Title :
CAVIAR-Based Vortex Core Region Detection
Author :
Li Zhang ; Machiraju, Raghu ; Thompson, Daniel
Author_Institution :
Dept. of Inf., Qilu Univ. Of Technol., Jinan, China
Abstract :
This paper presents a novel algorithm to enhance the robustness of vortex core detection that automatically learns to build a strong compound classifier based on a locally weighted combination of weak detectors and the training samples. We use semi-supervised learning with domain expert input to develop strategies for guiding the selective refinement process. This compound detector combines the advantages of each individual local detector. Our main application area is vortex detection in turbulent flows. We demonstrate the efficacy of our approach by applying the compound detector to a variety of fluid data examples.
Keywords :
computational fluid dynamics; expert systems; learning (artificial intelligence); mechanical engineering computing; pattern classification; turbulence; vortices; CAVIAR-based vortex core region detection; domain expert; fluid data examples; selective refinement process; semisupervised learning; strong compound classifier; turbulent flows; Boosting; Compounds; Detection algorithms; Detectors; Feature extraction; Robustness; Training; flow visualization; machine learning; vortex detection;
Conference_Titel :
Computer-Aided Design and Computer Graphics (CAD/Graphics), 2013 International Conference on
Conference_Location :
Guangzhou
DOI :
10.1109/CADGraphics.2013.48