X
Xiaoliang Fan
Researcher at Xiamen University
Publications - 64
Citations - 1349
Xiaoliang Fan is an academic researcher from Xiamen University. The author has contributed to research in topics: Workflow & Web service. The author has an hindex of 11, co-authored 57 publications receiving 515 citations. Previous affiliations of Xiaoliang Fan include Lanzhou University.
Papers
More filters
Journal ArticleDOI
GMAN: A Graph Multi-Attention Network for Traffic Prediction
TL;DR: GMAN as mentioned in this paper adapts an encoder-decoder architecture, where both the encoder and the decoder consist of multiple spatio-temporal attention blocks to model the impact of the spatiotemporal factors on traffic conditions, and proposes a graph multi-attention network (GMAN) to predict traffic conditions for time steps ahead at different locations on a road network graph.
Posted Content
GMAN: A Graph Multi-Attention Network for Traffic Prediction
TL;DR: Experimental results on two real-world traffic prediction tasks demonstrate the superiority of GMAN, and in the 1 hour ahead prediction, GMAN outperforms state-of-the-art methods by up to 4% improvement in MAE measure.
Journal ArticleDOI
Characterization and temperature controlling property of TiAlN coatings deposited by reactive magnetron co-sputtering
TL;DR: In this paper, a ternary coating of titanium aluminum nitride (TiAlN) was applied on satellite for thermal controlling in order to investigate thermal controlling property, and the results showed that the surface of the coatings becomes more compact and smoother with the N 2 /Ar ratios increase.
Journal ArticleDOI
DeepSTD: Mining Spatio-Temporal Disturbances of Multiple Context Factors for Citywide Traffic Flow Prediction
TL;DR: A two-phase end-to-end deep learning framework, namely DeepSTD to uncover the spatio-temporal disturbances (STD) to predict the citywide traffic flow and demonstrates that DeepSTD outperforms the state-of-the-art methods.
Journal ArticleDOI
Predicting duration of traffic accidents based on cost-sensitive Bayesian network and weighted K-nearest neighbor
TL;DR: This article proposes a two-level model, which consists of a cost-sensitive Bayesian network and a weighted K-nearest neighbor model, to predict the duration of accidents, and shows that the proposed approach achieves higher accuracy compared with classical models.