By Topic

Artificial Neural Network (ANN) beyond cots remote sensing packages: Implementation of Extreme Learning Machine (ELM) in MATLAB

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Shrestha, S. ; Inst. of Geodesy & Cartography, Warsaw, Poland ; Bochenek, Z. ; Smith, C.

The transfer of knowledge from research community to specialized remote sensing software has been extremely slow hindering the application of ANN techniques in remote sensing field. There are many variants of ANN depending upon its topology and its learning paradigms but Multilayer perception (MLP) with back propagation (BP) is widely used in remote sensing despite its limitation such as fine tuning of numbers of input parameters such as learning rate, momentum, number of hidden layers and number of hidden nodes. In this paper, recently proposed Extreme Learning Machine (ELM) version of ANN which is extremely fast and does not require any iterative learning is introduced. In ELM classifier, only number of neurons required has to be fine-tuned unlike numerous parameters in MLP. To disseminate, its use to wider audience in remote sensing field, its implementation in MATLAB in a Graphical User Interface (GUI) is described. The developed GUI is capable of handling large image files by employing a smarter technique of supplying rectangular chunk of image data through object oriented image adapter class and provides a simple and effective computation environment for performing ELM classification with accuracy assessment.

Published in:

Geoscience and Remote Sensing Symposium (IGARSS), 2012 IEEE International

Date of Conference:

22-27 July 2012