用Transformer重建稀疏轨迹，提升移动行为分析精度
BERT4Traj: Transformer Based Trajectory Reconstruction for Sparse Mobility Data
- 基于BERT思想设计轨迹补全模型，融合时空与上下文特征
- 在乌干达数据上优于马尔可夫、KNN、RNN等传统方法
- 适合城市规划、公共卫生等需要连续轨迹的场景
理解人类移动行为对公共健康、交通管理与城市规划至关重要。然而，由于数据采集限制（如低频GPS采样或仅记录通话时位置的通话详单数据），移动数据常呈现稀疏性。为此，我们提出BERT4Traj，一种基于Transformer的轨迹重建模型，通过预测稀疏移动序列中的隐藏访问点来还原完整轨迹。该模型受BERT的掩码语言建模目标与自注意力机制启发，结合空间嵌入、时间嵌入及人口统计、锚点等上下文特征。我们在乌干达坎帕拉的真实通话详单与GPS数据集上进行评估，结果表明，该方法显著优于马尔可夫链、KNN、RNN和LSTM等传统模型。实验显示，BERT4Traj能有效重构出细节丰富且连续的移动轨迹，增强对人类移动模式的洞察。
原文摘要 · Abstract (English)
Understanding human mobility is essential for applications in public health, transportation, and urban planning. However, mobility data often suffers from sparsity due to limitations in data collection methods, such as infrequent GPS sampling or call detail record (CDR) data that only capture locations during communication events. To address this challenge, we propose BERT4Traj, a transformer based model that reconstructs complete mobility trajectories by predicting hidden visits in sparse movement sequences. Inspired by BERT's masked language modeling objective and self_attention mechanisms, BERT4Traj leverages spatial embeddings, temporal embeddings, and contextual background features such as demographics and anchor points. We evaluate BERT4Traj on real world CDR and GPS datasets collected in Kampala, Uganda, demonstrating that our approach significantly outperforms traditional models such as Markov Chains, KNN, RNNs, and LSTMs. Our results show that BERT4Traj effectively reconstructs detailed and continuous mobility trajectories, enhancing insights into human movement patterns.
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。