Hierarchical Self-organizing Maps System for Action Classification

Zahra Gharaee, Peter Gärdenfors, Magnus Johnsson

2017

Abstract

We present a novel action recognition system that is able to learn how to recognize and classify actions. Our system employs a three-layered neural network hierarchy consisting of two self-organizing maps together with a supervised neural network for labelling the actions. The system is equipped with a module that pre-processes the 3D input data before the first layer, and a module that transforms the activity elicited over time in the first layer SOM into an ordered vector representation before the second layer, thus achieving a time invariant representation. We have evaluated our system in an experiment consisting of ten different actions selected from a publicly available data set with encouraging result.

Paper Citation

in Harvard Style

Gharaee Z., Gärdenfors P. and Johnsson M. (2017). Hierarchical Self-organizing Maps System for Action Classification . In Proceedings of the 9th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-220-2, pages 583-590. DOI: 10.5220/0006199305830590

in Bibtex Style

@conference{icaart17,
author={Zahra Gharaee and Peter Gärdenfors and Magnus Johnsson},
title={Hierarchical Self-organizing Maps System for Action Classification},
booktitle={Proceedings of the 9th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2017},
pages={583-590},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006199305830590},
isbn={978-989-758-220-2},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Hierarchical Self-organizing Maps System for Action Classification
SN - 978-989-758-220-2
AU - Gharaee Z.
AU - Gärdenfors P.
AU - Johnsson M.
PY - 2017
SP - 583
EP - 590
DO - 10.5220/0006199305830590