Detecting Transportation Mode Using Dense Smartphone GPS Trajectories and Transformer Models

TL;DR

This study introduces SpeedTransformer, a novel Transformer-based model that relies solely on speed inputs to infer transportation modes from dense smartphone GPS trajectories, and demonstrates strong flexibility in transfer learning.

Abstract

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.

Figures (15)

• Figure 1: Transformer architecture
• Figure 2: Data Pre-Processing
• Figure 3: Validation accuracies over epochs for Geolife and MOBIS. The SpeedTransformer consistently converges faster and achieves higher overall accuracy than the LSTM-Attention baseline on both datasets.
• Figure 4: Per class F1-Score for Geolife and MOBIS trainings using SpeedTransformer and LSTM. The SpeedTransformer consistently achieves better results than the LSTM-Attention across all classes on both datasets.
• Figure 5: Trip tracking interface in the CarbonClever application: (a) Trip initiation screen, where users start a new trip recording. (b) Active tracking screen showing real-time trip duration and status. (c) Trip completion and mode confirmation screen, where users select and verify the transportation mode. All interface texts are originally in Chinese.