Station passenger flow forecast for urban rail transit based on station attributes

Abstract

The new line station passenger flow forecast for urban rail is important in public transport service. The lack of the historical data of new rail line makes the forecast be a challenge. Traditional method always forecast the station passenger flow based on the land use numerical indicators, which is complex and not accurate. This paper proposes a novel passenger flow forecast method based on station attributes for urban rail. This method learns the passenger flow regularity and its impact factors from historical data of existing stations, and then forecast the passenger flow of new line station after evaluating the attributes of new station. It not only considers the characteristics of new line station, but also considers the regularity of existing stations. Experiment results show that our method can forecast the passenger flow on each hour throughout the day, and do not need large detailed investigation, which is more precision and convenient.

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 — 7 citations exist upstream.

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