Loading...
Please wait, while we are loading the content...
Similar Documents
Feature Extraction and Representation of Urban Road Networks Based on Travel Routes
| Content Provider | MDPI |
|---|---|
| Author | Huang, Shichen Shao, Chunfu Li, Juan Yang, Xiong Zhang, Xiaoyu Qian, Jianpei Wang, Shengyou |
| Copyright Year | 2020 |
| Description | [d=LANG.]Eextraction of traffic features [d=LANG.]constitutesis a key research direction in traffic safety planning. [d=S.H.]In previous traffic tasks, road network features are extracted manually.Although specific domain knowledge can be used to design features, different traffic tasks require careful effort in engineering features. [d=LANG.]In contrastConversely, Network Representation Learning aims to automatically learn low-dimensional node representations. Enlightened by feature learning in Natural Language Processing, representation learning of urban nodes is studied as a supervised task in this paper. [d=LANG.]Following this line of thinkingAlong this way, a deep learning framework, called StreetNode2VEC, is proposed for learning feature representations for nodes in the road network based on travel routes, and then model parameter calibration is performed. We explain the effectiveness of features from visualization, similarity analysis, and link prediction. In visualization, the features of nodes naturally present a clustered pattern, and different clusters correspond to different regions in the road network. [d=LANG.]Mmeanwhile, the features of nodes still retain their spatial information in similarity analysis. The proposed method StreetNode2VEC obtains a AUC score of 0.813 in link prediction, [d=LANG.]which is greater than that obtained from Graph Convolutional Network (GCN) and Node2vecwhich is more than GCN and Node2vec. This suggests that the features of nodes can be used to effectively and credibly predict whether a link should be established between two nodes. Overall, our work provides a new way [d=LANG.]of representingfor the representations of road nodes in the road network, which have potential in the traffic safety planning field. |
| Starting Page | 9621 |
| e-ISSN | 20711050 |
| DOI | 10.3390/su12229621 |
| Journal | Sustainability |
| Issue Number | 22 |
| Volume Number | 12 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2020-11-18 |
| Access Restriction | Open |
| Subject Keyword | Sustainability Transportation Science and Technology Intelligent Transportation System Urban Road Network Graph Embedding Deep Learning Feature Extraction |
| Content Type | Text |
| Resource Type | Article |
