Local block multilayer sparse extreme learning machine for effective feature extraction and classification of hyperspectral images

Faxian Cao, Zhijing Yang, Jinchang Ren, Wenchao Chen, Guojun Han, Yuzhen Shen

Research output: Contribution to journalArticle

9 Downloads (Pure)

Abstract

Although Extreme Learning Machines (ELM) have been successfully applied for the classification of hyperspectral images (HSIs), they still suffer from three main drawbacks. These include: 1) Ineffective feature extraction in HSIs due to a single hidden layer neuron network used; 2) ill-posed problems caused by the random input weights and biases; and 3) lack of spatial information for HSIs classification. To tackle the first problem, we construct a multilayer ELM for effective feature extraction from HSIs. The sparse representation is adopted with the multilayer ELM to tackle the ill-posed problem of ELM, which can be solved by the alternative direction method of multipliers (ADMM). This has resulted in the proposed multilayer sparse ELM (MSELM) model. Considering that the neighboring pixels are more likely from the same class, a local block extension is introduced for MSELM to extract the local spatial information, leading to the local block MSELM (LBMSLM). The loopy belief propagation (LBP) is also applied to the proposed MSELM and LBMSELM approaches to further utilize the rich spectral and spatial information for improving the classification. Experimental results show that the proposed methods have outperformed the ELM and other state-of-the-art approaches.
Original languageEnglish
Number of pages14
JournalIEEE Transactions on Geoscience and Remote Sensing
Publication statusAccepted/In press - 14 Feb 2019

Fingerprint

Learning systems
Feature extraction
Multilayers
Image classification
image classification
Neurons
machine learning
pixel
Pixels
method

Keywords

  • extreme learning machine
  • hyperspectral images
  • local block multilayer sparse ELM
  • loopy belief propagation
  • alternative direction method of multipliers

Cite this

@article{514c1a13eacb43168adcdf894d18cfea,
title = "Local block multilayer sparse extreme learning machine for effective feature extraction and classification of hyperspectral images",
abstract = "Although Extreme Learning Machines (ELM) have been successfully applied for the classification of hyperspectral images (HSIs), they still suffer from three main drawbacks. These include: 1) Ineffective feature extraction in HSIs due to a single hidden layer neuron network used; 2) ill-posed problems caused by the random input weights and biases; and 3) lack of spatial information for HSIs classification. To tackle the first problem, we construct a multilayer ELM for effective feature extraction from HSIs. The sparse representation is adopted with the multilayer ELM to tackle the ill-posed problem of ELM, which can be solved by the alternative direction method of multipliers (ADMM). This has resulted in the proposed multilayer sparse ELM (MSELM) model. Considering that the neighboring pixels are more likely from the same class, a local block extension is introduced for MSELM to extract the local spatial information, leading to the local block MSELM (LBMSLM). The loopy belief propagation (LBP) is also applied to the proposed MSELM and LBMSELM approaches to further utilize the rich spectral and spatial information for improving the classification. Experimental results show that the proposed methods have outperformed the ELM and other state-of-the-art approaches.",
keywords = "extreme learning machine, hyperspectral images, local block multilayer sparse ELM, loopy belief propagation, alternative direction method of multipliers",
author = "Faxian Cao and Zhijing Yang and Jinchang Ren and Wenchao Chen and Guojun Han and Yuzhen Shen",
note = "{\circledC} 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
year = "2019",
month = "2",
day = "14",
language = "English",
journal = "IEEE Transactions on Geoscience and Remote Sensing",
issn = "0196-2892",
publisher = "IEEE",

}

Local block multilayer sparse extreme learning machine for effective feature extraction and classification of hyperspectral images. / Cao, Faxian; Yang, Zhijing; Ren, Jinchang; Chen, Wenchao; Han, Guojun; Shen, Yuzhen.

In: IEEE Transactions on Geoscience and Remote Sensing, 14.02.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Local block multilayer sparse extreme learning machine for effective feature extraction and classification of hyperspectral images

AU - Cao, Faxian

AU - Yang, Zhijing

AU - Ren, Jinchang

AU - Chen, Wenchao

AU - Han, Guojun

AU - Shen, Yuzhen

N1 - © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2019/2/14

Y1 - 2019/2/14

N2 - Although Extreme Learning Machines (ELM) have been successfully applied for the classification of hyperspectral images (HSIs), they still suffer from three main drawbacks. These include: 1) Ineffective feature extraction in HSIs due to a single hidden layer neuron network used; 2) ill-posed problems caused by the random input weights and biases; and 3) lack of spatial information for HSIs classification. To tackle the first problem, we construct a multilayer ELM for effective feature extraction from HSIs. The sparse representation is adopted with the multilayer ELM to tackle the ill-posed problem of ELM, which can be solved by the alternative direction method of multipliers (ADMM). This has resulted in the proposed multilayer sparse ELM (MSELM) model. Considering that the neighboring pixels are more likely from the same class, a local block extension is introduced for MSELM to extract the local spatial information, leading to the local block MSELM (LBMSLM). The loopy belief propagation (LBP) is also applied to the proposed MSELM and LBMSELM approaches to further utilize the rich spectral and spatial information for improving the classification. Experimental results show that the proposed methods have outperformed the ELM and other state-of-the-art approaches.

AB - Although Extreme Learning Machines (ELM) have been successfully applied for the classification of hyperspectral images (HSIs), they still suffer from three main drawbacks. These include: 1) Ineffective feature extraction in HSIs due to a single hidden layer neuron network used; 2) ill-posed problems caused by the random input weights and biases; and 3) lack of spatial information for HSIs classification. To tackle the first problem, we construct a multilayer ELM for effective feature extraction from HSIs. The sparse representation is adopted with the multilayer ELM to tackle the ill-posed problem of ELM, which can be solved by the alternative direction method of multipliers (ADMM). This has resulted in the proposed multilayer sparse ELM (MSELM) model. Considering that the neighboring pixels are more likely from the same class, a local block extension is introduced for MSELM to extract the local spatial information, leading to the local block MSELM (LBMSLM). The loopy belief propagation (LBP) is also applied to the proposed MSELM and LBMSELM approaches to further utilize the rich spectral and spatial information for improving the classification. Experimental results show that the proposed methods have outperformed the ELM and other state-of-the-art approaches.

KW - extreme learning machine

KW - hyperspectral images

KW - local block multilayer sparse ELM

KW - loopy belief propagation

KW - alternative direction method of multipliers

UR - https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=36&punumber=36

M3 - Article

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

SN - 0196-2892

ER -