Tobacco distribution based on improved K-means algorithm

In order to solve the problem of distribution area segmentation of tobacco distribution, an improved k-means clustering algorithm was proposed in this paper. Firstly, the density of every node was calculated, and the first K nodes with the highest density were selected as initial clustering centers. Then the marginal nodes were prioritized to avoid the bad effect that marginal nodes might cause on clustering result. The experimental result demonstrated that the improved clustering algorithm not only avoided the local optima but also gave serious consideration to every important marginal node.