Cluster analysis based and threshold based selection localization algorithm for WSN

To improve nodes localization accuracy for wireless sensor network (WSN), we propose an optimized selection localization algorithm based on fuzzy c-means (FCM). By cluster analysis, algorithm can figure out the distance data which are far more beyond their true value, and then removes those data. Each three beacon nodes are selected to form groups. The groups are selected based on the ranges between nodes. Then in a group, beacon nodes acts as center to draw circles, and the ranges between unknown nodes are used as radii. Then the overlapping region is divided into four parts. The centroid and area of each part will be calculated. The ratio of each area will be the weight to calculate the centroid. Simulation results show that compared with the existing algorithms the optimized algorithm has been reduced the localization error.