一种基于SSA-DBN的室内可见光指纹定位算法  

An indoor visible light fingerprint localization algorithm based on SSA-DBN

作　　者：王鹏云 邵建华[1,2] 王宗生 程悦 杨薇 杜聪[1] WANG Pengyun;SHAO Jianhua;WANG Zongsheng;CHENG Yue;YANG Wei;DU Cong(School of Computer and Electronic Information,Nanjing Normal University,Nanjing 210023,China;Jiangsu Key Laboratory of Optoelectronics,Nanjing 210023,China)

机构地区：[1]南京师范大学计算机与电子信息学院,南京210023 [2]江苏省光电重点实验室,南京210023

出　　处：《激光杂志》2024年第1期159-165,共7页Laser Journal

摘　　要：室内可见光定位在精度方面有着较高的要求,针对这一问题,文中提出了一种麻雀搜索算法(Sparrow Search Algorithm,SSA)优化深度置信网络(Deep Belief Network,DBN)的室内可见光指纹定位算法。首先,采用信号强度特征值与位置坐标建立离线指纹库;其次,利用麻雀搜索算法较好的全局探索和局部开发的能力,对深度置信网络的初始权阈值进行优化,建立网络训练模型,对待定位目标的位置进行预测,避免了DBN陷入局部最优以及收敛速度较慢的问题。最后,利用已建立的离线指纹库数据,计算定位误差并分析。在4 m×4 m×2.5 m的空间中进行实验,结果表明:文中算法的平均定位误差为3.51 cm,定位误差在6 cm以内的概率为89.9%,与DBN定位算法相比,平均定位误差下降了约22.5%。Indoor visible light localization has high requirements in terms of accuracy,in order to solve this problem,a Sparrow Search Algorithm(SSA)is proposed to optimize the indoor visible light fingerprint localization algorithm of Deep Belief Network(DBN).Firstly,the signal strength characteristic value and position coordinates are used to establish an offline fingerprint database.Secondly,the good global exploration and local development capabilities of the sparrow search algorithm are used to optimize the initial weight threshold of the deep confidence network,establish a network training model,and predict the position of the positioning target,so as to avoid the problem of DBN falling into local optimization and slow convergence.Finally,using the established offline fingerprint database data,the positioning error is calculated and analyzed.In the space experiment,the results show that the average positioning error of the algorithm in the paper is 3.51 cm,and the probability of the positioning error within 6cm is 89.9%,which is about 22.5%lower than that of the DBN positioning algorithm.

关 键 词：可见光 室内定位 麻雀搜索算法 深度置信网络 

分 类 号：TN209[电子电信—物理电子学]