arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.00340cs.LG
收藏

基于密集智能手机GPS轨迹和Transformer模型的交通模式检测

Detecting Transportation Mode Using Dense Smartphone GPS Trajectories and Transformer Models

University of California San Diego(加州大学圣地亚哥分校);McGill University(麦吉尔大学);Mila - Quebec AI Institute(魁北克人工智能研究所);University of Pennsylvania(宾夕法尼亚大学);Duke Kunshan University(杜克昆山大学)

Yuandong Zhang, Othmane Echchabi, Tianshu Feng, Wenyi Zhang, Hsuai-Kai Liao, Charles Chang

AI总结:

本文提出SpeedTransformer模型,利用速度输入从密集GPS轨迹中检测交通模式,实验表明其优于传统深度学习模型,并在不同地理区域表现出良好的迁移学习能力。

摘要:

交通模式检测是地理人工智能和交通研究中的重要课题。本文引入了SpeedTransformer,一种基于Transformer的新型模型,仅依赖速度输入从密集智能手机GPS轨迹中推断交通模式。在基准实验中,SpeedTransformer优于传统深度学习模型,如长短期记忆网络。此外,该模型在迁移学习中表现出强大的灵活性,通过少量数据集微调后,在不同地理区域均能实现高准确率。最后,我们部署了该模型进行实际实验,在复杂建筑环境和高数据不确定性条件下,其性能始终优于基线模型。这些发现表明,结合密集GPS轨迹的Transformer架构在交通模式检测和更广泛的移动性研究中具有重要潜力。

英文摘要:

Transportation mode detection is an important topic within GeoAI and transportation research. In this study, we introduce SpeedTransformer, a novel Transformer-based model that relies solely on speed inputs to infer transportation modes from dense smartphone GPS trajectories. In benchmark experiments, SpeedTransformer outperformed traditional deep learning models, such as the Long Short-Term Memory (LSTM) network. Moreover, the model demonstrated strong flexibility in transfer learning, achieving high accuracy across geographical regions after fine-tuning with small datasets. Finally, we deployed the model in a real-world experiment, where it consistently outperformed baseline models under complex built environments and high data uncertainty. These findings suggest that Transformer architectures, when combined with dense GPS trajectories, hold substantial potential for advancing transportation mode detection and broader mobility-related research.

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。

↑