Rail transit passenger flow predicting method for predicting passenger travel probability and based on support vector machine (SVM)

Abstract

A rail transit passenger flow predicting method for predicting passenger travel probability and based on a support vector machine (SVM) includes the following steps: 1 collecting rail transit historical data including a starting station and a destination station of a passenger travel, station entering time and station leaving time; 2 acquiring passenger travel proportion in a statistics mode based on the historical data; 3 training the least square SVM according to the travel proportion obtained by statistics to predict the passenger travel probability; 4 storing the predicted travel proportion for a real-time passenger flow prediction module; 5 collecting real-time station entering passenger flow data which is used as a set of passenger station entering records; 6 acquiring the passenger travel probability at the station and stored in the step 4 and predicting the destination station of the passenger travel; 7 simulating the passenger travel by combining the departure interval of trains, calculating the time when the passengers reach and leave each station and updating full-road-network passenger flow. By means of the method, prediction is conducted by utilizing the passenger travel law, the station entering passenger flow can be predicted in real time, and prediction accuracy is high.

Description

technical field [0001] The invention provides a rail transit passenger flow prediction method based on a support vector machine (Support Vector Machine or SVM) to predict passenger travel probability, that is, provides a rail transit passenger flow prediction method based on SVM to predict passenger travel probability, and belongs to the field of computer application technology. Background technique [0002] With the rapid development of the national economy, the continuous acceleration of the urbanization process, and the continuous increase of urban population density, the pressure on urban traffic is gradually increasing. Rail transit has the characteristics of large passenger volume, fast speed, accurate time, long distance, high comfort, and little influence from external factors. Nowadays, it has been regarded as one of the key construction projects by more and more cities. [0003] Rail transit passenger flow prediction is based on rail transit operation data, predict...

AI Technical Summary

Problems solved by technology

[0009] The biggest problem with the above method is to deal with a subway station in isolation, without treating the subway network as a whole, so it is impossible to use passenger travel patterns to make predictions, which reduces the accuracy of predictions

Images