TY - GEN
T1 - A Road Segment Attribute Completion System
AU - Cirstea, Razvan Gabriel
AU - Gustafsson, Hilmar
AU - Pedersen, Rasmus Riis Gronbak
AU - Sehested, Rolf Hakon Verder
AU - Winkler, Tamas Imre
AU - Yang, Bin
N1 - Funding Information:
Acknowledgements: This work was supported by Independent Research Fund Denmark under agreements 8022-00246B and 8048-00038B.
Publisher Copyright:
© 2020 IEEE.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/6
Y1 - 2020/6
N2 - High-quality location based services rely on complete and accurate information of road segments. However, the attributes of road segments in online maps are often incomplete. For example, to compute fastest routes, a navigation system requires information, such as speed limits and road categories, of all road segments. While in OpenStreeMap, such attributes are often missing for many road segments. To contend with incomplete attributes, we propose a system that is able to utilize different machine learning techniques, including both non-deep learning and deep learning algorithms, to fill in the missing attributes. The system is developed and integrated into aSTEP, a spatio-Temporal data analytic platform developed by Aalborg University, and is tested using data collected from four major Danish cities.
AB - High-quality location based services rely on complete and accurate information of road segments. However, the attributes of road segments in online maps are often incomplete. For example, to compute fastest routes, a navigation system requires information, such as speed limits and road categories, of all road segments. While in OpenStreeMap, such attributes are often missing for many road segments. To contend with incomplete attributes, we propose a system that is able to utilize different machine learning techniques, including both non-deep learning and deep learning algorithms, to fill in the missing attributes. The system is developed and integrated into aSTEP, a spatio-Temporal data analytic platform developed by Aalborg University, and is tested using data collected from four major Danish cities.
UR - http://www.scopus.com/inward/record.url?scp=85090386668&partnerID=8YFLogxK
U2 - 10.1109/MDM48529.2020.00051
DO - 10.1109/MDM48529.2020.00051
M3 - Article in proceeding
AN - SCOPUS:85090386668
T3 - Proceedings - IEEE International Conference on Mobile Data Management
SP - 236
EP - 237
BT - Proceedings - 2020 21st IEEE International Conference on Mobile Data Management, MDM 2020
PB - IEEE
T2 - 21st IEEE International Conference on Mobile Data Management, MDM 2020
Y2 - 30 June 2020 through 3 July 2020
ER -