arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.00276cs.LG
收藏

面向交通需求预测的灵活节点图构建方法

Graph Construction with Flexible Nodes for Traffic Demand Prediction

Jinyan Hou, Shan Liu, Ya Zhang, Haotong Qin

AI总结:

本文针对自由浮动交通需求预测中道路网络匹配不灵活的问题,提出基于密度聚类算法HDPC-L的灵活节点图构建方法,并利用客流数据初始化GNN边权重,在深圳共享单车和海口网约车数据集上显著提升预测精度与计算效率。

摘要:

图神经网络(GNNs)已被广泛应用于交通需求预测,交通出行方式可分为基于站点的模式和自由浮动交通模式。现有交通图构建研究主要依赖地图匹配,基于道路网络来构建图。然而,自由浮动交通需求预测中数据分布的复杂性和不均匀性使得道路网络匹配缺乏灵活性。为应对这些挑战,本文提出了一种专为自由浮动交通模式设计的新型图构建方法。我们提出了一种新颖的基于密度的聚类算法(HDPC-L)来确定图中节点的灵活位置,克服了传统聚类算法的计算瓶颈,并能够有效处理大规模数据集。此外,我们从客流数据中提取有价值的信息来初始化GNNs的边权重。在两个真实世界数据集——深圳共享单车数据集和海口网约车数据集上的综合实验表明,该方法显著提升了模型性能。平均而言,我们的模型在这两个数据集上的准确率分别提高了约25%和19.5%。同时,该方法显著提升了计算效率,在这两个数据集上的训练时间分别减少了约12%和32.5%。我们的代码已公开于https://github.com/houjinyan/HDPC-L-ODInit。

英文摘要:

Graph neural networks (GNNs) have been widely applied in traffic demand prediction, and transportation modes can be divided into station-based mode and free-floating traffic mode. Existing research in traffic graph construction primarily relies on map matching to construct graphs based on the road network. However, the complexity and inhomogeneity of data distribution in free-floating traffic demand forecasting make road network matching inflexible. To tackle these challenges, this paper introduces a novel graph construction method tailored to free-floating traffic mode. We propose a novel density-based clustering algorithm (HDPC-L) to determine the flexible positioning of nodes in the graph, overcoming the computational bottlenecks of traditional clustering algorithms and enabling effective handling of large-scale datasets. Furthermore, we extract valuable information from ridership data to initialize the edge weights of GNNs. Comprehensive experiments on two real-world datasets, the Shenzhen bike-sharing dataset and the Haikou ride-hailing dataset, show that the method significantly improves the performance of the model. On average, our models show an improvement in accuracy of around 25\% and 19.5\% on the two datasets. Additionally, it significantly enhances computational efficiency, reducing training time by approximately 12% and 32.5% on the two datasets. We make our code available at https://github.com/houjinyan/HDPC-L-ODInit.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑