用手机轨迹速度数据，用Transformer模型精准识别出行方式。
Detecting Transportation Mode Using Dense Smartphone GPS Trajectories and Transformer Models
- 基于速度输入的Transformer模型，无需其他传感器数据。
- 在多区域测试中微调后准确率高，适应复杂城市环境。
- 适合做智慧城市、出行分析等实际应用的开发者参考。
交通模式检测是地理人工智能与交通研究的重要课题。本文提出SpeedTransformer，一种仅依赖速度输入的新型Transformer模型，用于从密集的智能手机GPS轨迹中推断出行方式。基准实验表明，SpeedTransformer优于传统深度学习模型（如长短期记忆网络，LSTM）。此外，该模型在迁移学习中表现出强适应性，经少量数据微调后即可在不同地理区域实现高准确率。最后，我们在真实场景中部署模型，发现其在复杂建成环境与高数据不确定性条件下持续优于基线模型。结果表明，结合密集GPS轨迹与Transformer架构，在交通模式检测及更广泛的移动性研究中具有巨大潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。