Detecting Transportation Mode Using Dense Smartphone GPS Trajectories and Transformer Models
This work addresses the problem of accurately detecting transportation modes for GeoAI and transportation research, offering incremental improvements with a novel method.
The paper tackled transportation mode detection from smartphone GPS trajectories by introducing SpeedTransformer, a Transformer-based model using only speed inputs, which outperformed traditional deep learning models like LSTM in benchmarks and showed high accuracy in transfer learning and real-world experiments.
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.