关键词: 城市交通, 时间预测, 皮尔逊相关系数, 双参卷积理论模型, 出行时间, 机器学习

Abstract:

With the development of urban economy and the accelerated pace of people’s life, research on the travel time of people in the field of smart transportation has become a hot issue.The passing time in the estimated itinerary before travel makes it easier for people to plan the travel route more reasonably. Path planning based on time state characteristics is also one of the important means to solve the traffic problem.The existing models pay more attention to the vehicle arrival time or most of the predictions combined with the real and complete historical transit time data. There are few studies on whether the floating vehicle’s running state, vehicle speed, etc. have an impact on time.Based on this situation, this paper proposes a road time prediction model based on state features.In a fixed period of time, the trajectory data is deeply analyzed in combination with the situation of renting the vehicle passenger or not, the double parameter convolution theory model based on density partition is constructed based on vehicle speed, and the travel time is calculated by the final speed value.The experimental results show that the proposed model algorithm has higher accuracy and practicability than the traditional time prediction algorithm, which improves people’s rationalization and hierarchy of travel arrangements, and has important significance for formulating urban road travel strategies.

Key words: urban transportation, time series prediction, Pearson correlation coefficient, double parameter convolution, travel time, machine learning