Analysing the spatial-temporal characteristics of bus travel demand using the heat map

Document Type

Journal Article

Publication Date

2017

Subject Area

place - asia, place - urban, mode - bus, ridership - demand, planning - surveys, technology - passenger information, operations - service span

Keywords

Bus travel demand, Bus service evaluation, Smart card data, Data visualisation, Heat maps, Spatial-temporal characteristics

Abstract

As the basic travel service for urban transit, bus services carry the majority of urban passengers. The characterisation of urban residents' transit trips can provide a first-hand reference for the evaluation, management and planning of public transport. Over the past two decades, data from smart cards have become a new source of travel survey data, providing more comprehensive spatial-temporal information about urban public transport trips. In this paper, a multi-step methodology for mining smart card data is developed to analyse the spatial-temporal characteristics of bus travel demand. Using the bus network in Guangzhou, China, as a case study, a smart card dataset is first processed to quantitatively estimate the travel demand at the bus stop level. The term ‘bus service coverage’ is introduced to map the bus travel demand from bus stops to regions. This dataset is used to create heat maps that visualise the regional distribution of bus travel demand. To identify the distribution patterns of bus travel demand, two-dimensional principal component analysis and principal component analysis are applied to extract the features of the heat maps, and the Gaussian mixture model is used for the feature clustering. The proposed methodology visually reveals the spatial-temporal patterns of bus travel demand and provides a practical set of visual analytics for transit trip characterisation.

Rights

Permission to publish the abstract has been given by Elsevier, copyright remains with them.

Comments

Journal of Transport Geography home Page:

http://www.sciencedirect.com/science/journal/09666923

Share

COinS