Name
Abstract | ||
|---|---|---|
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. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/MDM48529.2020.00051 | 2020 21st IEEE International Conference on Mobile Data Management (MDM) |
Keywords | DocType | ISSN |
high-quality location based services,road categories,road segment attribute completion system,navigation system,OpenStreeMap,machine learning,nondeep learning,STEP,spatio-temporal data analytic platform,deep learning | Conference | 1551-6245 |
ISBN | Citations | PageRank |
978-1-7281-4664-5 | 0 | 0.34 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Razvan-Gabriel Cirstea | 1 | 7 | 0.78 |
| Hilmar Gustafsson | 2 | 0 | 0.34 |
| Rasmus Riis Gronbak Pedersen | 3 | 0 | 0.34 |
| Rolf Hakon Verder Sehested | 4 | 0 | 0.34 |
| Tamas Imre Winkler | 5 | 0 | 0.34 |
| Bin Yang | 6 | 706 | 34.93 |