Subway short-time passenger flow prediction method based on machine learning

Abstract

The invention discloses a subway short-time passenger flow prediction method based on machine learning. On the basis of subway card shooting data, all passengers are assumed to travel according to the shortest route, and the flow of all intervals and in all stations is counted in a unit time window; subway station passenger flow in the unit time window serves as nodes, subway interval passenger flow in the unit time window serves as the weight of the edge, and a subway passenger flow network is built; features whose influences are most important to a single target interval are selected out to be brought into a follow-up regression prediction model. The recursive feature elimination algorithm is used for completing feature selection, and important features of the target interval in a target time window are selected out. The regression prediction model is built through the gradient boosted regression tree method, and subway short-time passenger flow prediction is achieved. High prediction precision can be achieved through the method under the condition that a data source is simplex. The regression prediction model is built through historical data and combined with real-time data to predict the subway short-time passenger flow, and help is provided for design optimization of urban rail transit operation marshalling.

Description

technical field [0001] The invention belongs to the technical field of transportation, and in particular relates to a method for predicting short-term passenger flow of subways based on machine learning. Background technique [0002] With the acceleration of urbanization in our country, urban traffic problems are becoming more and more prominent, and the urban rail transit system is the fundamental way to solve the public transportation in large and medium-sized cities, which is relatively closed and has a large number of people. Real-time and accurate rail transit passenger flow prediction is crucial to the optimization of urban rail transit operation formation design. This study proposes a method of combining the historical passenger flow data of the subway with real-time information, and predicting the short-term burst passenger flow of the subway with the help of machine learning. The study found that the prediction based on the combination of historical passenger flow ...

AI Technical Summary

Problems solved by technology

[0004] 1. Traditional forecasting methods, the forecasting results are not accurate

[0005] 2. The existing models with high prediction accuracy are relatively complex, and the data quality requirements are high, and even multi-source data need to be integrated

Images