Crowd profiling algorithm mass transit data

被引：0

作者：

Zhang J. ^{[1
,2
]}

Wang F. ^{[3
]}

Guo Q. ^{[1
]}

机构：

[1] College of Information Science and Engineering, Hunan Normal University, Changsha

[2] School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha

[3] School of Mathematics and Statistics, Hunan Normal University, Changsha

来源：

Guofang Keji Daxue Xuebao/Journal of National University of Defense Technology | 2023年 / 45卷 / 02期

关键词：

crowd portraits; PageRank algorithm; text clustering; trajectory textualization;

D O I：

10.11887/j.cn.202302006

中图分类号：

学科分类号：

摘要：

Crowd profiling of massive transit data is valuable for analyzing the travel characteristics and traffic trends of urban groups, but the processing of the data is time-consuming, low-quality and difficult to interpret. A systematic solution for crowd profiling of massive public transport data was proposed. Based on the PageRank algorithm, the trajectories of people passing through important stations were filtered out, which greatly reduced the trajectory data of the target population. A textual analysis method for trajectories was proposed to improve the interpretability of crowd profiling. And the K-means algorithm based on cosine distance as the clustering algorithm for crowd profiling was analysed and determined. The experiments on 30 million passengers′ transit data show that the proposed algorithm can solve the problem of crowd profiling in massive transit data in a more systematic way, while the K-means algorithm based on cosine distance has the best clustering effect and the accuracy rate is about 80%. The crowd profiling and its trajectory were visually displayed by using Flow Map, and the results are consistent with real-world crowd behavioural characteristics. © 2023 National University of Defense Technology. All rights reserved.

引用

页码：55 / 64

页数：9

共 22 条

[1] ZHAO M X., Optimization of bus route network based on passenger travel characteristics method research[D], (2022)
[2] LEGARA E F T, MONTEROLA C P., Inferring passenger type from commuter eigentravel matrices, Transportmetrica B:Transport Dynamics, 6, 3, pp. 230-250, (2018)
[3] WANG C S, PU Y X., Analysis of classification and activity characteristics of urban residents based on Labeled-LDA model, Computer Applications and Software, 39, 11, pp. 17-24, (2022)
[4] WANG Y Y., Research on methods of extracting commuting trip characteristic based on public transportation multi-source data, (2014)
[5] CHENG J, LIU J J, GAO Y., Analyzing the spatio-temporal characteristics of Beijing′s OD trip volume based on time series clustering method[J], Journal of Geo-Information Science, 18, 9, pp. 1227-1239, (2016)
[6] SUN G D, ZHANG B, LIU Y Q, Et al., Taxi hot area function discovery based on passenger data[J], Computer Engineering, 43, 5, pp. 16-22, (2017)
[7] AL-DOHUKI S, WU Y Y, KAMW F, Et al., SemanticTraj:a new approach to interacting with massive taxi trajectories[J], IEEE Transactions on Visualization and Computer Graphics, 23, 1, pp. 11-20, (2017)
[8] LIU H, JIN S C, YAN Y Y, Et al., Visual analytics of taxi trajectory data via topical sub-trajectories[J], Visual Informatics, 3, 3, pp. 140-149, (2019)
[9] SANTOS F, ALMEIDA A, MARTINS C, Et al., Using POI functionality and accessibility levels for delivering personalized tourism recommendations[J], Computers, Environment and Urban Systems, 77, (2019)
[10] YE Z N, CHEN Y H, ZHANG L., The analysis of space use around Shanghai metro stations using dynamic data from mobile applications[J], Transportation Research Procedia, 25, pp. 3147-3160, (2017)

← 1 2 3 →