Neural networks designed on approximate reasoning architecture and their applications

This paper proposes a Neural-Network-Based Fuzzy logic system for navigation control of intelligent vehicles. First, the use of Neural Networks and Fuzzy Logic to provide intelligent vehicles with more autonomy and intelligence is discussed. Second, the system for the obstacle avoidance behavior is developed. Fuzzy Logic improves Neural Networks (NN) obstacle avoidance approach by handling imprecision and rule-based approximate reasoning. This system must make the vehicle able, after supervised learning, to achieve two tasks: 1- to make one’s way towards its target by a NN, and 2- to avoid static or dynamic obstacles by a Fuzzy NN capturing the behavior of a human expert. Afterwards, two association phases between each task and the appropriate actions are carried out by Trial and Error learning and their coordination allows to decide the appropriate action. Finally, the simulation results display the generalization and adaptation abilities of the system by testing it in new unexplored environments.

Download Full-text

Recognition of handwritten numeric characters using neural networks designed on approximate reasoning architecture

Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan) ◽

10.1109/ijcnn.1993.714153 ◽

2005 ◽

Cited By ~ 3

Author(s):

Y. Kojima ◽

H. Yamamoto ◽

T. Kohda ◽

S. Sakaue ◽

S. Maruno ◽

...

Keyword(s):

Neural Networks ◽

Approximate Reasoning

Download Full-text

Special Issue on the Sixth International Conference on Fuzzy Systems (AFSS' 2004)

Journal of Advanced Computational Intelligence and Intelligent Informatics ◽

10.20965/jaciii.2006.p0443 ◽

2006 ◽

Vol 10 (4) ◽

pp. 443-443

Author(s):

Nguyen Hoang Phuong ◽

Keyword(s):

Neural Networks ◽

Fuzzy Logic ◽

Hybrid Systems ◽

Fuzzy Systems ◽

Constraint Satisfaction Problems ◽

Approximate Reasoning ◽

Special Issue ◽

International Conference ◽

Sixth International Conference ◽

Sixth International

This special issue features five papers devoted to fuzzy systems and their applications. Papers were selected from those accepted and presented at the Sixth International Conference on Fuzzy Systems (AFSS' 2004) held in Hanoi, Vietnam on December 15-17, 2004. AFSS' 2004 and Tutorials held in Hue city on December 18-19, 2004, included a wide spectrum of research topics on "fuzzy set theory", "intelligent technology", "fuzzy logic and approximate reasoning", "neural networks", "genetic algorithms", "hybrid systems" and "soft computing". Over 40 papers were accepted and presented by researchers from countries including Brazil, Canada, Taiwan, India, Korea, Malaysia, Japan and Vietnam. Five papers receiving outstanding recommendations in reviews have been selected for this issue. The topics they address include fuzzy logic for robots, data mining, neural networks in medicine, Fuzzy Constraint Satisfaction Problems, and hybrid systems. As editors of this special issue, we are sincerely grateful to the authors. Special thanks also go to the referees for their excellent work, to Mr. Kazuki Ohmori for his aid in coordinating the issue's publication, and to the JACIII Editorial Board, especially Professor Kaoru Hirota for his invaluable support and encouragement. Finally, we thank Professors Masao Mukaidono and Witold Pedrycz for their contributions to AFSS' 2004. Without their support, AFSS' 2004 and this issue would not have been possible.

Download Full-text