Abstract | ||
---|---|---|
The precise spatio-temporal position data of vehicles is useful for most studies, such as wireless link lifetime and node degree in vehicular ad hoc networks. However, due to the system errors and random errors, the existing Global Positioning System (GPS) only provides the positional accuracy about 10m or even worse. In this paper, to address the issue of positional accuracy, a Clustering and Approximating (C-A) algorithm is proposed. We first divide each road into several small parts which are described by linear functions. Then a linear regression algorithm is utilized to approximate traces under system errors, which is reliable for reducing GPS errors. Particularly, when two roads are very close, GPS points may be mapped on adjacent roads. A clustering algorithm is taken to separate GPS points and their positions are revised by the iterative utilization of the linear regression algorithm. In the end, the method mentioned above smoothes raw GPS data of buses in Taiwan to make it available for further researches. Compared with existing methods, the method described in this paper characterized with low cost and high reliability in different situations. Besides, its simple model will make the process of revising data more convenient. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/VTCFall.2016.7880866 | 2016 IEEE 84th Vehicular Technology Conference (VTC-Fall) |
Keywords | Field | DocType |
GPS points,linear regression algorithm,linear functions,C-A algorithm,clustering and approximating algorithm,positional accuracy,Global Positioning System,vehicular ad hoc networks,node degree,wireless link lifetime,spatio-temporal position data | Approximation algorithm,Data mining,Wireless,Computer science,Smoothing,Global Positioning System,Wireless ad hoc network,Cluster analysis,Linear function,Linear regression | Conference |
ISSN | ISBN | Citations |
2577-2465 | 978-1-5090-1702-7 | 0 |
PageRank | References | Authors |
0.34 | 10 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xun Zhou | 1 | 1 | 1.69 |
Changle Li | 2 | 375 | 51.60 |
Xiaoming Yuan | 3 | 21 | 5.73 |
Bing Xia | 4 | 2 | 2.39 |
Guoqiang Mao | 5 | 2474 | 156.87 |
Lei Xiong | 6 | 5 | 6.36 |