No open-access location is known for this record yet.
No open-access location is known for this record yet.
The peak-hour cross-section passenger volume (PCPV) is a key index to characterize the travel demand of urban rail transit. To improve the forecasting accuracy of PCPV is of great importance in the urban rail transit passenger flow organization. Because of the expansive scale of urban rail transit network and the free transfer within it, the forecasting of PCPV is becoming more and more difficult. Thus a combined forecasting model based on correlation analysis is proposed in this paper to enhance the rationality and accuracy of PCPV forecasting. Firstly, key factors that affect PCPV are indentified. Secondly, regression models between PCPV and factors are established based on correlation analysis. An artificial neural network is utilized to analyze and forecast the PCPV time series, and then a combined forecasting model is constructed by regression approaches. A case study is conducted to show the effectiveness and practicability of the combined forecasting model through comparison.
Loading…
Stored only when both papers are in the corpus — 2 citations exist upstream.
Imported from OpenAlex (CC0) — nothing here is generated.