Behavior categorization using Correlation Based Adaptive Resonance Theory

Author

Yavas, Mustafa ; Alpaslan, Ferda Nur

Author_Institution

Dept. of Comput. Eng., Middle East Tech. Univ., Ankara, Turkey

fYear

2009

fDate

24-26 June 2009

Firstpage

724

Lastpage

729

Abstract

This paper presents a new method of categorizing robot behavior, which is based on a variation of correlation based adaptive resonance theory (CobART) learning. CobART is a type of ART 2 network and its main contribution is the usage of correlation analysis methods for category matching. This study uses derivation based correspondence and Euclidian distance as correlation analysis methods for behavior categorization. Tests show that the proposed method generates better results than ART 2 categorization even when a priori SOM (self-organizing map) categorization is combined with ART 2 categorization.

Keywords

adaptive resonance theory; behavioural sciences; category theory; correlation methods; learning (artificial intelligence); robots; self-organising feature maps; ART 2 categorization; CobART learning; behavior categorization; category matching; correlation analysis methods; correlation based adaptive resonance theory; self-organizing map categorization; Adaptive control; Hidden Markov models; Human robot interaction; Programmable control; Recurrent neural networks; Resonance; Robot sensing systems; Robotics and automation; Subspace constraints; Testing; Robot behavior recognition; adaptive resonance theory; correlation analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Automation, 2009. MED '09. 17th Mediterranean Conference on

Conference_Location

Thessaloniki

Print_ISBN

978-1-4244-4684-1

Electronic_ISBN

978-1-4244-4685-8

Type

conf

DOI

10.1109/MED.2009.5164629

Filename

5164629