Extracting Visited Points of Interest from Vehicle Trajectories

Ilkcan Keles; Matthias Schubert; Peer Kröger; Simonas Saltenis; Christian Søndergaard Jensen

doi:10.1145/3080546.3080552

Extracting Visited Points of Interest from Vehicle Trajectories

Ilkcan Keles, Matthias Schubert, Peer Kröger, Simonas Saltenis, Christian Søndergaard Jensen

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

8 Citations (Scopus)

Abstract

Identifying visited points of interest (PoIs) from vehicle trajectories remains an open problem that is difficult due to vehicles parking often at some distance from the visited PoI and due to some regions having a high PoI density. We propose a visited PoI extraction (VPE) method that identifies visited PoIs using a Bayesian network. The method considers stay duration, weekday, arrival time, and PoI category to compute the probability that a PoI is visited. We also provide a method to generate labeled data from unlabeled GPS trajectories. An experimental evaluation shows that VPE achieves a precision@3 value of 0.8, indicating that VPE is able to model the relationship between the temporal features of a stop and the category of the visited PoI.

Original language	English
Title of host publication	Proceedings of the Fourth International ACM Workshop on Managing and Mining Enriched Geo-Spatial Data
Number of pages	6
Publisher	Association for Computing Machinery
Publication date	2017
Article number	2
ISBN (Electronic)	978-1-4503-5047-1
DOIs	https://doi.org/10.1145/3080546.3080552
Publication status	Published - 2017
Event	Fourth International ACM SIGMOD Workshop on Managing and Mining Enriched Geo-Spatial Data - Chicago, United States Duration: 14 May 2017 → 19 May 2017

Workshop

Workshop	Fourth International ACM SIGMOD Workshop on Managing and Mining Enriched Geo-Spatial Data
Country/Territory	United States
City	Chicago
Period	14/05/2017 → 19/05/2017

Access to Document

10.1145/3080546.3080552

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{8d890cfabe3546e29023798692435411,

title = "Extracting Visited Points of Interest from Vehicle Trajectories",

abstract = "Identifying visited points of interest (PoIs) from vehicle trajectories remains an open problem that is difficult due to vehicles parking often at some distance from the visited PoI and due to some regions having a high PoI density. We propose a visited PoI extraction (VPE) method that identifies visited PoIs using a Bayesian network. The method considers stay duration, weekday, arrival time, and PoI category to compute the probability that a PoI is visited. We also provide a method to generate labeled data from unlabeled GPS trajectories. An experimental evaluation shows that VPE achieves a precision@3 value of 0.8, indicating that VPE is able to model the relationship between the temporal features of a stop and the category of the visited PoI.",

author = "Ilkcan Keles and Matthias Schubert and Peer Kr{\"o}ger and Simonas Saltenis and Jensen, {Christian S{\o}ndergaard}",

year = "2017",

doi = "10.1145/3080546.3080552",

language = "English",

booktitle = "Proceedings of the Fourth International ACM Workshop on Managing and Mining Enriched Geo-Spatial Data",

publisher = "Association for Computing Machinery",

address = "United States",

note = "Fourth International ACM SIGMOD Workshop on Managing and Mining Enriched Geo-Spatial Data ; Conference date: 14-05-2017 Through 19-05-2017",

}

Keles, I, Schubert, M, Kröger, P, Saltenis, S & Jensen, CS 2017, Extracting Visited Points of Interest from Vehicle Trajectories. in Proceedings of the Fourth International ACM Workshop on Managing and Mining Enriched Geo-Spatial Data., 2, Association for Computing Machinery, Fourth International ACM SIGMOD Workshop on Managing and Mining Enriched Geo-Spatial Data, Chicago, Illinois, United States, 14/05/2017. https://doi.org/10.1145/3080546.3080552

Extracting Visited Points of Interest from Vehicle Trajectories. / Keles, Ilkcan; Schubert, Matthias; Kröger, Peer et al.
Proceedings of the Fourth International ACM Workshop on Managing and Mining Enriched Geo-Spatial Data. Association for Computing Machinery, 2017. 2.

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Extracting Visited Points of Interest from Vehicle Trajectories

AU - Keles, Ilkcan

AU - Schubert, Matthias

AU - Kröger, Peer

AU - Saltenis, Simonas

AU - Jensen, Christian Søndergaard

PY - 2017

Y1 - 2017

N2 - Identifying visited points of interest (PoIs) from vehicle trajectories remains an open problem that is difficult due to vehicles parking often at some distance from the visited PoI and due to some regions having a high PoI density. We propose a visited PoI extraction (VPE) method that identifies visited PoIs using a Bayesian network. The method considers stay duration, weekday, arrival time, and PoI category to compute the probability that a PoI is visited. We also provide a method to generate labeled data from unlabeled GPS trajectories. An experimental evaluation shows that VPE achieves a precision@3 value of 0.8, indicating that VPE is able to model the relationship between the temporal features of a stop and the category of the visited PoI.

AB - Identifying visited points of interest (PoIs) from vehicle trajectories remains an open problem that is difficult due to vehicles parking often at some distance from the visited PoI and due to some regions having a high PoI density. We propose a visited PoI extraction (VPE) method that identifies visited PoIs using a Bayesian network. The method considers stay duration, weekday, arrival time, and PoI category to compute the probability that a PoI is visited. We also provide a method to generate labeled data from unlabeled GPS trajectories. An experimental evaluation shows that VPE achieves a precision@3 value of 0.8, indicating that VPE is able to model the relationship between the temporal features of a stop and the category of the visited PoI.

U2 - 10.1145/3080546.3080552

DO - 10.1145/3080546.3080552

M3 - Article in proceeding

BT - Proceedings of the Fourth International ACM Workshop on Managing and Mining Enriched Geo-Spatial Data

PB - Association for Computing Machinery

T2 - Fourth International ACM SIGMOD Workshop on Managing and Mining Enriched Geo-Spatial Data

Y2 - 14 May 2017 through 19 May 2017

ER -

Extracting Visited Points of Interest from Vehicle Trajectories

Abstract

Workshop

Access to Document

AUB Link

Fingerprint

Cite this