基于信息熵模型的地铁乘客出行规律稳定性度量
洪玲1,2原梦1,2刘伟3彭秀秀4江志彬1,2
Stability Measurement of Metro Passenger Travel Patterns Based on Information Entropy Model
HONG Ling1,2YUAN Meng1,2LIU Wei3PENG Xiuxiu4JIANG Zhibin1,2
-
作者信息:1.同济大学道路与交通工程教育部重点实验室，201804，上海
2.上海市轨道交通结构耐久与系统安全重点实验室，201804，上海
3.上海申通地铁集团有限公司技术中心，201103，上海
4.上海市隧道工程轨道交通设计研究院，200235，上海
-
Affiliation:1.Key Laboratory of Road and Traffic Engineering of the Ministry of Education, Tongji University, 201804, Shanghai, China
2.Shanghai Key Laboratory of Structural Durability and System Safety for Railway Transportation, 201804, Shanghai, China
3.Technical Center of Shanghai Shentong Metro Group Co., Ltd., 201103, Shanghai, China
4.Shanghai Tunnel Engineering & Rail Transit Design and Research Institute, 200235, Shanghai, China
-
关键词:
-
Key words:
-
DOI:10.16037/j.1007-869x.2025.03.017
-
中图分类号/CLCN:U293.13
-
栏目/Col:研究报告
摘要:
［目的］为更精确地度量城市轨道交通乘客个体出行规律稳定性，提升出行预测精度，解决现有信息熵模型在量化稳定性时存在的偏差问题，为交通规划和管理提供更可靠的数据支持。［方法］首先，构建以单日出行站点次序为基础的日出行链，作为分析乘客出行规律的核心数据结构。其次，基于LCS(最长公共子序列)算法设计日出行链相似性度量方法，通过计算日出行链之间的LCS长度评估其相似性，并构建相似度矩阵以表征个体出行的日间重复程度。为进一步提高稳定性度量的准确性，引入修正系数α对传统信息熵模型进行改进，以消除基础模型输出熵值中的偏离。最后，通过实际乘客出行案例，构建乘客日出行链，分别计算修正前后的信息熵值，对比分析模型改进效果，并验证其在不同乘客群体中的适用性。［结果及结论］改进后的信息熵模型能有效消除基础模型输出熵值中的偏离，对乘客出行链规律程度的量化输出更符合实际出行的稳定性特征，对多数乘客有较好的适应性。该方法为城市轨道交通乘客出行规律的精确度量提供了新的思路，有助于提升出行预测的精度和可靠性，为交通运营优化提供科学依据。
Abstracts:
［Objective］ It is aimed to more accurately measure the individual travel pattern stability of urban rail transit passengers, improve travel prediction accuracy, and address bias issues in existing information entropy models when quantifying stability, providing more reliable data support for transportation planning and management. ［Method］ First, a daily travel chain is constructed based on the sequence of stations visited in a single day, serving as the core data structure for analyzing passenger travel patterns. Next, a similarity measurement method for daily travel chains is designed based on LCS (longest common subsequence) algorithm. The similarity between daily travel chains is evaluated by calculating their LCS length, and a similarity matrix is constructed to present the daily travel repetition degree for individuals. To further enhance the accuracy of stability measurement, a correction coefficient α is introduced to improve the traditional information entropy model, eliminating deviations in the entropy values produced by the base model. Finally, real passenger travel cases are used to construct daily travel chains, and the information entropy values before and after correction are calculated. A comparative analysis is conducted to assess the effectiveness of the model improvements and verify its applicability to different passenger groups. ［Result & Conclusion］ The improved information entropy model effectively eliminates deviations in the entropy values of the base model, providing a more accurate quantification output of the passenger travel pattern stability, adequately adaptable to most passengers. This method offers a new approach to accurately measuring urban rail transit passenger travel patterns, helping to improve travel prediction accuracy and reliability while providing a scientific basis for optimizing transportation operations.
- 上一篇: 高铁物流运输模式及其可行性
- 下一篇: 基于频响应函数曲率微分相关性分析的钢轨轨底裂纹检测方法
过刊浏览
资料下载
友情链接