Filters








236 Hits in 9.8 sec

Deep learning for intelligent traffic sensing and prediction: recent advances and future challenges

Xiaochen Fan, Chaocan Xiang, Liangyi Gong, Xin He, Yuben Qu, Saeed Amirgholipour, Yue Xi, Priyadarsi Nanda, Xiangjian He
2020 CCF Transactions on Pervasive Computing and Interaction  
In this paper, we present an up-to-date literature review on the most advanced research works in deep learning for intelligent traffic sensing and prediction.  ...  With the emerging concepts of smart cities and intelligent transportation systems, accurate traffic sensing and prediction have become critically important to support urban management and traffic control  ...  They further proposed a dynamic spatio-temporal graph convolutional neural network for traffic forecasting.  ... 
doi:10.1007/s42486-020-00039-x fatcat:c3c2b3fvpzdqdlxy2ke7ckxlpu

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:2201.09101v2 fatcat:x7b6o4crijdsxepahlt3oqb2be

Scale-Aware Neural Architecture Search for Multivariate Time Series Forecasting [article]

Donghui Chen, Ling Chen, Zongjiang Shang, Youdong Zhang, Bo Wen, Chenghu Yang
2021 arXiv   pre-print
A multi-scale decomposition module transforms raw time series into multi-scale sub-series, which can preserve multi-scale temporal patterns.  ...  In this paper, we propose a scale-aware neural architecture search framework for MTS forecasting (SNAS4MTF).  ...  and edges using bi-component graph convolution. • AutoSTG [20] : A spatio-temporal graph forecasting method, which integrates neural architecture search to capture complex spatio-temporal correlations  ... 
arXiv:2112.07459v1 fatcat:igbp4gubw5hblf6vthwslmx7ou

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.  ...  ST-GCN [38] is another deep learning framework for traffic prediction, integrating graph convolution and gated temporal convolution through spatio-temporal convolutional blocks.  ... 
arXiv:2103.07719v1 fatcat:ysqgbsalfjehpojx22d2ae77gm

Community-Aware Multi-Task Transportation Demand Prediction

Hao Liu, Qiyu Wu, Fuzhen Zhuang, Xinjiang Lu, Dejing Dou, Hui Xiong
2021 AAAI Conference on Artificial Intelligence  
To this end, in this paper, we propose the Multi-task Spatio-Temporal Network with Mutually-supervised Adaptive task grouping (Ada-MSTNet) for community-aware transportation demand prediction.  ...  Specifically, we first construct a sequence of multi-view graphs from both spatial and community perspectives, and devise a spatio-temporal neural network to simultaneously capture the sophisticated correlations  ...  After that, we devised a spatio-temporal network for simultaneous spatio-temporal and community correlation modeling.  ... 
dblp:conf/aaai/LiuWZLD021 fatcat:zyfrzuoztnafxpbyidkozdz6iq

Generative Adversarial Networks for Spatio-temporal Data: A Survey [article]

Nan Gao, Hao Xue, Wei Shao, Sichen Zhao, Kyle Kai Qin, Arian Prabowo, Mohammad Saiedur Rahaman, Flora D. Salim
2021 arXiv   pre-print
Recently, GAN-based techniques are shown to be promising for spatio-temporal-based applications such as trajectory prediction, events generation and time-series data imputation.  ...  We summarise the application of popular GAN architectures for spatio-temporal data and the common practices for evaluating the performance of spatio-temporal applications with GANs.  ...  For instance, Yu et al. introduced Spatio-Temporal Graph Convolutional Networks (STGCN) [166] to solve the prediction problem in traffic networks.  ... 
arXiv:2008.08903v3 fatcat:pbhxbfgw65bodksjdmwazwo4dq

Space Meets Time: Local Spacetime Neural Network For Traffic Flow Forecasting [article]

Song Yang, Jiamou Liu, Kaiqi Zhao
2022 arXiv   pre-print
Based on this idea, we introduce local spacetime neural network (STNN), which employs novel spacetime convolution and attention mechanism to learn the universal spatio-temporal correlations.  ...  The challenge arises as traffic flows often exhibit intrinsic and latent spatio-temporal correlations that cannot be identified by extracting the spatial and temporal patterns of traffic data separately  ...  multi-attention network equipped with spatial, temporal and transform attention. • MTGCN [26] : Multivariate time series forecasting with graph neural networks. 4) Experiment Settings: We implemented  ... 
arXiv:2109.05225v2 fatcat:q7njhzvbxzd4be5z24tawygsxy

STAGCN: Spatial–Temporal Attention Graph Convolution Network for Traffic Forecasting

Yafeng Gu, Li Deng
2022 Mathematics  
Meanwhile, most recurrent neural networks (RNNs) or convolutional neural networks (CNNs) cannot effectively capture temporal correlations, especially for long-term temporal dependencies.  ...  In this paper, we propose a spatial–temporal attention graph convolution network (STAGCN), which acquires a static graph and a dynamic graph from data without any prior knowledge.  ...  with fully connected LSTM hidden units [32] . • DCRNN: Diffusion convolutional recurrent neural network [12] , which integrates diffusion graph convolution into gated recurrent units. • STGCN: Spatio-temporal  ... 
doi:10.3390/math10091599 fatcat:5pkibiw3c5f6xmnr3azcotgmim

Uncertainty Quantification for Traffic Forecasting: A Unified Approach [article]

Weizhu Qian, Dalin Zhang, Yan Zhao, Kai Zheng, James J.Q. Yu
2022 arXiv   pre-print
We first leverage a spatio-temporal model to model the complex spatio-temporal correlations of traffic data.  ...  Uncertainty is an essential consideration for time series forecasting tasks. In this work, we specifically focus on quantifying the uncertainty of traffic forecasting.  ...  spatio-temporal correlations.  ... 
arXiv:2208.05875v1 fatcat:zdqfxmlx5bffjfvlg7s7nu2b5q

MARRS: A Framework for multi-objective risk-aware route recommendation using Multitask-Transformer

Bhumika, Debasis Das
2022 Sixteenth ACM Conference on Recommender Systems  
We introduce a wide, deep, and multitask-learning (WD-MTL) framework that uses a transformer to extract spatial, temporal, and semantic correlation for predicting crime, accident, and traffic flow of particular  ...  This paper introduces a novel framework, namely MARRS, a multi-objective route recommendation system based on heterogeneous urban sensing open data (i.e., crime, accident, traffic flow, road network, meteorological  ...  The spatio-temporal features are then fed into a WD-MTL model for predicting accident, crime, and traffic risks using WD-MTL architecture.  ... 
doi:10.1145/3523227.3546787 fatcat:wcjnmatusjaolcmfeyz3nvzyam

Towards Spatio-Temporal Aware Traffic Time Series Forecasting–Full Version [article]

Razvan-Gabriel Cirstea, Bin Yang, Chenjuan Guo, Tung Kieu, Shirui Pan
2022 arXiv   pre-print
across time, where, for example, there exist certain periods across a day showing stronger temporal correlations.  ...  Traffic time series forecasting is challenging due to complex spatio-temporal dynamics time series from different locations often have distinct patterns; and for the same time series, patterns may vary  ...  . • DCRNN [17] employs GRU to model temporal dependencies (TD) and diffusion graph convolution to model sensor correlations (SC). • STGCN [29] uses 2D convolution to model TD and graph convolution  ... 
arXiv:2203.15737v3 fatcat:wm3akyt3hnf6zcovpu4q6uim2i

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

Haitao Yuan, Guoliang Li
2021 Data Science and Engineering  
In this paper, we provide a comprehensive survey on traffic prediction, which is from the spatio-temporal data layer to the intelligent transportation application layer.  ...  At first, we split the whole research scope into four parts from bottom to up, where the four parts are, respectively, spatio-temporal data, preprocessing, traffic prediction and traffic application.  ...  To predict for multivariate traffic flows, Yan et al.  ... 
doi:10.1007/s41019-020-00151-z fatcat:nnnnxnpo3bgk3l4hpr7kk2n4xa

CATN: Cross Attentive Tree-Aware Network for Multivariate Time Series Forecasting

Hui He, Qi Zhang, Simeng Bai, Kun Yi, Zhendong Niu
2022 AAAI Conference on Artificial Intelligence  
Hence, we present CATN, an end-to-end model of Cross Attentive Tree-aware Network to jointly capture the interseries correlation and intra-series temporal patterns.  ...  Modeling complex hierarchical and grouped feature interaction in the multivariate time series data is indispensable to comprehending the data dynamics and predicting the future condition.  ...  Graph neural networks (GNNs) have obtained great achievements in multivariate time series forecasting viewed from a graph perspective to capture inter-series correlation.  ... 
dblp:conf/aaai/HeZBYN22 fatcat:uli3qqyopjenfborrx3zhds5c4

A Survey on Societal Event Forecasting with Deep Learning [article]

Songgaojun Deng, Yue Ning
2021 arXiv   pre-print
This paper is dedicated to providing a systematic and comprehensive overview of deep learning technologies for societal event predictions.  ...  We first introduce how event forecasting problems are formulated as a machine learning prediction task.  ...  [63] developed an imbalance-aware hyper-ensemble for spatio-temporal crime prediction, focusing on low population density areas. Yi et al.  ... 
arXiv:2112.06345v1 fatcat:jtdlo67bbbazhj6xea55h6bbqa

2020 Index IEEE Transactions on Intelligent Transportation Systems Vol. 21

2020 IEEE transactions on intelligent transportation systems (Print)  
., +, TITS Jan. 2020 285-297 T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction.  ...  ., +, TITS July 2020 3046-3055 T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction.  ... 
doi:10.1109/tits.2020.3048827 fatcat:ab6he3jkfjboxg7wa6pagbggs4
« Previous Showing results 1 — 15 out of 236 results