Graph-based representation for identifying individual travel activities with spatiotemporal trajectories and POI data.
Graph-based representation for identifying individual travel activities with spatiotemporal trajectories and POI data.
复制标题
DOI：
10.1038/s41598-022-19441-9
复制
发表时间：
2022-09-21
影响因子：
4.6
通讯作者：
Huang, Qunying
中科院分区：
文献类型：
--
作者：
Liu, Xinyi;Wu, Meiliu;Peng, Bo;Huang, Qunying
个人日常旅行活动（例如，工作，吃饭）用各种机器学习模型（例如，贝叶斯网络，随机森林），用于了解人们经常旅行的目的。然而，劳动密集型的工程工作往往需要提取有效的功能。此外，特征和模型主要针对具有规律的日常行进例程和模式的个体轨迹进行校准，并且因此在应用于具有更不规则模式的新轨迹时遭受较差的概括性。同时，大多数现有的模型不能提取特征来显式地表示规则的出行活动序列。因此，本文提出了一种基于图的时空轨迹和兴趣点（POI）数据的旅行活动类型识别，定义为Gstp2Vec。具体地，通过连接规则活动区域（即，区域），其中边表示区域对之间的行程。轨迹的统计（例如，访问频率、活动持续时间）和POI分布（例如，餐馆的百分比）被编码为节点特征。接着，将出行频率、平均出行持续时间和平均出行距离编码为边权重。然后训练一系列前馈神经网络，通过从多跳邻域中采样和聚合时空和POI特征来生成活动节点的低维嵌入。通过旅行调查收集的活动类型标签被用作反向传播的地面实况。与真实世界的GPS轨迹的实验结果表明，Gstp2Vec显着减少特征工程的努力，自动学习的特征嵌入从原始轨迹与最小的preposing努力。该方法不仅提高了模型的泛化能力，对不同出行模式的测试个体轨迹具有更高的识别精度，而且具有更好的效率和鲁棒性。特别是，我们对最常见的日常旅行活动（例如，居住和工作）的人与不同的旅行模式优于国家的最先进的分类模型。
Individual daily travel activities (e.g., work, eating) are identified with various machine learning models (e.g., Bayesian Network, Random Forest) for understanding people’s frequent travel purposes. However, labor-intensive engineering work is often required to extract effective features. Additionally, features and models are mostly calibrated for individual trajectories with regular daily travel routines and patterns, and therefore suffer from poor generalizability when applied to new trajectories with more irregular patterns. Meanwhile, most existing models cannot extract features to explicitly represent regular travel activity sequences. Therefore, this paper proposes a graph-based representation of spatiotemporal trajectories and point-of-interest (POI) data for travel activity type identification, defined as Gstp2Vec. Specifically, a weighted directed graph is constructed by connecting regular activity areas (i.e., zones) detected via clustering individual daily travel trajectories as graph nodes, with edges denoting trips between pairs of zones. Statistics of trajectories (e.g., visit frequency, activity duration) and POI distributions (e.g., percentage of restaurants) at each activity zone are encoded as node features. Next, trip frequency, average trip duration, and average trip distance are encoded as edge weights. Then a series of feedforward neural networks are trained to generate low-dimensional embeddings for activity nodes through sampling and aggregating spatiotemporal and POI features from their multihop neighborhoods. Activity type labels collected via travel surveys are used as ground truth for backpropagation. The experiment results with real-world GPS trajectories show that Gstp2Vec significantly reduces feature engineering efforts by automatically learning feature embeddings from raw trajectories with minimal prepossessing efforts. It not only enhances model generalizability to receive higher identification accuracy on test individual trajectories with diverse travel patterns, but also obtains better efficiency and robustness. In particular, our identification of the most common daily travel activities (e.g., Dwelling and Work) for people with diverse travel patterns outperforms state-of-the-art classification models.
登录
查看更多内容
DOI：
10.1016/j.trc.2015.02.018
发表时间：
2015-09-01
影响因子：
8.3
作者：
Alexander, Lauren;Jiang, Shan;Gonzalez, Marta C.
通讯作者：
Gonzalez, Marta C.
影响因子：
3.4
作者：
Li, Chengming;Hu, Jiaxi;Wu, Zheng
通讯作者：
Wu, Zheng
影响因子：
2.8
作者：
Batty, M.;Axhausen, K. W.;Portugali, Y.
通讯作者：
Portugali, Y.
DOI：
10.1080/13658816.2016.1145225
发表时间：
2016-01-01
影响因子：
5.7
作者：
Huang, Qunying;Wong, David W. S.
通讯作者：
Wong, David W. S.
应用随机森林方法对出行模式选择行为进行建模
影响因子：
5.2
作者：
Cheng, Long;Chen, Xuewu;Witlox, Frank
通讯作者：
Witlox, Frank