Social context awareness from taxi traces

Abstract

Mining social context from human mobility is an emerging area. This study aims to answer: Are there consistent associations to correlate people's collective mobility patterns with region functions? By applying co-training based multi-view spectral clustering to FFT represented traffic rhythms and Bags of POI based region function descriptors, we obtain consistent partition of the taxi GPS data and POI data in Beijing, that is, most data objects possess the same class labels when grouped using either feature separately. Therefore, region functions should be a critical factor to affect people's travel behaviors and it is possible to infer traffic patterns to be generated from newly planned region functions based on the associations between the data of two modalities so as to minimize traffic congestions at the urban planning stage.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 6 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.