Extracting activity patterns from taxi trajectory data: a two-layer framework using spatio-temporal clustering, Bayesian probability and Monte Carlo simulation

ABSTRACT

Global positioning system (GPS) data generated from taxi trips is a valuable source of information that offers an insight into travel behaviours of urban populations with high spatio-temporal resolution. However, in its raw form, GPS taxi data does not offer information on the purpose (or intended activity) of travel. In this context, to enhance the utility of taxi GPS data sets, we propose a two-layer framework to identify the related activities of each taxi trip automatically and estimate the return trips and successive activities after the trip, by using geographic point-of-interest (POI) data and a combination of spatio-temporal clustering, Bayesian inference and Monte Carlo simulation. Two million taxi trips in New York, the United States of America, and ten million taxi trips in Shenzhen, China, are used as inputs for the two-layer framework. To validate each layer of the framework, we collect 6,003 trip diaries in New York and 712 questionnaire surveys in Shenzhen. The results show that the first layer of the framework performs better than comparable methods published in the literature, while the second layer has high accuracy when inferring return trips.

KEYWORDS:

• Spatio-temporal clustering
• Bayesian probabilities
• Monte Carlo simulation
• travel behaviours

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported by Ningbo Science and Technology Bureau [2017D10034, 2014A35006]; Zhejiang Natural Science Foundation [LR17G010001]; Shenzhen Scientific Research and Development Funding Program [CXZZS20150504141623042]; the UK Engineering and Physical Sciences Research Council [EP/L015463/1]; and Refinitiv (formerly Thomson Reuters Financial and Risk), National Science Foundation of China [41671387,71471092,91546106].

Notes on contributors

Shuhui Gong

Shuhui Gong is the PhD candidate in the University of Nottingham, Ningbo China. Her research interests includes GIS, computer, geography, urban science and other related fields.

John Cartlidge

John Carlidge is the Refinitiv Lecturer in Data Science and Financial Informatics in the department of computer science, University of Bristol. His research interests includes financial technology, trading technologies, data science, and machine learning.

Ruibin Bai

Ruibin Bai is the head of computer science, in the University of Nottingham Ningbo China. His research interests are mainly focused on employing latest search and machine learning techniques (Meta-heuristics, Hyper-heuristics, Evolutionary Algorithms, and Machine Learning) as well as conventional optimisation approaches (LP/IP/MIP, Branch & Bound, Cutting Plane, Nonlinear Programming) to solve various real-world problem applications, including transportation scheduling, space planning, and timetabling.

Yang Yue

Yang Yue is the head of the school of architecture and urban planning, in the department of urban spatial information engineering, Shenzhen university. She has presided over a number of national natural science foundation projects, as well as cooperative scientific research projects from Microsoft, Siemens, tencent and other industries. She also served as academic services in GIS, computer, geography, urban science and other fields.

Qingquan Li

Qingquan Li is the president of shenzhen university, former executive vice President of wuhan university. He is also the director of key laboratory of national bureau of surveying, mapping and geographic information of coastal zone geographical environment monitoring, and the director of key laboratory of spatial information intelligent perception and service of shenzhen municipality. He has engaged in teaching and scientific research of geographical information system, intelligent transportation and 3S integration for a long time.

Guoping Qiu

Guoping Qiu in the professor both in the University of Nottingham, UK, and in Shenzhen University. He has been engaged in the teaching and research of image processing, computer vision, machine learning and multimedia signal processing for more than 20 years.