Smart City Gnosys

Smart city article details

Title	Dual Temporal Gated Multi-Graph Convolution Network For Taxi Demand Prediction
ID_Doc	21159
Authors	Yang T.; Tang X.; Liu R.
Year	2023
Published	Neural Computing and Applications, 35, 18
DOI	http://dx.doi.org/10.1007/s00521-021-06092-6
Abstract	Taxi demand prediction is essential to build efficient traffic transportation systems for smart city. It helps to properly allocate vehicles, ease the traffic pressure and improve passengers’ experience. Traditional taxi demand prediction methods mostly rely on time-series forecasting techniques, which cannot model the nonlinearity embedded in data. Recent studies start to combine the Euclidean spatial features through grid-based methods. By considering the spatial correlations among different regions, we can capture how the temporal events have impacts on those with adjacent links or intersections and improve prediction precision. Some graph-based models are proposed to encode the non-Euclidean correlations as well. However, the temporal periodicity of data is often overlooked, and the study units are usually constructed as oversimplified grids. In this paper, we define places with specific semantic and humanistic experiences as study units, using a fuzzy set method based on adaptive kernel density estimation. Then, we introduce dual temporal gated multi-graph convolution network to predict the future taxi demand. Specifically, multi-graph convolution is used to model spatial correlations with graphs, including the neighborhood, functional similarities and landscape similarities based on street view images. As for the temporal dependencies modeling, we design the dual temporal gated branches to capture information hidden in both previous and periodic observations. Experiments on two real-world datasets show the effectiveness of our model over the baselines. © 2021, The Author(s).
Author Keywords	Demand prediction; Graph convolution; Spatiotemporal modeling; Street view

Similar Articles

Id	Similarity	Authors	Title	Published
38444	0.943	Wu M.; Zhu C.; Chen L.	Multi-Task Spatial-Temporal Graph Attention Network For Taxi Demand Prediction	ACM International Conference Proceeding Series (2020)
5524	0.935	Xue X.; Zhou C.; Zhang X.; Guo J.	A Taxi Demand Prediction Model Based On Spectral Domain Graph Convolution	Proceedings of SPIE - The International Society for Optical Engineering, 12613 (2023)
52523	0.916	Shu P.; Sun Y.; Zhao Y.; Xu G.	Spatial-Temporal Taxi Demand Prediction Using Lstm-Cnn	IEEE International Conference on Automation Science and Engineering, 2020-August (2020)
52828	0.904	Bhanu M.; Priya S.; Moreira J.M.; Chandra J.	St-Agp: Spatio-Temporal Aggregator Predictor Model For Multi-Step Taxi-Demand Prediction In Cities	Applied Intelligence, 53, 2 (2023)
34857	0.896	Elmi S.; Kian-Lee T.	Learned Taxi Fare For Real-Life Trip Trajectories Via Temporal Resnet Exploration	ACM International Conference Proceeding Series (2020)
54463	0.888	Askari B.; Le Quy T.; Ntoutsi E.	Taxi Demand Prediction Using An Lstm-Based Deep Sequence Model And Points Of Interest	Proceedings - 2020 IEEE 44th Annual Computers, Software, and Applications Conference, COMPSAC 2020 (2020)
60161	0.888	Wu Y.; Zhang H.; Li C.; Tao S.; Yang F.	Urban Ride-Hailing Demand Prediction With Multi-View Information Fusion Deep Learning Framework	Applied Intelligence, 53, 8 (2023)
4604	0.885	Wang T.; Li S.; Li W.; Yuan Q.; Chen J.; Tang X.	A Short-Term Parking Demand Prediction Framework Integrating Overall And Internal Information	Sustainability (Switzerland), 15, 9 (2023)
29828	0.884	Dai R.; Xu S.; Gu Q.; Ji C.; Liu K.	Hybrid Spatio-Temporal Graph Convolutional Network: Improving Traffic Prediction With Navigation Data	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2020)
33112	0.884	Du C.; Samonte M.J.C.	Internet Taxi Trip Prediction Based On Multi-Source Data Fusion	Advances in Transdisciplinary Engineering, 61 (2024)