摘要
针对Wi Fi位置指纹定位时由于受到室内环境变化的影响而造成精度严重下降的问题,本文提出了一种基于混合遗传粒子群算法和候选位置指纹的室内定位系统,本系统采用在定位服务阶段选择多个位置指纹作为候选位置指纹,利用遗传算法搜索全局较优的位置指纹组合,并采用粒子群优化算法快速准确地找到最佳的位置指纹。仿真结果表明,基于混合遗传粒子群算法提高了室内定位精度,可以快速精确地搜索到最佳位置,同时减小了遗传算法时延较大的缺点,避免了局部最优解问题。
Aiming at the problem of serious degradation of accuracy due to indoor environment changes in Wi Fi fingerprint position,this paper proposes an indoor positioning technology based on candidate fingerprints and hybrid genetic particle swarm optimization. In the online phase,a plurality of candidate fingerprints are selected by using the probabilistic model of location fingerprints. An genetic algorithm is applied to search the global better location fingerprinting combination,and a Particle Swarm Optimization algorithm is adapted to quickly search the best position fingerprint,and the corresponding position of the fingerprint is used as the final device estimation position. Simulation results show,GA-PSO algorithm can improve indoor positioning accuracy,it searches for the best position more quickly and accurately,reduces the disadvantage of larger delay of GA algorithm and avoids the problem of local optimal solution.
作者
凌海波
周先存
何富贵
LING Hai-bo;ZHOU Xian-cun;HE Fu-gui(College of Electronic and Information Engineering,West Anhui University,Lu’an 237012,China)
出处
《南阳理工学院学报》
2018年第2期67-71,76,共6页
Journal of Nanyang Institute of Technology
基金
国家自然科学基金资助项目(61702375
61572366)
