Hybrid Context-Aware Multimodal Routing

Abstract

Selecting the appropriate route in urban multimodal transport networks may require information from several sources, such as user preferences and contextual information. Such information could be used to choose different transport modes for a route, to avoid the use of hired private vehicles (HPV), like taxis, in certain segments of the trip with poor traffic conditions, for example. Therefore, this paper proposes the use of hybrid Hired Private Vehicles and Transit (HPV-transit) to enable a more personalized urban routing. User's impressions over trips' cost and duration are taken into account to select better hybrid routes. A taxi dataset was used to create graphs that map the main mobility flows in New York City. To create these graphs we propose a novel flow-based clustering technique which identifies trending mobility flows based on spatio-temporal datasets containing departures and arrivals. These flows are used to evaluate the performance of the hybrid HPV-transit. We compare the proposed solution with traditional transit or HPV only trips. It is possible to conclude that the adoption of HPV-transit trips can bring benefits in terms of cost and duration for urban mobility.

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 — 12 citations exist upstream.

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