Zepu Wang, Luyao Niu, Ruolin Li, Jeff, Ban · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.26707 · cited by 0 works (OpenAlex) · open-access PDF
La detección de movilidad en red combina la inferencia de trayectoria local con el contexto geoespacial remoto, haciendo que las decisiones de comunicación formen parte del sistema de predicción. Presentamos GeoSplit, un marco de servidores para el reconocimiento del modo de viaje que separa la utilidad de la evidencia del mapa, su transferencia de tiempo de entrenamiento y su adquisición selectiva en el tiempo de ejecución. En GeoLife con etiquetas del 10%, evaluamos estos componentes bajo el agrupamiento del día del usuario y el desacuerdo del usuario. Para los usuarios invisibles, el contexto de mapa completo alineado eleva la macro-F1 de 0.7154 a 0.7864, mientras que la destilación informada por el mapa produce un estudiante solo en movimiento en 0.7225. A través de una interfaz de
Machine translation (Meta M2M100); the English original follows.
Networked mobility sensing couples local trajectory inference with remote geospatial context, making communication decisions part of the prediction system. We present GeoSplit, an edge--server framework for travel-mode recognition that separates the utility of map evidence, its training-time transfer, and its selective acquisition at runtime. On GeoLife with 10% labels, we evaluate these components under user-day and user-disjoint grouping. For unseen users, aligned full-map context raises macro-F1 from 0.7154 to 0.7864, while map-informed distillation yields a motion-only student at 0.7225. Through a compact query interface, entropy gating achieves 0.7729 macro-F1 versus 0.7738 for all queries, querying 39.5% of trajectories and reducing application payload by 60.5%. Under user-day grouping, selective and all-query scores are similarly close at a 21.6% query rate. Learned value estimation and probability fusion offer no consistent improvement. These results illustrate communication-efficient edge--server inference for an intelligent transportation sensing task.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Inference, Artificial intelligence, Geospatial analysis, Trajectory, Context (archaeology)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26707, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange