Local Block Multilayer Sparse Extreme Learning Machine for Effective Feature Extraction and Classification of Hyperspectral Images

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 (FE) in HSIs due to a single hidden layer neuron network used; 2) ill-posed pro...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing 2019-08, Vol.57 (8), p.5580-5594
Main Authors: Cao, Faxian, Yang, Zhijing, Ren, Jinchang, Chen, Weizhao, Han, Guojun, Shen, Yuzhen
Format: Article
Language:English
Subjects:
Alternative direction method of multipliers (ADMMs)
Artificial neural networks
Classification
extreme learning machine (ELM)
Feature extraction
hyperspectral images (HSI)
Hyperspectral imaging
Ill posed problems
Image classification
Information processing
Iron
Learning algorithms
local block multilayer sparse ELM (LBMSELM)
loopy belief propagation (LBP)
Multilayers
Neurons
Nonhomogeneous media
Spatial data
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 (FE) 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 FE 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. 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 (LBMSELM). The loopy belief propagation 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.
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2019.2900509