Research map / Image generation / Autoregressive and latent generation
SynMob: Creating High-Fidelity Synthetic GPS Trajectory Dataset for Urban Mobility Analysis
Yuanshao Zhu, Yongchao Ye, Ying Wu, Xiangyu Zhao, James Yu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| train on synthetic instead of original data | DCRNN · SYN-CHENGDU traffic demand prediction | RMSE: 7.29 -> 6.48 | Mixed |
| train on synthetic instead of original data | AGCRN · SYN-CHENGDU traffic demand prediction | MAPE: 30.47 -> 30.97 | No clear effect |
| train on synthetic instead of original data | MTGNN · SYN-CHENGDU traffic demand prediction | RMSE: 6.81 -> 6.41 | No clear effect |
| train on synthetic instead of original data | GWNet · SYN-CHENGDU traffic demand prediction | MAE: 4.65 -> 4.47 | No clear effect |
| train on synthetic instead of original data | DeepTTE · SYN-CHENGDU travel time estimation | RMSE: 216.93 -> 193.34 | Mixed |
| train on synthetic instead of original data | TEMP · SYN-CHENGDU travel time estimation | MAE: 182.74 -> 174.42 | No clear effect |
| train on synthetic instead of original data | XGBoost · SYN-CHENGDU travel time estimation | MAPE: 17.97 -> 16.94 | No clear effect |
| train on synthetic instead of original data | WDR · SYN-CHENGDU travel time estimation | RMSE: 258.64 -> 247.29 | No clear effect |
| use second synthetic dataset SYN-XI'AN instead of SYN-CHENGDU | GWNet · SYN-XI'AN traffic demand prediction | MAPE: 30.82 -> 32.53 | Mixed |
| use second synthetic dataset SYN-XI'AN instead of SYN-CHENGDU | DCRNN · SYN-XI'AN traffic demand prediction | MAPE: 30.83 -> 32.65 | Mixed |
| train on SYN-XI'AN synthetic instead of original data | WDR · SYN-XI'AN travel time estimation | RMSE: 221.90 -> 244.16 | Hurt |
| train on SYN-XI'AN synthetic instead of original data | DeepTTE · SYN-XI'AN travel time estimation | RMSE: 169.26 -> 172.51 | No clear effect |
Closest papers by meaning
- GTG: Generalizable Trajectory Generation Model for Urban Mobility (AAAI 2025 · similarity 0.86)
- Generative Human Trajectory Recovery via Embedding-Space Conditional Diffusion (ICML 2025 · similarity 0.86)
- Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarking (NeurIPS 2024 · similarity 0.85)
- BO4Mob: Bayesian Optimization Benchmarks for High-Dimensional Urban Mobility Problem (NeurIPS 2025 · similarity 0.85)
- Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities (NeurIPS 2025 · similarity 0.85)
- SeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow Benchmark (NeurIPS 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
