data and Information Security, IWBIS 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	71-76
Number of pages	6
ISBN (Electronic)	9781509034772
DOIs	https://doi.org/10.1109/IWBIS.2016.7872892
Publication status	Published - 6 Mar 2017
Event	2016 International Workshop on Big Data and Information Security, IWBIS 2016 - Jakarta, Indonesia Duration: 18 Oct 2016 → 19 Oct 2016

Publication series

Name	2016 International Workshop on Big Data and Information Security, IWBIS 2016

Conference

Conference	2016 International Workshop on Big Data and Information Security, IWBIS 2016
Country/Territory	Indonesia
City	Jakarta
Period	18/10/16 → 19/10/16

Keywords

Big Data
Deep belief network (DBN)
dimensionality reduction
restricted Boltzmann machine (RBM)

Access to Document

10.1109/IWBIS.2016.7872892

Cite this

Arsa, D. M. S., Jati, G., Mantau, A. J., & Wasito, I. (2017). Dimensionality reduction using deep belief network in big data case study: Hyperspectral image classification. In 2016 International Workshop on Big Data and Information Security, IWBIS 2016 (pp. 71-76). Article 7872892 (2016 International Workshop on Big Data and Information Security, IWBIS 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IWBIS.2016.7872892

Arsa, Dewa Made Sri ; Jati, Grafika ; Mantau, Aprinaldi Jasa et al. / Dimensionality reduction using deep belief network in big data case study : Hyperspectral image classification. 2016 International Workshop on Big Data and Information Security, IWBIS 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 71-76 (2016 International Workshop on Big Data and Information Security, IWBIS 2016).

@inproceedings{d13a95629d1047509feb8271685a338c,

title = "Dimensionality reduction using deep belief network in big data case study: Hyperspectral image classification",

abstract = "The high dimensionality in big data need a heavy computation when the analysis needed. This research proposed a dimensionality reduction using deep belief network (DBN). We used hyperspectral images as case study. The hyperspectral image is a high dimensional image. Some researched have been proposed to reduce hyperspectral image dimension such as using LDA and PCA in spectral-spatial hyperspectral image classification. This paper proposed a dimensionality reduction using deep belief network (DBN) for hyperspectral image classification. In proposed framework, we use two DBNs. First DBN used to reduce the dimension of spectral bands and the second DBN used to extract spectral-spatial feature and as classifier. We used Indian Pines data set that consist of 16 classes and we compared DBN and PCA performance. The result indicates that by using DBN as dimensionality reduction method performed better than PCA in hyperspectral image classification.",

keywords = "Big Data, Deep belief network (DBN), dimensionality reduction, restricted Boltzmann machine (RBM)",

author = "Arsa, {Dewa Made Sri} and Grafika Jati and Mantau, {Aprinaldi Jasa} and Ito Wasito",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 International Workshop on Big Data and Information Security, IWBIS 2016 ; Conference date: 18-10-2016 Through 19-10-2016",

year = "2017",

month = mar,

day = "6",

doi = "10.1109/IWBIS.2016.7872892",

language = "English",

series = "2016 International Workshop on Big Data and Information Security, IWBIS 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "71--76",

booktitle = "2016 International Workshop on Big Data and Information Security, IWBIS 2016",

address = "United States",

}

Arsa, DMS, Jati, G, Mantau, AJ & Wasito, I 2017, Dimensionality reduction using deep belief network in big data case study: Hyperspectral image classification. in 2016 International Workshop on Big Data and Information Security, IWBIS 2016., 7872892, 2016 International Workshop on Big Data and Information Security, IWBIS 2016, Institute of Electrical and Electronics Engineers Inc., pp. 71-76, 2016 International Workshop on Big Data and Information Security, IWBIS 2016, Jakarta, Indonesia, 18/10/16. https://doi.org/10.1109/IWBIS.2016.7872892

Dimensionality reduction using deep belief network in big data case study: Hyperspectral image classification. / Arsa, Dewa Made Sri; Jati, Grafika; Mantau, Aprinaldi Jasa et al.
2016 International Workshop on Big Data and Information Security, IWBIS 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 71-76 7872892 (2016 International Workshop on Big Data and Information Security, IWBIS 2016).

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

TY - GEN

T1 - Dimensionality reduction using deep belief network in big data case study

T2 - 2016 International Workshop on Big Data and Information Security, IWBIS 2016

AU - Arsa, Dewa Made Sri

AU - Jati, Grafika

AU - Mantau, Aprinaldi Jasa

AU - Wasito, Ito

PY - 2017/3/6

Y1 - 2017/3/6

N2 - The high dimensionality in big data need a heavy computation when the analysis needed. This research proposed a dimensionality reduction using deep belief network (DBN). We used hyperspectral images as case study. The hyperspectral image is a high dimensional image. Some researched have been proposed to reduce hyperspectral image dimension such as using LDA and PCA in spectral-spatial hyperspectral image classification. This paper proposed a dimensionality reduction using deep belief network (DBN) for hyperspectral image classification. In proposed framework, we use two DBNs. First DBN used to reduce the dimension of spectral bands and the second DBN used to extract spectral-spatial feature and as classifier. We used Indian Pines data set that consist of 16 classes and we compared DBN and PCA performance. The result indicates that by using DBN as dimensionality reduction method performed better than PCA in hyperspectral image classification.

AB - The high dimensionality in big data need a heavy computation when the analysis needed. This research proposed a dimensionality reduction using deep belief network (DBN). We used hyperspectral images as case study. The hyperspectral image is a high dimensional image. Some researched have been proposed to reduce hyperspectral image dimension such as using LDA and PCA in spectral-spatial hyperspectral image classification. This paper proposed a dimensionality reduction using deep belief network (DBN) for hyperspectral image classification. In proposed framework, we use two DBNs. First DBN used to reduce the dimension of spectral bands and the second DBN used to extract spectral-spatial feature and as classifier. We used Indian Pines data set that consist of 16 classes and we compared DBN and PCA performance. The result indicates that by using DBN as dimensionality reduction method performed better than PCA in hyperspectral image classification.

KW - Big Data

KW - Deep belief network (DBN)

KW - dimensionality reduction

KW - restricted Boltzmann machine (RBM)

UR - http://www.scopus.com/inward/record.url?scp=85017035500&partnerID=8YFLogxK

U2 - 10.1109/IWBIS.2016.7872892

DO - 10.1109/IWBIS.2016.7872892

M3 - Conference contribution

AN - SCOPUS:85017035500

T3 - 2016 International Workshop on Big Data and Information Security, IWBIS 2016

SP - 71

EP - 76

BT - 2016 International Workshop on Big Data and Information Security, IWBIS 2016

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 18 October 2016 through 19 October 2016

ER -

Arsa DMS, Jati G, Mantau AJ, Wasito I. Dimensionality reduction using deep belief network in big data case study: Hyperspectral image classification. In 2016 International Workshop on Big Data and Information Security, IWBIS 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 71-76. 7872892. (2016 International Workshop on Big Data and Information Security, IWBIS 2016). doi: 10.1109/IWBIS.2016.7872892

Dimensionality reduction using deep belief network in big data case study: Hyperspectral image classification

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this