Narrow Results

The gravity model is a widely recognized tool for estimating the movement of people and goods. In this study, we introduce two gravitational variables, population size and regional GDP per capita (RGDPPC), to explain the characteristics of population movement between and within cities in South Korea. A log-linearized gravity model is employed to run regression analyses at three spatial levels: the national level (encompassing the entirety of South Korea), the metropolitan level (focusing on the Seoul and Busan Metropolitan Transportation Areas) and the city level (specifically in Seoul and Busan). The study incorporates data on various modes of transportation from 246 of the 250 municipalities in South Korea. Predictive performance of the model is better when utilizing national-level data. However, as spatial area decreases and population density increases, the models explanatory power decreases significantly when relying solely on data related to either population size or RGDPPC. The findings suggest that incorporation of both population size and RGDPPC into the gravity model best captures the dynamics of traffic flow within economically integrated regions. This relationship is analogous to gravitational fields generated by two distinct types of mass. Including both population size and RGDPPC, the gravity model can be leveraged effectively to estimate traffic patterns, particularly within regions characterized by high economic integration.

The unreasonable setting of urban bus stops is a common problem in real life, which seriously affects people’s happiness, sense of belonging and brand in the city. However, the existing related research on the above problems generally has the defects of high technical complexity and high cost. Therefore, we aim to propose a way to optimize the setting of urban public transportation stations and reduce the technical complexity and high cost of existing public transportation station optimization by using artificial intelligence algorithms. First, we extract and integrate bus GPS data and bus card swipe data in the business system and perform exploratory analysis on the pre-processed data. Second, the original k-NN algorithm is improved, and an ik-NN algorithm is proposed to determine the cardholder’s boarding point. Then, we divide the upstream and downstream lines to calculate the total number of upstream and downstream passengers. Third, we propose an algorithm for calculating the number of passengers getting off at bus stations and calculating the number of passengers getting on and off at each bus station. Finally, according to the number of passengers getting on and off at each bus station, the OD matrix is constructed, the residents’ travel rules are analyzed, and optimization suggestions for the setting of urban bus stations are proposed. This paper selects the public transit GPS data set and swipe card data set of Shenzhen, China for experiments. The experimental results show that: (1) Compared with K-means, the ik-NN algorithm we proposed can effectively determine the actual car station of each cardholder, and the algorithm is less sensitive to feature dimensions. At the same time, the ik-NN algorithm has a high operating efficiency and is less affected by the “$k$” value. (2) The calculation algorithm for the number of passengers getting off at bus stations can effectively use the existing data of the business system to determine the number of passengers getting off at each bus station. Therefore, the calculation times of this algorithm are low, and the accuracy is high. (3) The optimization suggestions for bus stations based on the OD matrix analysis of residents’ travel rules meet the needs of urban development and have certain reference value.