Affiliations: [a] College of Computer Science, South-Central University for Nationalities, Wuhan, 430074, Hubei, China. E-mail: 2018016@mail.scuec.edu.cn | [b] School of Faculty of Machinery and Electronics, Wuhan Railway Vocational and Technical College, Wuhan, 430205, Hubei, China. E-mail: chengfen1121@163.com
Abstract: With the development of society and the Internet and the advent of the cloud era, people began to pay attention to big data. The background of big data brings opportunities and challenges to the research of urban intelligent transportation networks. Urban transportation system is one of the important foundations for maintaining urban operation. The rapid development of the city has brought tremendous pressure on the traffic, and the congestion of urban traffic has restricted the healthy development of the city. Therefore, how to improve the urban transportation network model and improve transportation and transportation has become an urgent problem to be solved in urban development. Specific patterns hidden in large-scale crowd movements can be studied through transportation networks such as subway networks to explore urban subway transportation modes to support corresponding decisions in urban planning, transportation planning, public health, social networks, and so on. Research on urban subway traffic patterns is crucial. At the same time, a correct understanding of the behavior patterns and laws of residents’ travel is a key factor in solving urban traffic problems. Therefore, this paper takes the metro operation big data as the background, takes the passenger travel behavior in the urban subway transportation system as the research object, uses the behavior entropy to measure the human behavior, and actively explores the urban subway traffic mode based on the metro passenger behavior entropy in the context of big data. At the same time, the congestion degree of the subway station is analyzed, and the redundancy time optimization model of the subway train stop is established to improve the efficiency of the subway operation, so as to provide important and objective data and theoretical support for the traveler, planner and decision maker. Compared to the operation graph without redundant time, the total travel time optimization effect of passengers is 7.74%, and the waiting time optimization effect of passengers is 6.583%.
Keywords: Big data, urban subway traffic mode, behavioral entropy, congestion
