553 Hits in 7.6 sec

SOUP: Spatial-Temporal Demand Forecasting and Competitive Supply [article]

Bolong Zheng, Qi Hu, Lingfeng Ming, Jilin Hu, Lu Chen, Kai Zheng, Christian S. Jensen
2021 arXiv   pre-print
In this paper, we study the problem of spatial-temporal demand forecasting and competitive supply (SOUP). We address the problem in two steps.  ...  Specifically, we propose a Spatial-Temporal Graph Convolutional Sequential Learning (ST-GCSL) algorithm that predicts the service requests across locations and time slots.  ...  CONCLUSION We study the problem of spatial-temporal demand forecasting and competitive supply (SOUP).  ... 
arXiv:2009.12157v2 fatcat:rzo7c3xczzayldentads4yrlvq

Multi-Graph Convolutional-Recurrent Neural Network (MGC-RNN) for Short-Term Forecasting of Transit Passenger Flow [article]

Yuxin He, Lishuai Li, Xinting Zhu, Kwok Leung Tsui
2021 arXiv   pre-print
The temporal dynamics of the inter-station correlations are also modeled via the proposed multi-graph convolutional-recurrent neural network structure.  ...  We propose to use multiple graphs to encode the spatial and other heterogenous inter-station correlations.  ...  Lv et al. (2020) proposed a Temporal Multi-Graph Convolutional Network (T-MGCN) to jointly model the spatial, temporal, semantic correlations for traffic flow prediction [12] .  ... 
arXiv:2107.13226v1 fatcat:isi7xdhkvjhozcfgnnwuxdz4ee

FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic Forecasting [article]

Boris N. Oreshkin, Arezou Amini, Lucy Coyle, Mark J. Coates
2020 arXiv   pre-print
Forecasting of multivariate time-series is an important problem that has applications in traffic management, cellular network configuration, and quantitative finance.  ...  In this paper we propose a novel learning architecture that achieves performance competitive with or better than the best existing algorithms, without requiring knowledge of the graph.  ...  Graph Convolutional Network, merges graph convolutions with gated temporal convolutions); Graph WaveNet [41] , fuses graph convolution and dilated causal convolution; and GMAN [48] (Graph Multi-Attention  ... 
arXiv:2007.15531v2 fatcat:erqvvmdpqvektecabgcsc5htua

ADST: Forecasting Metro Flow using Attention-Based Deep Spatial-Temporal Networks with Multi-Task Learning

Hongwei Jia, Haiyong Luo, Hao Wang, Fang Zhao, Qixue Ke, Mingyao Wu, Yunyun Zhao
2020 Sensors  
Although both the spatial and temporal perspectives have been considered in modeling, most existing works have ignored complex temporal correlations or underlying spatial similarity.  ...  Specifically, each channel uses the framework of residual networks, the rectified block and the multi-scale convolutions to mine spatiotemporal correlations.  ...  Acknowledgments: Our sincere thankfulness be tendered to all the reviewers for their valuable comments and helpful suggestions. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s20164574 pmid:32824074 pmcid:PMC7472615 fatcat:ynrvnnerabby5hpnqrcqesv4qa

On the Inclusion of Spatial Information for Spatio-Temporal Neural Networks [article]

Rodrigo de Medrano, José L. Aznarte
2020 arXiv   pre-print
When confronting a spatio-temporal regression, it is sensible to feed the model with any available prior information about the spatial dimension.  ...  For example, it is common to define the architecture of neural networks based on spatial closeness, adjacency, or correlation.  ...  (from now on, just closeness) and use CNNs. • Define the system in a graph structure and model it via graph convolutional networks (GCN).  ... 
arXiv:2007.07559v2 fatcat:kvoa5xzyjzdxrfrnksiffy5lxe

Short-Term Prediction of Demand for Ride-Hailing Services: A Deep Learning Approach

Long Chen, Piyushimita Vonu Thakuriah, Konstantinos Ampountolas
2021 Journal of Big Data Analytics in Transportation  
This paper proposes UberNet, a deep learning convolutional neural network for short-time prediction of demand for ride-hailing services.  ...  UberNet employs a multivariate framework that utilises a number of temporal and spatial features that have been found in the literature to explain demand for ride-hailing services.  ...  as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.  ... 
doi:10.1007/s42421-021-00041-4 fatcat:s3kjmtekmfbaldbkqpidcu7s3i

Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting [article]

Defu Cao, Yujing Wang, Juanyong Duan, Ce Zhang, Xia Zhu, Conguri Huang, Yunhai Tong, Bixiong Xu, Jing Bai, Jie Tong, Qi Zhang
2021 arXiv   pre-print
In this paper, we propose Spectral Temporal Graph Neural Network (StemGNN) to further improve the accuracy of multivariate time-series forecasting.  ...  After passing through GFT and DFT, the spectral representations hold clear patterns and can be predicted effectively by convolution and sequential learning modules.  ...  For instance, DCRNN [20] incorporates both spatial and temporal dependencies in the convolutional recurrent neural network for traffic forecasting.  ... 
arXiv:2103.07719v1 fatcat:ysqgbsalfjehpojx22d2ae77gm

Neural forecasting: Introduction and literature overview [article]

Konstantinos Benidis, Syama Sundar Rangapuram, Valentin Flunkert, Bernie Wang, Danielle Maddix, Caner Turkmen, Jan Gasthaus, Michael Bohlke-Schneider, David Salinas, Lorenzo Stella, Laurent Callot, Tim Januschowski
2020 arXiv   pre-print
As the prevalence of neural network based solutions among the best entries in the recent M4 competition shows, the recent popularity of neural forecasting methods is not limited to industry and has also  ...  Building on these foundations, the article then gives an overview of the recent literature on neural networks for forecasting and applications.  ...  Neural forecasting methods can be interesting in this context as they permit the combination of spatial and temporal information when available [126] as one can typically combine convolution in the spatial  ... 
arXiv:2004.10240v1 fatcat:i3nbsw5sojckdee5d4magpwsl4

Guest Editorial: Special Issue on Communications and Data Analytics in the Smart Grid

Ying-Jun Angela Zhang, Hans-Peter Schwefel, Hamed Mohsenian-Rad, Christian Wietfeld, Chen Chen, Hamid Gharavi
2020 IEEE Journal on Selected Areas in Communications  
quality, and variety of data that utilities and grid operators are collecting on supply, transmission, distribution, and demand.  ...  Given the wide choice of communication and network technologies, intensive research efforts are needed to compare options and optimize solutions for Smart Grids.  ...  Cyber Security and Resilience for the Smart Grids The paper "Fault Location in Power Distribution Systems via Deep Graph Convolutional Networks" develops a new graph convolutional network (GCN) framework  ... 
pmid:33029039 pmcid:PMC7537467 fatcat:vgblruonejb65ewidldzjracnq

Learning to Optimize Industry-Scale Dynamic Pickup and Delivery Problems [article]

Xijun Li, Weilin Luo, Mingxuan Yuan, Jun Wang, Jiawen Lu, Jie Wang, Jinhu Lu, Jia Zeng
2021 arXiv   pre-print
In our method, the delivery demands are first forecast using spatial-temporal prediction method, which guides the neural network to perceive spatial-temporal distribution of delivery demand when dispatching  ...  In this paper, we propose a data-driven approach, Spatial-Temporal Aided Double Deep Graph Network (ST-DDGN), to solve industry-scale DPDP.  ...  This work was supported in part by the Fundamental Research Funds for the Central Universities (WK3490000004) and Natural Science Foundation of China (61822604, 61836006, U19B2026).  ... 
arXiv:2105.12899v1 fatcat:4a44smz4anfh7iijvi55ccj5ya

A Multi-view Multi-task Learning Framework for Multi-variate Time Series Forecasting [article]

Jinliang Deng, Xiusi Chen, Renhe Jiang, Xuan Song, Ivor W. Tsang
2021 arXiv   pre-print
Therefore, there are two fundamental views which can be used to analyze MTS data, namely the spatial view and the temporal view.  ...  Applying these two operations with prior knowledge on the spatial and temporal view allows the model to adaptively extract MVMT information while predicting.  ...  Common neural architectures applied on time series data include recurrent neural networks (RNNs), longshort term memory (LSTM) [7] , Transformer [8] , Wavenet [9] and temporal convolution networks  ... 
arXiv:2109.01657v1 fatcat:tpsl5jf4l5bfnbtvpj4sh2aukm

A Continuous Taxi Pickup Path Recommendation under The Carbon Neutrality Context

Mengmeng Chang, Yuanying Chi, Zhiming Ding, Jing Tian, Yuhao Zheng
2021 ISPRS International Journal of Geo-Information  
As a result, the continuous pickup path balanced the relation between travel demands and taxi supply, improving the economic and environmental benefits of taxi operation and contributing to the goal of  ...  First, an adaptive learning spatiotemporal neural network was used to predict the coarse-grained distribution of potential trips.  ...  Origin-destination matrix prediction via graph convolution: A new perspective of passenger demand modeling.  ... 
doi:10.3390/ijgi10120821 fatcat:h2f3yabouveuzdckbfxu6u3nwy

Feature selection and extraction in spatiotemporal traffic forecasting: a systematic literature review

Dmitry Pavlyuk
2019 European Transport Research Review  
A spatiotemporal approach that simultaneously utilises both spatial and temporal relationships is gaining scientific interest in the field of traffic flow forecasting.  ...  This paper systematically reviews studies that apply feature selection and extraction methods for spatiotemporal traffic forecasting.  ...  The introduced network weight matrix utilises graph characteristics of the road network such as betweenness centrality and vulnerability to discover complementary and competitive spatial links.  ... 
doi:10.1186/s12544-019-0345-9 fatcat:dkbgkt7o2natxh5s5t5nfwcq5m

A Survey of Traffic Prediction: from Spatio-Temporal Data to Intelligent Transportation

Haitao Yuan, Guoliang Li
2021 Data Science and Engineering  
First, we summarize traffic data into five types according to their difference on spatial and temporal dimensions.  ...  ., classification, generation and estimation/forecasting). In particular, we summarize the challenges and discuss how existing methods address these challenges.  ...  [140] apply the MLP model and the residual network architecture to forecast both travel supply and travel demand.  ... 
doi:10.1007/s41019-020-00151-z fatcat:nnnnxnpo3bgk3l4hpr7kk2n4xa

PSML: A Multi-scale Time-series Dataset for Machine Learning in Decarbonized Energy Grids [article]

Xiangtian Zheng, Nan Xu, Loc Trinh, Dongqi Wu, Tong Huang, S. Sivaranjani, Yan Liu, Le Xie
2021 arXiv   pre-print
load, renewable generation, weather, voltage and current measurements at multiple spatio-temporal scales.  ...  events; (ii) robust hierarchical forecasting of load and renewable energy with the presence of uncertainties and extreme events; and (iii) realistic synthetic generation of physical-law-constrained measurement  ...  networks with both spatial and temporal dependencies: event localization is a great challenge when only temporal dependencies are modeled in deep learning approaches.  ... 
arXiv:2110.06324v1 fatcat:quumrkzw6fhmhgdpcwwjrber5q
« Previous Showing results 1 — 15 out of 553 results