LSTM network: a deep learning approach for short-term traffic forecast

By Zheng Zhao, Weihai Chen, Xingming Wu, Peter C. Y. Chen, Jingmeng Liu. 2017

1,716 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/eb8b18fa6a2c42b2c33395633508609e4ec9dcc5

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

1. Yinhai Wang
2. Zhiyong Cui
3. Ruimin Ke
4. Philip S. Yu
5. Senzhang Wang
6. Yunpeng Wang
7. Xiaolei Ma
8. Shengna Guo

In Control and Systems Engineering

1. Yinhai Wang
2. Zhiyong Cui
3. Ruimin Ke
4. Zhifeng Bao
5. A. K. Qin
6. Farhana Murtaza Choudhury
7. Baihua Zheng
8. David Alexander Tedjopurnomo

In Transportation

1. Philip S. Yu
2. Senzhang Wang
3. Yunpeng Wang
4. Shengna Guo
5. Youfang Lin
6. Huaiyu Wan
7. Xiaolei Ma
8. Yinhai Wang

Citations in the corpus

• Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction (2018, neutral): “Several studies [2, 22-25, 34, 43, 44, 45] have been done to examine the applicability of LSTMs in traffic forecasting, and the results demonstrate the advantages of LSTMs.”
• Short-Term Forecasting of Passenger Demand under On-Demand Ride Services: A Spatio-Temporal Deep Learning Approach (2017, background): “To address temporal correlations (another inherit property in real-time traffic forecasting), the family of recurrent neural networks (RNN) (Williams and Zipser, 1989) was widely viewed as one of the most suitable structures (Zhao et al., 2017).”
• TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting (2024, methodology): “And RNN-based methods adopt the recurrent structure to model the temporal state transition (Lai et al., 2018; Zhao et al., 2017).”
• Spatial temporal incidence dynamic graph neural networks for traffic flow forecasting (2020, methodology): “Different from previous deep learning based models [4, 21, 18, 14], they either take external influences such as holidays, weekends, events, etc.”
• Deep Spatial–Temporal 3D Convolutional Neural Networks for Traffic Data Forecasting (2019, background): “Ma et al. [2] and Zhao et al. [24] employed LSTM-based networks to predict short-term traffic speed and traffic flow.”
• Online Incremental Machine Learning Platform for Big Data-Driven Smart Traffic Management (2019, background): “This has been recently attempted in [32], where correlations of the traffic flow of targeted road segment and that of its upstream and downstream road segments are considered for the prediction.”
• Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather station (2020, background): “There are several evaluation metrics which can be used to calculate the loss in a neural network such as but not limited to mean squared error (MSE), mean absolute error (MAE), root mean squared error (RMSE), quadratic cost, cross-entry cost, exponential cost, Hellinger distance, and Kullback–Leible”
• A Survey on Modern Deep Neural Network for Traffic Prediction: Trends, Methods and Challenges (2020, methodology): “These datasets usually cover the Ring Road area, as can be seen in the works [45], [46], [47], [48] and [49].”
• Prediction of epidemic trends in COVID-19 with logistic model and machine learning technics (2020, neutral): “[19] Zhao Z, Chen W, Wu X, Chen PCY, Liu J.”
• iTransformer: Inverted Transformers Are Effective for Time Series Forecasting (2023, background): “Going beyond contemporaneous TCNs (Bai et al., 2018; Liu et al., 2022a) and RNN-based forecasters (Zhao et al., 2017; Rangapuram et al., 2018; Salinas et al., 2020), Transformer has exhibited powerful sequence modeling capability and promising model scalability, leading to the trend of passionate…”
• Holistic Network Virtualization and Pervasive Network Intelligence for 6G (2023, background): “…to identify the correlation of multi-dimensional input data and have been applied in modulation classification [112]; recurrent neural networks (RNNs) explore the correlation among a sequence of the data and have been widely adopted for traffic prediction [113] and wireless channel modeling [133].”
• Stacked Bidirectional and Unidirectional LSTM Recurrent Neural Network for Forecasting Network-wide Traffic State with Missing Values (2020, methodology): “Most of the newly proposed traffic forecasting models Ma et al. (2015); Duan et al. (2016); Chen et al. (2016); Zhao et al. (2017); Wu and Tan (2016); Song et al. (2016); Yu et al. (2017a) are based on recurrent neural networks (RNNs), which mainly process sequence data by maintaining a chain-like…”