Analysis of bus travel characteristics and predictions of elderly passenger flow based on smart card data
Analysis of bus travel characteristics and predictions of elderly passenger flow based on smart card data
复制标题
DOI：
10.3934/era.2022217
复制
发表时间：
2022
影响因子：
0.8
通讯作者：
Gang Cheng;Changliang He
中科院分区：
文献类型：
--
作者：
Gang Cheng;Changliang He
优惠的公共交通政策为老年人出行提供了重要的社会福利支持。然而，老年人面临的出行问题，如高峰时段的交通拥堵，并没有引起交通相关部门的足够重视。本研究提出老年人乘坐公共交通的客流预测模型，并利用公交智能卡数据对模型进行验证。本研究采用短时间序列聚类（STSC）方法整合老年人公交出行异质性要素，通过分析客流时空特征，准确识别老年乘客需求。根据客流的需求和特点，构建了短时间序列聚类季节性自回归综合移动平均（STSC-SARIMA）模型进行客流预测。时空出行特征分析确定了老年人每天出行的三个高峰期。与其他时段相比，早高峰的出行人数明显更多。同时，与途经中心城区、多社区和人口密集地区的公交线路相比，其他地区的公交线路客流量明显下降。该研究模型应用于中国拉萨。预测结果表明，该模型具有较高的预测精度和适用性。除了初步应用外，该预测模型为巴士客流预测提供了新的方向，以支持更好的公共交通政策制定和改善老年人的流动性。
Preferential public transport policies provide an important social welfare support for travel by the elderly. However, the travel problems faced by the elderly, such as traffic congestion during peak hours, have not attracted enough attention from transportation-related departments. This study proposes a passenger flow prediction model for the elderly taking public transport and validates it using bus smart card data. The study incorporates short time series clustering (STSC) to integrate the elements of the heterogeneity of bus trips taken by the elderly, and accurately identifies the needs of elderly passengers by analysing passenger flow spatiotemporal characteristics. According to the needs and characteristics of passenger flow, a short time series clustering Seasonal Autoregressive Integrated Moving Average (STSC-SARIMA) model was constructed to predict passenger flow. The analysis of spatiotemporal travel characteristics identified three peak periods for the elderly to travel every day. The number of people traveling in the morning peak was significantly larger compared to other periods. At the same time, compared with bus lines running through central urban areas, multi-community, and densely populated areas, the passenger flow of bus lines in other areas dropped significantly. The study model was applied to Lhasa, China. The prediction results verify that the model has high prediction accuracy and applicability. In addition to the initial application, this predictive model provides new directions for bus passenger flow forecasting to support better public transport policy-making and improve elderly mobility.