Using LSTM and GRU neural network methods for traffic flow prediction

By Rui Fu, Zuo Zhang, Li Li. Youth Academic Annual Conference of Chinese Association of Automation, 2016

1,297 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/3df05017006ae30d9414ebf08b2bd7211451e3e8

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. Yunpeng Wang
5. Xiaolei Ma
6. Zhong Fan
7. Ling Zhao
8. Bernardo Pérez Orozco

In Control and Systems Engineering

1. Yinhai Wang
2. Zhiyong Cui
3. Ruimin Ke
4. Zhong Fan
5. Bernardo Pérez Orozco
6. Stephen J. Roberts
7. Henry Leung
8. Tao Lin

In Transportation

1. Yunpeng Wang
2. Xiaolei Ma
3. Yinhai Wang
4. Zhong Fan
5. Ling Zhao
6. Bernardo Pérez Orozco
7. Stephen J. Roberts
8. Zhiyong Cui

Citations in the corpus

• Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction (2018, background): “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.”
• Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks (2017, result): “Fu [39]); the results indicate that LSTMs outperform MLP and SVMs.”
• Anomaly Detection for IoT Time-Series Data: A Survey (2020, methodology): “With the development of RNNs [66], [67] such as LSTM and GRU the ability for the neural network approach to better model the variability present in complex univariate systems has been demonstrated in [68].”
• A Review of Deep Learning Models for Time Series Prediction (2019, background): “Thus, LSTM can maintain temporal information in the state for a long number of timesteps and is widely used in sequential data analysis, prediction and classification tasks [85]–[88] in univariate and multivariate [89], [90] domains.”
• T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction (2018, methodology): “In addition, since the recurrent neural network (RNN) and its variants have long short-term memory (LSTM) and the gated recurrent unit (GRU) can effectively use the self-circulation mechanism, they can learn temporal dependence well and achieve better prediction results [13], [41].”
• A3T-GCN: Attention Temporal Graph Convolutional Network for Traffic Forecasting (2020, background): “Recurrent neural networks (RNNs), long short-term memory (LSTM) [13], and gated recurrent units (GRUs)[7] have been successfully utilized in traffic forecasting because they can use self-circulation mechanism and model temporal dependence [20, 25].”
• MOrdReD: Memory-based Ordinal Regression Deep Neural Networks for Time Series Forecasting (2018, methodology): “…recurrent models with a greater numbers of units have now been successfully used in several application domains, such as traffic flow prediction [22, 23], precipitation nowcasting [24], chaotic dynamical systems [25, 26], electricity market price [27], financial market predictions [28] and energy…”
• Privacy-Preserving Traffic Flow Prediction: A Federated Learning Approach (2020, methodology): “[22] first proposed GRU neural network methods for TFP.”