DNN-based prediction model for spatio-temporal data

By Junbo Zhang, Yu Zheng, Dekang Qi, Ruiyuan Li, Xiuwen Yi. 2016

743 citations recorded by the source corpus.

Subfields: Building and Construction, Environmental Engineering, Transportation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Building and Construction

In Environmental Engineering

In Transportation

Citations in the corpus

A survey on data fusion in internet of things: Towards secure and privacy-preserving fusion (2019, background): “Crowd flows forecasting [42] SVM Efficient to deal with huge datasets, have the ability of handling high dimensional data Poor processing capacity for oversized data sets, sensitive to incomplete data.”
DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting (2022, methodology): “One type of classic methods is to cascade convolutional neural networks (CNN) and recurrent neural networks (RNN) to address the spatial-temporal dependencies in road network (Zhang et al., 2016; Li & Shahabi, 2018).”
Graph Neural Networks for Intelligent Transportation Systems: A Survey (2023, methodology): “They evaluated their framework using three real datasets and by comparing against HA, ordinary linear regression (OLR), XGBoost [52], DeepST [53], ResST-Net [54], DMVST-Net [55], ConvLSTM [56], FCL-Net [57], FlowFlexDP [58], DCRNN [6], and STGCN [27].”
Predicting Citywide Crowd Flows Using Deep Spatio-Temporal Residual Networks (2017, methodology): “We first briefly revisit the crowd flow prediction problem [3].”
Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction (2018, background): “Though previous studies (Zhang, Zheng, and Qi 2017; Zhang et al. 2016) consider periodicity, they fail to consider the sequential dependency and the temporal shifting in the periodicity.”
Memory in Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity From Spatiotemporal Dynamics (2018, methodology): “ entering and leaving the same district at this time. We generate sequences from TaxiBJ dataset and split the whole dataset into a training set and a test set as described in the work of Zhang et al. [37]. Each sequence contains 8 consecutive frames, 4 for the inputs and 4 for the predictions. The f”
Self-Attention ConvLSTM for Spatiotemporal Prediction (2020, methodology): “We follow the setup in previous works (Oliu et al. 2018; Zhang et al. 2016; Wang et al. 2017a; 2018b; 2019) to construct the training and testing sets.”
Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction (2018, background): “Zhang et al. (2016) and Zhang, Zheng, and Qi (2017) proposed to use residual CNN on the images of trafﬁc ﬂow.”
Traffic transformer: Capturing the continuity and periodicity of time series for traffic forecasting (2020, background): “Zhang, Zheng, Qi, Li, and Yi (2016) designed a deep learning model which takes into account both temporal aspects (temporal closeness, periods, and trends of crowd traffic) and spatial proximity.”
Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks (2017, background): “For a large-sized network with hundreds of links, capturing the spatial and temporal features of any link is very challenging [4,5].”
Deep Distributed Fusion Network for Air Quality Prediction (2018, methodology): “proposed a CNN-based network to extract features [13, 15, 16].”
Deep Learning for Spatio-Temporal Data Mining: A Survey (2019, methodology): “The spatial maps can be usually represented as image-like matrices, and thus are suitable to be processed with CNN models for predictive learning [62], [73], [172],”
Short-Term Load Forecasting With Deep Residual Networks (2018, background): “The selected inputs allow us to capture both short-term closeness and long-term trends in the load and temperature time series [24].”
Dynamic Spatial-Temporal Graph Convolutional Neural Networks for Traffic Forecasting (2019, background): “Some attempts have been made to apply deep Recurrent Neural Networks (RNN)(Wu and Tan 2016) and Convolution Neural Network (CNN) (Zhang et al. 2016; Zhang, Zheng, and Qi 2016; Ma et al. 2017) to predict traffic flow.”
Deep Learning on Traffic Prediction: Methods, Analysis, and Future Directions (2021, background): “[1] divided a city into I”
Spatial temporal incidence dynamic graph neural networks for traffic flow forecasting (2020, methodology): “• DeepST [38]: It is a deep neural network based prediction model, and models the spatial-temporal data as temporal closeness, period and seasonal trend.”
When Will You Arrive? Estimating Travel Time Based on Deep Neural Networks (2018, methodology): “(Zhang et al. 2016) used the 2D-CNN to predict the citywide crowd flow.”