We conduct dimensional affect recognition of bodily expressions.
•
Hybrid particle swarm optimization (PSO) is proposed for feature selection.
•
It mitigates premature convergence problem of conventional PSO.
•
Mutation mechanisms of each subswarm work cooperatively to avoid stagnation.
•
Our system outperforms other PSO-based and bodily expression perception research.
NGLC 2004-2010.National Geological Library of China All Rights Reserved.
Add:29 Xueyuan Rd,Haidian District,Beijing,PRC. Mail Add: 8324 mailbox 100083
For exchange or info please contact us via email.