Research on Community Division Algorithm with Directed and Weighted Network in Pervasive Sensing Environment

In view of the existing community network division algorithm without considering the weight and direction of the edge, we propose a novel algorithm in Pervasive Sensing Environment. Based on the node optimal path, the algorithm calculates the optimal path tree of mobile nodes, similarity index and community dispersion index and so on parameters to realize the reasonable division for directed weighted community network. The experimental results show that the accuracy of the algorithm is to achieve an average of 95%, higher than existing models about 10.9%. In addition, the algorithm still has good accuracy for other different types of network data, further demonstrated the efficiency and scalability of the algorithm.