Visualization model of big data based on self-organizing feature map neural network and graphic theory for smart cities

The process of current urban and accelerating the number of motor vehicles increased rapidly resulting in road traffic pressure is increasing, we need to analyze large data traffic in the city, to guide urban road planning and improve the level of city management, and city operation rules found from traffic data in complex. However, traffic data are characterized by large amount and high dimension, which makes the analysis process difficult. In this paper, the composition, characteristics and application of large data in traffic field are introduced. Mining multi-source heterogeneous data traffic generated by the depth of the traffic data to establish a comprehensive analysis platform and project evaluation subsystem, the formation of integrated traffic system model for multi field, multi-level application requirements. In this paper, we propose a visualization model based on self-organizing feature map neural networks with graph theory. This paper analyzes the traffic data of the whole life cycle, combing the traffic data collection, analysis, discovery, the level of application, and uses big data techniques to guide the city traffic planning, construction, management, operation and decision support.