摘要
为解决基于相对位置的定位算法易受环境干扰,定位精度不高的问题,提出一种基于改进灰狼算法-广义回归神经网络(IGWO-GRNN)的室内3D定位算法。利用GRNN建立3D定位模型,通过IGWO优化平滑因子,将待测节点与信标节点间的信号强度值作为神经网络的输入,神经网络的输出即为待测节点的真实三维坐标。将仿真结果与其它算法进行比较,验证了所提算法的定位精度与收敛速度均优于其它算法。
To solve the problems that the location algorithm based on relative position is easy to be interfered by environment and the positioning accuracy is not high,an indoor 3D positioning algorithm based on improved gray wolf algorithm-generalized regression neural network(IGWO-GRNN)was proposed.The 3D positioning model was established using GRNN,and the smoothing factor was optimized using IGWO.The signal strength value between the node to be tested and the beacon node was taken as the input of the neural network,and the output of the neural network was the real three-dimensional coordinates of the node to be tested.Comparing the simulation results with other algorithms,it is verified that the positioning accuracy and convergence speed of the proposed algorithm are better than that of other algorithms.
作者
高媛
阳媛
王鸿磊
GAO Yuan;YANG Yuan;WANG Hong-lei(School of Information Engineering,Xuzhou College of Industrial Technology,Xuzhou 221000,China;School of Instrument Science and Engineering,Southeast University,Nanjing 210096,China;School of Information and Control Engineering,China University of Mining and Technology,Xuzhou 221000,China)
出处
《计算机工程与设计》
北大核心
2021年第12期3461-3468,共8页
Computer Engineering and Design
基金
国家自然科学基金青年基金项目(61601123)
徐州市科技发展基金项目(KC17132)。
关键词
灰狼算法
广义回归神经网络
3D定位
平滑因子
信号强度
gray wolf algorithm
generalized regression neural network
3D positioning
smoothing factor
signal strength
