Journal: Engineering and Management Science DOI: 10.32629/ems.v8i9.22154
Abstract
出行目的识别是理解居民出行行为规律、支撑交通规划与管理决策的关键环节。传统基于问卷调查的出行目的获取方法成本高、时效性差，难以满足精细化交通治理需求。本文利用手机GPS定位数据高精度、连续采样的优势，提出一种融合多源特征的多层证据链出行目的识别方法。首先，采用改进的时空密度聚类算法（ST-DBSCAN）识别个体出行停留点，提取出行端点及停留时长；其次，从时空特征、用地属性、POI语义、历史规律四个维度构建证据体系，分别量化各证据因子与出行目的的条件依赖关系；最后，基于贝叶斯网络实现多源证据的概率融合，输出最大后验概率对应的出行目的。实验结果表明，本文方法在典型出行目的识别中准确率达到87.5%，为城市交通需求分析与治理决策提供了有效支撑。
Keywords
手机GPS；出行目的；ST-DBSCAN；多源证据；贝叶斯网络
Full Text
PDF - Viewed/Downloaded: 0 TimesReferences
[1] Wolf J, Guensler R, Bachman W. Elimination of the travel diary: Experiment to derive trip purpose from global positioning system travel data[J]. Transportation Research Record, 2001, 1768(1): 125-134.
[2] Shen L, Stopher P R. A process for trip purpose imputation from Global Positioning System data[J]. Transportation Research Part C: Emerging Technologies, 2013, 36: 261-267.
[3] Liu F, Janssens D, Wets G, et al. Annotating mobile phone location data with activity purposes using machine learning algorithms[J]. Expert Systems with Applications, 2013, 40(8): 3299-3311.
[4] Xiao G, Juan Z, Zhang C. Detecting trip purposes from smartphone-based travel surveys with artificial neural networks and particle swarm optimization[J]. Transportation Research Part C: Emerging Technologies, 2016, 71: 447-463.
[5] Lyu S, Han T, Li P, et al. A dual-flow attentive network with feature crossing for chained trip purpose inference[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(1): 631-644.
[2] Shen L, Stopher P R. A process for trip purpose imputation from Global Positioning System data[J]. Transportation Research Part C: Emerging Technologies, 2013, 36: 261-267.
[3] Liu F, Janssens D, Wets G, et al. Annotating mobile phone location data with activity purposes using machine learning algorithms[J]. Expert Systems with Applications, 2013, 40(8): 3299-3311.
[4] Xiao G, Juan Z, Zhang C. Detecting trip purposes from smartphone-based travel surveys with artificial neural networks and particle swarm optimization[J]. Transportation Research Part C: Emerging Technologies, 2016, 71: 447-463.
[5] Lyu S, Han T, Li P, et al. A dual-flow attentive network with feature crossing for chained trip purpose inference[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(1): 631-644.
Copyright © 2026 王亮, 杨茜, 陈升升, 姚振兴
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License