摘要
针对标准粒子群算法的缺点,在原有算法的基础上,提出一种动态权值的粒子群优化算法,使得粒子在迭代过程中惯性权值随粒子进化度和聚合度的变化而改变,并将其尝试性的运用到数据融合领域.实验结果表明,改进的PSO算法能近似最优地确定数据融合中各权值因子,使融合在信息源的可靠性、信息的冗余度/互补度以及进行融合的分级结构不确定的情况下,以近似最优的方式对传感器数据进行融合.
Because of stranded PSO limitation, a dynamically changing weight PSO algorithm is proposed on the basic of the normal PSO algorithm. The weight is changed in every loop according to the swarm evolution degree and aggregation degree factor. Then the paper describes a novel hierarchical data fusion algorithm adopting this algorithm. The distinctive feature of this is its capability of fusing data in a near optimal manner when no information about the reliability of the information sources, the degree of redundancy/complementarity of the information sources and the structure of the hierarchy is available.
出处
《常熟理工学院学报》
2009年第2期111-114,共4页
Journal of Changshu Institute of Technology
基金
"863"研究计划项目(2006AA10A301).
关键词
标准粒子群算法
动态权值
数据融合
冗余度/互补度
standard PSO algorithm
dynamically weight
data fusion
redundancy/complementarity