Application of Numenta® Hierarchical Temporal Memory for land-use classification

Authors

  • A.J. Perea
  • J.E. Meroño
  • M.J. Aguilera

Abstract

The aim of this paper is to present the application of memoryprediction theory, implemented in the form of a Hierarchical Temporal Memory (HTM), for land-use classification. Numenta®HTM is a new computing technology that replicates the structure and function of the human neocortex. In this study, a photogram, received by a photogrammetric UltraCamD® sensor of Vexcel, and data on 1 513 plots in Manzanilla (Huelva, Spain) were used to validate the classification, achieving an overall classification accuracy of 90.4%. The HTMapproach appears to hold promise for land-use classification.

Downloads

Published

2010-01-19

Issue

Vol. 105 No. 9/10 (2009)

Section

Research Articles

License

Creative Commons License
All articles are published under a Creative Commons Attribution 4.0 International Licence

Copyright is retained by the authors. Readers are welcome to reproduce, share and adapt the content without permission provided the source is attributed.

Disclaimer: The publisher and editors accept no responsibility for statements made by the authors

How to Cite

Perea, A., Meroño, J., & Aguilera, M. (2010). Application of Numenta® Hierarchical Temporal Memory for land-use classification. South African Journal of Science, 105(9/10). https://sajs.co.za/article/view/10248
Views
  • Abstract 106
  • PDF 67