Real-time prediction method for passenger flow volume of rail transit subway station

• Main Authors: LIU XIULIAN, HU HUA, LIU ZHIGANG, HAO YANXI, DENG ZIHUAN
• Format: Patent
• Language: Chinese; English
• Published: 22.11.2019
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; PHYSICS; WIRELESS COMMUNICATIONS NETWORKS

The invention belongs to the technical field of urban rail transit intelligent management. The real-time prediction method for the passenger flow volume of the rail transit subway station comprises the steps that the duration between the train departure moment before two adjacent trains of the subway station and the moment after the next train leaves the station for a period of time serves as a statistical period, and a certain peak time period of a current characteristic day is divided into N statistical periods; calculating the WiFi passenger flow Xt-1 of the whole subway station and the video passenger flow density of each congestion point area j in the last statistical period of the current characteristic day; wiFi passenger flow Xt-1 of a subway whole station and video passenger flowdensity of each congestion point area j in a previous statistical period of the current characteristic day are used as input; predicting the actual passenger flow Yt of the whole subway station in thecurrent statistical perio