Share Email Print
cover

Proceedings Paper

Discovery of emerging patterns with immune network theory
Author(s): Bo Chen; Chuanzhi Zang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper presents an immune network-based emergent pattern recognition method. The artificial immune network provides more flexible learning tools than neural networks and clustering technologies. With a neural network, a network structure has to be defined first. The immune network allows their components to change and learn patterns by changing the strength of connections between individual components. The presented computational model achieves emergent pattern recognition by dynamically constructing a network of feature vectors to represent the internal image of input data patterns. The immune network-based emergent pattern recognition approach has tested using a benchmark civil structure. The test result shows the feasibility of using the presented method for the emergent structural damage pattern recognition.

Paper Details

Date Published: 31 March 2010
PDF: 9 pages
Proc. SPIE 7647, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2010, 764727 (31 March 2010); doi: 10.1117/12.847612
Show Author Affiliations
Bo Chen, Michigan Technological Univ. (United States)
Chuanzhi Zang, Michigan Technological Univ. (United States)


Published in SPIE Proceedings Vol. 7647:
Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2010
Masayoshi Tomizuka, Editor(s)

© SPIE. Terms of Use
Back to Top