A variant of gravitational classification

@article{TomaszGórecki2014,
abstract = {In this article there is proposed a new two-parametrical variant of the gravitational classification method. We use the general idea of objects' behavior in a gravity field. Classification depends on a test object's motion in a gravity field of training points. To solve this motion problem, we use a simulation method. This classifier is compared to the 1NN method, because our method tends towards it for some parameter values. Experimental results on different data sets demonstrate an improvement in efficiency and that this approach outperforms the 1NN method by providing a significant reduction in the mean classification error rate.},
author = {Tomasz Górecki, Maciej Luczak},
journal = {Biometrical Letters},
keywords = {machine learning; nearest neighbor method; dynamic classifier; gravitational classification; data mining; derivative dynamic time warping; dynamic time warping; time series},
language = {eng},
number = {1},
pages = {1-12},
title = {A variant of gravitational classification},
url = {http://eudml.org/doc/268776},
volume = {51},
year = {2014},
}

TY - JOUR
AU - Tomasz Górecki
AU - Maciej Luczak
TI - A variant of gravitational classification
JO - Biometrical Letters
PY - 2014
VL - 51
IS - 1
SP - 1
EP - 12
AB - In this article there is proposed a new two-parametrical variant of the gravitational classification method. We use the general idea of objects' behavior in a gravity field. Classification depends on a test object's motion in a gravity field of training points. To solve this motion problem, we use a simulation method. This classifier is compared to the 1NN method, because our method tends towards it for some parameter values. Experimental results on different data sets demonstrate an improvement in efficiency and that this approach outperforms the 1NN method by providing a significant reduction in the mean classification error rate.
LA - eng
KW - machine learning; nearest neighbor method; dynamic classifier; gravitational classification; data mining; derivative dynamic time warping; dynamic time warping; time series
UR - http://eudml.org/doc/268776
ER -