Hyperspectral Image Classification Using Reduced Extreme Learning Machine


SIĞIRCI İ. O. , BİLGİN G.

3rd International Conference on Computer Science and Engineering (UBMK), Sarajevo, Bosnia And Herzegovina, 20 - 23 September 2018, pp.372-375 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/ubmk.2018.8566604
  • City: Sarajevo
  • Country: Bosnia And Herzegovina
  • Page Numbers: pp.372-375

Abstract

In the classification of hyperspectral images, kernel based approaches have been shown to be successful results. Too much training or testing data in the images increases the computation time and memory requirements in the kernel computations. Extreme learning machines that can be used with the kernel approach also need the same requirements in kernel computations. In this study, improvements were made in terms of computation time and memory using reduced kernel extreme learning machines (RKELM). The obtained results are presented comparatively through the tables of performance and time information with kernel extreme learning machine (KELM).