Knowledge Discovery from Urban Trajectory Data: A Survey
Open Access
- 22 August 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (15) , 1-36
Abstract
Comprehending the mobility of entities in urban environments is crucial for developing and maintaining efficient and livable cities. This survey presents fundamental concepts, methods, and challenges related to knowledge discovery from urban trajectory data, including data acquisition, preprocessing, mining, and practical applications. Unlike previous studies, our survey offers a holistic and integrated view of these steps, ensuring that each stage is optimized to contribute to the overall performance of the mobility knowledge discovery process. Moreover, we identify operational and technical challenges, discussing potential future directions that can unlock new opportunities and advancements in this field.Keywords
Funding Information
- Institut national de recherche en informatique et en automatique (STIC AmSud LINT (code 22-STIC-07))
- Conselho Nacional de Desenvolvimento Científico e Tecnológico (312682/2021-2)
- Fundação de Amparo à Pesquisa do Estado de Minas Gerais (APQ-00426-22)
- Fundação de Amparo à Pesquisa do Estado de São Paulo (2023/00721-1)
- French National Research Agency as part of the PEPR MOBIDEC Mob Sci-Dat Factory project (ANR-23-PEMO-0004)
This publication has 163 references indexed in Scilit:
- Urban ride-hailing demand prediction with multi-view information fusion deep learning frameworkApplied Intelligence, 2022
- Understanding the impact of temporal scale on human movement analyticsJournal of Geographical Systems, 2022
- Location- and keyword-based querying of geo-textual data: a surveyThe VLDB Journal, 2021
- Context-aware, preference-based vehicle routingThe VLDB Journal, 2020
- Spatiotemporal clustering: a reviewArtificial Intelligence Review, 2019
- Analyzing large-scale human mobility data: a survey of machine learning methods and applicationsKnowledge and Information Systems, 2018
- Exploiting Sequential Influence for Personalized Location-Based Recommendation Systems2017
- Data representation for time series data mining: time domain approachesWIREs Computational Statistics, 2016
- The great time series classification bake off: a review and experimental evaluation of recent algorithmic advancesData Mining and Knowledge Discovery, 2016
- A review of moving object trajectory clustering algorithmsArtificial Intelligence Review, 2016