基于WiFi数据的地铁车站客流预警模型

为了降低地铁车站因客流增加或突发事件产生的客流安全风险，提出了基于WiFi探针检测数据的地铁车站客流预警模型。基于WiFi探针客流数据采集原理、数据属性特征和探针网络化布设方案，实现了对WiFi探针原始数据的预处理。同时建立了基于时间序列的地铁车站短时客流预测模型，并与线性回归模型进行了比较，通过计算地铁车站客流承载能力，构建了车站客流预警指标和分级预警模型。最后以上海地铁江苏路站为例进行模型验证，结果表明，基于WiFi探针技术的地铁车站客流检测和预测模型具备可行性和有效性，且预警模型对客流预警应用和研究有一定的参考意义。

Early-Warning Model of Metro Station Passenger Flow Based on WiFi Data

In order to solve the problem of passenger flow security risks caused by increased passenger flow and sudden passenger flow at metro stations, a method for early warning of passenger flow at metro stations based on WiFi probe detection data is proposed. Firstly, based on the WiFi probe passenger flow data detection principle, station layout and analysis of passenger flow characteristics, the probe’s raw data is preprocessed, and then a short-term passenger flow prediction model is established based on time series. Then through the calculation of the carrying capacity of the metro station, the station passenger flow early warning indicator and the passenger flow classification early warning model are constructed. Finally, the Shanghai Metro Jiangsu Road Station is used as an example of model verification. The results show that the WiFi probe technology-based subway station passenger flow detection and prediction model is feasible and effective, and the early warning model has some reference significance for passenger flow early warning application and research.