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)
Accepted for publication in the International Journal of Geographical Information Science, February 2026. This is the accepted manuscript. The final version of record will appear in IJGIS (Taylor and Francis)
发表信息:
International Journal of Geographical Information Science (2026)
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.
Semi-supervised GANs to Infer Travel Modes in GPS Trajectories
Transportation Research for Integrated Planning (TRIP) Lab(交通综合规划研究实验室);Concordia University(康考迪亚大学);Laboratory of Innovations in Transportation (LiTrans)(交通创新实验室);Ryerson University(瑞尔森大学)
BERT4Traj: Transformer Based Trajectory Reconstruction for Sparse Mobility Data
University of Georgia(佐治亚大学);Department of Geography University of Georgia(佐治亚大学地理系);College of Public Health University of Georgia(佐治亚大学公共卫生学院);University of Texas at Austin(德克萨斯大学奥斯汀分校)
Unsupervised Abnormal Stop Detection for Long Distance Coaches with Low-Frequency GPS
School of Information Science and Technology, Beijing University of Technology(北京工业大学信息科学与技术学院);Beijing Intelligent Transportation Development Center(北京市智能交通发展中心)
Beyond 9-to-5: A Generative Model for Augmenting Mobility Data of Underrepresented Shift Workers
Department of Civil and Environmental Engineering, Samueli School of Engineering, University of California at Los Angeles(土木与环境工程系,工程学院,加州大学洛杉矶分校);Novateur Research Solutions(Novateur研究解决方案)
针对轮班工作者在交通调查中代表性不足的问题,提出基于transformer的GPS轨迹生成方法,利用周期感知嵌入与转移损失补全其活动模式,并在Los Angeles County数据上取得平均JSD<0.02的分布对齐效果。
Micro-Macro Spatial-Temporal Graph-based Encoder-Decoder for Map-Constrained Trajectory Recovery
School of Computer and Information Technology, Beijing Jiaotong University(北京交通大学计算机与信息技术学院);Beijing Key Laboratory of Traffic Data Analysis and Mining(北京市交通数据分析与挖掘重点实验室)
Learning Citywide Patterns of Life from Trajectory Monitoring
Novateur Research Solutions(诺瓦图研究解决方案公司)
最近,真实世界人类移动数据集的激增促进了轨迹预测、需求预测、旅行时间估计和异常检测等方面的地理空间和交通研究。然而,这些数据集也可以更广泛地对复杂的人类流动系统进行描述性分析。我们将生命分析模式正式定义为在线无监督异常检测的自然,可解释的扩展,我们不仅监控数据流的异常,还明确提取正常模式。为了学习生活模式,我们将计算生物学和神经机器人学研究中的“需要时生长”(Grow When Required,GWR)情景记忆应用到地理空间分析的新领域。这种受生物启发的神经网络与自组织映射(SOM)相关,当它在GPS流上迭代时,会逐步构建一组“记忆”或原型交通模式。然后,它将每个新的观察结果与之前的经验进行比较,从而对数据进行在线、无监督的聚类和异常检测。我们从波尔图出租车数据集中挖掘感兴趣的模式,包括主要的公共假日和新发现的交通异常,如节日和音乐会,据我们所知,这些都是以前没有被承认或报告的。我们预计,逐步学习正常和异常道路交通行为的能力将在许多领域有用,包括智能城市、自动驾驶汽车以及城市规划和管理。