DocumentCode :
3109828
Title :
A Neuro-Fuzzy Model for Motion Cognition
Author :
Shaarawy, Mohamed ; Belal, Mohamed ; ElGindy, Ehab
Author_Institution :
Helwan Univ., Cairo
fYear :
2007
fDate :
11-13 July 2007
Firstpage :
406
Lastpage :
411
Abstract :
Motion tracking is a traditional problem that was tackled by various approaches including statistical methods and dynamical filtering techniques. In this paper, we introduce an approach that models this problem as a cognitive process in which motion is captured and stored as knowledge and hence can be recalled or recognized. The adaptive neuro-fuzzy inference system (ANFIS) model is used as a cognitive model in order to model and represent motion features. Motion dynamics and curvature are model inputs and the tracked object positions are the output. The model is tested on a set of motions representing maneuvering and non-maneuvering targets and it successfully tracked all motions. Moreover, the model has the ability to learn more quickly. The results are more accurate in comparison with similar work using feed forward neural network (FFNN).
Keywords :
cognitive systems; fuzzy neural nets; fuzzy reasoning; ANFIS; adaptive neuro-fuzzy inference system; curvature; knowledge storage; motion cognition; motion dynamics; motion tracking; neuro-fuzzy model; Brain modeling; Cognition; Humans; Information filtering; Mathematical model; Motion estimation; Neural networks; Statistical analysis; Target tracking; Vehicle dynamics; Cognitive Model.; Dynamic Model; Maneuvering Target; Target Tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer and Information Science, 2007. ICIS 2007. 6th IEEE/ACIS International Conference on
Conference_Location :
Melbourne, Qld.
Print_ISBN :
0-7695-2841-4
Type :
conf
DOI :
10.1109/ICIS.2007.31
Filename :
4276416
Link To Document :
بازگشت