Research on Taxi Operation Characteristics by Improved DBSCAN Density Clustering Algorithm and K-means Clustering Algorithm

Abstract With the development of urbanization, problem urban traffic congestion is becoming more and serious. An improved k-means clustering algorithm was proposed to solve that traditional center could easily be affected by fall into local optimal solution. Based on big data New York City taxis, operational characteristics are analyzed. The experimental results show K-means has a better analysis effect in terms hot demand for taxis.