Intelligent affect regression for bodily expressions using hybrid particle swarm optimization and adaptive ensembles
作者：
Highlights：
• 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.
摘要
•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.
论文关键词：Bodily expression,Adaptive ensemble regression,Particle swarm optimization,Genetic algorithm,Support vector regression,Mutation distributions
论文评审过程：Received 10 October 2014, Revised 6 July 2015, Accepted 11 July 2015, Available online 21 July 2015, Version of Record 29 August 2015.
论文官网地址：https://doi.org/10.1016/j.eswa.2015.07.022
