1,632 Hits in 7.1 sec

Uncertainty Intervals for Graph-based Spatio-Temporal Traffic Prediction [article]

Tijs Maas, Peter Bloem
2020 arXiv   pre-print
Many traffic prediction applications rely on uncertainty estimates instead of the mean prediction.  ...  We propose Quantile Graph Wavenet, a Spatio-Temporal neural network that is trained to estimate a density given the measurements of previous timesteps, conditioned on a quantile.  ...  Graph WaveNet Graph WaveNet is neural network architecture for spatio-temporal traffic prediction.  ... 
arXiv:2012.05207v1 fatcat:qrfyoavhifchdi442whgy67bua

A Visual Analytics Approach for Traffic Flow Prediction Ensembles

Kezhi Kong, Yuxin Ma, Chentao Ye, Junhua Lu, Xiqun Chen, Wei Zhang, Wei Chen
2018 Pacific Conference on Computer Graphics and Applications  
In this paper, we propose a novel visual analytics approach for analyzing the predicted ensembles. Our approach models the uncertainty of different traffic flow prediction results.  ...  Traffic flow prediction plays a significant role in Intelligent Transportation Systems (ITS).  ...  In summary, the main contributions of our research are in the following three folds: 1) a novel scheme that uses spatio-temporal graph ensembles to analyze the uncertainty induced by traffic flow prediction  ... 
doi:10.2312/pg.20181281 dblp:conf/pg/KongMYLCZC18 fatcat:yhyjbafxzbhd3gyyuekr6d2vey

MFDGCN: Multi-Stage Spatio-Temporal Fusion Diffusion Graph Convolutional Network for Traffic Prediction

Zhengyan Cui, Junjun Zhang, Giseop Noh, Hyun Jun Park
2022 Applied Sciences  
Existing traffic prediction studies use distance-based graphs to represent spatial relationships, which ignores the deep connections between non-adjacent spatio-temporal information.  ...  This promotes the effective fusion of a spatio-temporal multimodal and uses the diffuse convolution method to model the graph structure and time series in traffic prediction, respectively.  ...  with deep spatio-temporal dependencies being easily ignored in road network traffic prediction based on simple distance maps and spatio-temporal fusion methods.  ... 
doi:10.3390/app12052688 fatcat:u2v25562ubhabbi54mtfrdwabm

Bayesian Graph Convolutional Network for Traffic Prediction [article]

Jun Fu, Wei Zhou, Zhibo Chen
2021 arXiv   pre-print
Recently, adaptive graph convolutional network based traffic prediction methods, learning a latent graph structure from traffic data via various attention-based mechanisms, have achieved impressive performance  ...  the presence of negative spatial relationships; and (3) lacking investigation on uncertainty of the graph structure.  ...  It introduces the information of traffic data and uncertainty into the graph structure using a Bayesian approach. Moreover, it is a plug-and-play module for graph-based traffic prediction networks.  ... 
arXiv:2104.00488v1 fatcat:cmpvycldpvagfdyqb3prfppjui

Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting

Bing Yu, Haoteng Yin, Zhanxing Zhu
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
In this paper, we propose a novel deep learning framework, Spatio-Temporal Graph Convolutional Networks (STGCN), to tackle the time series prediction problem in traffic domain.  ...  Timely accurate traffic forecast is crucial for urban traffic control and guidance.  ...  However, due to the uncertainty and complexity of traffic flow, those methods are less effective for relatively long-term predictions.  ... 
doi:10.24963/ijcai.2018/505 dblp:conf/ijcai/YuYZ18 fatcat:du2tmnse6bawxersbwhvi63am4

3D Graph Convolutional Networks with Temporal Graphs: A Spatial Information Free Framework For Traffic Forecasting [article]

Bing Yu, Mengzhang Li, Jiyong Zhang, Zhanxing Zhu
2019 arXiv   pre-print
Spatio-temporal prediction plays an important role in many application areas especially in traffic domain.  ...  However, due to complicated spatio-temporal dependency and high non-linear dynamics in road networks, traffic prediction task is still challenging.  ...  These prediction types are challenging due to the complexity of spatio-temporal dependencies and particularly the uncertainty of long-term forecasting.  ... 
arXiv:1903.00919v1 fatcat:277skdpx35erxkk4hamxxp4gmy

Deep Learning on Traffic Prediction: Methods, Analysis and Future Directions [article]

Xueyan Yin, Genze Wu, Jinze Wei, Yanming Shen, Heng Qi, Baocai Yin
2021 arXiv   pre-print
This problem is challenging due to the complicated and dynamic spatio-temporal dependencies between different regions in the road network.  ...  The purpose of this paper is to provide a comprehensive survey on deep learning-based approaches in traffic prediction from multiple perspectives.  ...  STSGCN [49] simultaneously extracted localized spatio-temporal correlation information based on the adjacency matrix of localized spatio-temporal graph.  ... 
arXiv:2004.08555v3 fatcat:ovhhumph2vbezpvc5m6qlk3udq

Traffic Flow Prediction Model Based on Spatio-Temporal Dilated Graph Convolution

2020 KSII Transactions on Internet and Information Systems  
Facing these challenges, a model of Spatio-Temporal Dilated Convolutional Network (STDGCN) is proposed for assistance of extracting highly nonlinear and complex characteristics to accurately predict the  ...  The proposed STDGCN integrates the dilated convolution into the graph convolution, which realizes the extraction of the spatial and temporal characteristics of traffic flow data, as well as features of  ...  based on time series prediction in traffic research; LSTM: Long Short-Term Memory Network, which is a more commonly used RNN model; STGCN: Spatio-Temporal Graph Convolutional Networks defines matrices  ... 
doi:10.3837/tiis.2020.09.002 fatcat:5r6wn247nvchthnokrelldhwfa

On Event Detection from Spatial Time Series for Urban Traffic Applications [chapter]

Gustavo Souto, Thomas Liebig
2016 Lecture Notes in Computer Science  
This article provides a survey on event processing in spatio-temporal data streams with a special focus on urban traffic. BibTeX:  ...  The "Big Data"based intelligent environments and smart cities require algorithms that process these massive amounts of spatio-temporal data.  ...  Recently, pattern-graphs were introduced in [27] , their pattern description is capable to express the temporal relations among various occurring events following the interval-calculus [2] .  ... 
doi:10.1007/978-3-319-41706-6_11 fatcat:jk3ogwpvpjesxab3uk5ick7f5q

T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction [article]

Ling Zhao, Yujiao Song, Chao Zhang, Yu Liu, Pu Wang, Tao Lin, Min Deng, Haifeng Li
2018 arXiv   pre-print
Experiments demonstrate that our T-GCN model can obtain the spatio-temporal correlation from traffic data and the predictions outperform state-of-art baselines on real-world traffic datasets.  ...  To capture the spatial and temporal dependence simultaneously, we propose a novel neural network-based traffic forecasting method, the temporal graph convolutional network (T-GCN) model, which is in combination  ...  Temporal Graph Convolutional Network To capture the spatial and temporal dependences from traffic data at the same time, we propose a temporal graph convolutional network model (T-GCN) based on a graph  ... 
arXiv:1811.05320v3 fatcat:2ih3hng7uzahxfmlxdplhtj3gu

Identifying Hidden Influences of Traffic Incidents' effect in Smart Cities

Attila Nagy, Vilmos Simon
2018 Proceedings of the 2018 Federated Conference on Computer Science and Information Systems  
This novel analysis can give a significant insight to improve the operation of currently widespread traffic prediction algorithms.  ...  To reveal these relationships, we are investigating unexpected events such as traffic jams or accidents.  ...  Deep learning based prediction model was also presented for spatio-temporal data [17] .  ... 
doi:10.15439/2018f194 dblp:conf/fedcsis/NagyS18 fatcat:labiuq5f7rfrbldqbgrbpnywzi

Spatio-Temporal Stream Processing [chapter]

Rodney Topor, Kenneth Salem, Amarnath Gupta, Kazuo Goda, Johannes Gehrke, Nathaniel Palmer, Mohamed Sharaf, Alexandros Labrinidis, John F. Roddick, Ariel Fuxman, Renée J. Miller, Wang-Chiew Tan (+205 others)
2009 Encyclopedia of Database Systems  
We propose an unsupervised stream processing framework that learns a Bayesian representation of observed spatio-temporal activities and their causal relations.  ...  This allows the model to be efficient through compactness and sparsity in the causal graph, and to provide probabilities at any level of abstraction for activities or chains of activities.  ...  Gaussian Processes Gaussian Processes have been shown to be useful for prediction, modeling and detecting spatio-temporal trajectories such as motor vehicles in crossings [8] , marine vessel paths [12  ... 
doi:10.1007/978-0-387-39940-9_3665 fatcat:mivvr7iy6jgmrmjmijhmppougq

HiSTGNN: Hierarchical Spatio-temporal Graph Neural Networks for Weather Forecasting [article]

Minbo Ma, Peng Xie, Fei Teng, Tianrui Li, Bin Wang, Shenggong Ji, Junbo Zhang
2022 arXiv   pre-print
Recently, the Graph Neural Networks (GNNs) based methods have achieved excellent performance for spatio-temporal forecasting.  ...  In this paper, we propose a novel Hierarchical Spatio-Temporal Graph Neural Network (HiSTGNN) to model cross-regional spatio-temporal correlations among meteorological variables in multiple stations.  ...  Spatio-temporal Graph Neural Networks Recently, many studies focus on applying spatio-temporal graph neural networks in spatio-temporal forecasting tasks like traffic prediction [13] , taxi demand prediction  ... 
arXiv:2201.09101v1 fatcat:2x3synujnvfmrhdvctqdsviay4

STGAT: Spatial-Temporal Graph Attention Networks for Traffic Flow Forecasting

Xiangyuan Kong, Weiwei Xing, Xiang Wei, Peng Bao, Jian Zhang, Wei Lu
2020 IEEE Access  
In this paper, we propose an end-to-end deep learning based dual path framework, i.e., Spatial-Temporal Graph Attention Network (STGAT), for traffic flow forecasting.  ...  INDEX TERMS Traffic flow forecasting, spatial-temporal graph neural networks, intelligent transportation systems.  ...  OGCRNN (optimized graph convolution recurrent neural network) [32] is a RNN based approach for traffic prediction.  ... 
doi:10.1109/access.2020.3011186 fatcat:kta4b7vy5jd6he5jtdqenyciea

Gated Residual Recurrent Graph Neural Networks for Traffic Prediction

Cen Chen, Kenli Li, Sin G. Teo, Xiaofeng Zou, Kang Wang, Jie Wang, Zeng Zeng
The factors make traffic prediction a challenging task due to the uncertainty and complexity of traffic states.  ...  Based on Res-RGNN and hop Res-RGNN, we finally propose a novel end-to-end multiple Res-RGNNs framework, referred to as "MRes-RGNN", for traffic prediction.  ...  In the following, we shall present the key definitions that are used for directed graph based traffic prediction.  ... 
doi:10.1609/aaai.v33i01.3301485 fatcat:wvazfis5arcvhm3dwdwadftari
« Previous Showing results 1 — 15 out of 1,632 results