结合基于密度的噪声应用空间聚类和反距离加权算法的城市环境电磁频谱地图构建

Construction of Electromagnetic Spectrum Map for Urban Environ⁃ment Based on DBSCAN-IDW Algorithm

针对传统电磁频谱地图构建方法感知节点分布不均匀、监测数据存在异常值等问题,将基于密度的噪声应用空间聚类(Density-based Spatial Clustering of Applications with Noise,DBSCAN)算法与反距离加权(Inverse Distance Weighting,IDW)算法相结合,提出一种城市环境电磁频谱地图构建方法。该算法首先通过DBSCAN减轻极端值的影响,并分离核心点、边界点和噪声点,将每个核心点的局部密度作为权重,计算簇的加权中心点。其次,运用IDW对聚类簇的加权中心点进行插值估计,以显著减少需要进行插值的数据点数量,从而构建精度更高的电磁频谱地图。仿真结果表明:与IDW算法和反障碍距离加权算法相比,所提算法重构得到的电磁频谱地图的平均绝对误差和归一化均方误差分别降低了10%和23%以上。

Aiming at the problems of uneven distribution of sensing nodes and abnormal values in monitoring data,an urban environment electromagnetic spectrum map construction method was proposed by combining density-based spatial clustering of applications with noise(DBSCAN)and inverse distance weighting(IDW)algorithm.Firstly,DBSCAN was used to reduce the influence of extreme values,and separate the core points,boundary points and noise points.The local density of each core point was used as weight to calculate the weighted center point of the cluster.Secondly,IDW was used to interpolate the weighted center point of the cluster,by which the number of data points needed to be interpolated could be significantly reduced and the electromagnetic spectrum map would be more accurate.Simulation results showed that compared with the IDW algorithm and the VIDW algorithm,the mean absolute error and the normalized mean square error of the electromagnetic spectrum map reconstructed by the proposed algorithm can be reduced by more than 10%and 23%respectively.