Modelling socioeconomic attributes of public transit passengers
- PDF / 2,446,286 Bytes
- 25 Pages / 439.37 x 666.142 pts Page_size
- 87 Downloads / 209 Views
Modelling socioeconomic attributes of public transit passengers Hamed Faroqi1 · Mahmoud Mesbah1,2 · Jiwon Kim1 Received: 15 May 2019 / Accepted: 8 June 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract The lack of personal and economic attributes in emerging public transit big data (such as smart card data) is a general issue that needs to be addressed. Passengers in the public transit network are from different socioeconomic classes, and their trip attributes usually depend on their personal and economic attributes. For instance, age as a demographic attribute plays an important role in trip attributes; adolescent passengers travel to school, young professionals travel to work, and old passengers travel to medical facilities more often. Relations between the socioeconomic and trip attributes of the passengers can be examined by developing a Bayesian network that represents the relations between the attributes by directed acyclic graphs, and calculating the joint and conditional probability values in the graph. This study infers the socioeconomic attributes of the public transit passengers from the trip attributes through developing a Bayesian network. Considered socioeconomic attributes are age, gender, and income; considered trip attributes are start time and duration of the trip, stay duration, and available origin and destination land use types. First, potential structures of the Bayesian network are examined by comparing network scores and arc strength test. After learning the network’s parameters, the reasoning is done through both prediction and diagnosis in the network. Also, the most likely combinations of the socioeconomic and trip attributes are discovered. The case study for developing the Bayesian network is a Household Travel Survey dataset from Queensland, Australia, that contains both socioeconomic and trip attributes. Results clearly show how the socioeconomic attributes can be inferred from the trip attributes. Discovered probability distributions can be used to enrich the smart card datasets with the socioeconomic attributes. Moreover, the Bayesian classifier is applied to the dataset to validate the capability of the model in predicting the socioeconomic attributes. In the end, the developed network is implemented on a set of smart card records to discuss the potential applications.
* Hamed Faroqi [email protected] Extended author information available on the last page of the article
13
Vol.:(0123456789)
H. Faroqi et al.
Keywords Probabilistic models · Decision graphs · Data mining · Spatial analyses · Travel surveys · Smart card data JEL Classification R00
1 Introduction Emerging big datasets in the public transit network have provided necessary grounds for developing novel applications and travel behaviour studies. However, these datasets lack important personal and economic attributes of passengers that traditionally have been used to develop transport models. Socioeconomic attributes of the passengers affect how they travel in the public transit network
Data Loading...
