Supervised classification for functional data: a weighted distance approach Articles uri icon

publication date

  • July 2012

start page

  • 2334

end page

  • 2346

issue

  • 7

volume

  • 56

international standard serial number (ISSN)

  • 0167-9473

electronic international standard serial number (EISSN)

  • 1872-7352

abstract

  • A natural methodology for discriminating functional data is based on the distances from the observation or its derivatives to group representative functions (usually the mean) or their derivatives. It is proposed to use a combination of these distances for supervised classification. Simulation studies show that this procedure performs very well, resulting in smaller testing classification errors. Applications to real data show that this technique behaves as well as &- and in some cases better than &- existing supervised classification methods for functions