Particle filter resampling based on optimized combinatorial algorithm

doi:10.1109/ITiME.2011.6132049

	Particle filter resampling based on optimized combinatorial algorithm
	Li, Rui; Mao, Li; Zhang, Jiurui
	2011
会议日期	December 9, 2011 - December 11, 2011
会议地点	Guangzhou, China
关键词	Chaos theory Genetic algorithms Iterative methods Monte Carlo methods Combinatorial algorithm Crossover and mutation Immune algorithms Immune genetic algorithms Immunity algorithms Local optimizations Particle Filtering Resampling
卷号	2
DOI	10.1109/ITiME.2011.6132049
页码	27-30
英文摘要	In particle Alter algorithm, the resampling step effectively solves the problem of particles degeneracy; however, it reduces the particle variety. This article describes how to use chaos, immunity algorithm and genetic algorithm carried on particle resampling corrective method. We present a novel algorithm which combines immune algorithm, chaos and genetic algorithm. This immune genetic algorithm based on chaos initializes cluster by the over-spread character and randomicity of chaos to improve search speed and renews cluster by chaos sequence and enhancing cluster diversity to avoid local optimization. Chaos also is adopts to optimize the local optimization to increase precision. After crossover and mutation, using chaotic local optimization near the optimal solution to enhance the precision of the solutions. The experimental results show that it has the quicker convergence rate and the better iterative estimating capability, compared with the particle resampling based on the immunity genetic algorithm. © 2011 IEEE.
会议录	ITME 2011 - Proceedings: 2011 IEEE International Symposium on IT in Medicine and Education
会议录出版者	IEEE Computer Society
语种	英语
内容类型	会议论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/116260]
专题	计算机与通信学院
作者单位	School of Computer and Communication, LanZhou University of Technology, LanZhou, China
推荐引用方式 GB/T 7714	Li, Rui,Mao, Li,Zhang, Jiurui. Particle filter resampling based on optimized combinatorial algorithm[C]. 见:. Guangzhou, China. December 9, 2011 - December 11, 2011.