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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

13 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 languageEnglish
Title of host publication2016 International Workshop on Big Data and Information Security, IWBIS 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages71-76
Number of pages6
ISBN (Electronic)9781509034772
DOIs
Publication statusPublished - 6 Mar 2017
Event2016 International Workshop on Big Data and Information Security, IWBIS 2016 - Jakarta, Indonesia
Duration: 18 Oct 201619 Oct 2016

Publication series

Name2016 International Workshop on Big Data and Information Security, IWBIS 2016

Conference

Conference2016 International Workshop on Big Data and Information Security, IWBIS 2016
Country/TerritoryIndonesia
CityJakarta
Period18/10/1619/10/16

Keywords

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

Fingerprint

Dive into the research topics of 'Dimensionality reduction using deep belief network in big data case study: Hyperspectral image classification'. Together they form a unique fingerprint.

Cite this