Traffic Flow Prediction With Big Data: A Deep Learning Approach

By Yisheng Lv, Yanjie Duan, Wenwen Kang, ZhengXi Li, Feiyue Wang. IEEE transactions on intelligent transportation systems (Print), 2015

2,921 citations recorded by the source corpus.

Subfields: Building and Construction, Control and Systems Engineering, Transportation

View Paper: https://www.semanticscholar.org/paper/94deb62af3054c49e7d80bd7eb3ed5efe990fc0b

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 Control and Systems Engineering

In Transportation

Citations in the corpus

Multi-period Time Series Modeling with Sparsity via Bayesian Variational Inference (2017, methodology): “Another method for time series forecasting can be found in [8], which uses Stacked Autoencoders (SAE) to”
Deep Learning for Spatio-Temporal Data Mining: A Survey (2019, methodology): “for road-level traffic prediction [104], [136], [191].”
Road Traffic Forecasting: Recent Advances and New Challenges (2018, background): “Prediction Horizon Prediction horizon [1], [7], [10], [11], [13], [25], [29], [30]”
Deep Learning Based Forecasting of Critical Infrastructure Data (2017, methodology): “For instance, in [36] a stacked denoising autoencoder is used to predict the indoor temperature and in [29, 31] stacked autoencoders have been used to predict the flow of traffic and weather conditions.”
A Survey on Mobile Crowdsensing Systems: Challenges, Solutions, and Opportunities (2019, background): “In intelligent transportation systems, deep learning techniques can be used to analyze spatio-temporal correlations to predict traffic flows and improve travel times [312], and to prevent pedestrian”
Big Data Analytics in Intelligent Transportation Systems: A Survey (2019, background): “[85] propose a novel deep-learning- based traffic prediction model that considered spatiotemporal relations, and employed stack autoencoder (SAE) to extract traffic features.”
Big Data Analytics in Operations Management (2018, background): “In the literature, Lv et al. (2015) employ a deep learning approach to study trafﬁc ﬂow predictions with big trafﬁc ﬂow data.”
Short-Term Forecasting of Passenger Demand under On-Demand Ride Services: A Spatio-Temporal Deep Learning Approach (2017, background): “Lv et al. (2015) stated that a stacked autoencoder model helped to capture generic traffic flow features and characterize spatial temporal correlations in traffic flow prediction.”
Dynamic and Multi-faceted Spatio-temporal Deep Learning for Traffic Speed Forecasting (2021, background): “Traffic forecasting has attracted much attention of enormous researchers in the past decades [21].”
Privacy-Preserving Traffic Flow Prediction: A Federated Learning Approach (2020, methodology): “[1] first applied the stacked autoencoder (SAE) model to TFP.”
Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction (2017, methodology): “Second, the depth of CNN should be neither too large nor too small [39] and, thus, CNN is capable of learning much more complex relations while maintaining the convergence of the model.”
Time Series Forecasting Based on Augmented Long Short-Term Memory (2017, positive): “Deep belief networks (DBN) are frequently employed in current short-term traffic forecasting [7] [8], and pre-training strategies with unsupervised learning algorithms such as Restricted Boltzmann machine (RBM) [9] and Stacked AutoEncoder (SAE) [11] are also used.”
Using Deep Learning-Based Approach to Predict Remaining Useful Life of Rotating Components (2018, background): “These domains include predicting car traffic [25], weather [26], wind”