A hybrid deep learning based traffic flow prediction method and its understanding

By Yuankai Wu, Huachun Tan, Lingqiao Qin, Bin Ran, Zhuxi Jiang. 2018

698 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/5dc29514e7926c0cfa19b5b3a7d98ecfc9df542f

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

In Control and Systems Engineering

1. Zhiyong Cui
2. Ruimin Ke
3. Rui Zhao
4. Kristian C. Henrickson
5. Ruqiang Yan
6. Zhifeng Bao
7. A. K. Qin
8. Farhana Murtaza Choudhury

In Transportation

1. Chao Ning
2. Zhiyong Cui
3. A. K. Qin
4. Jiayun Luo
5. Weiwei Jiang
6. Krzysztof Janowicz
7. Farhana Murtaza Choudhury
8. Fengqi You

Citations in the corpus

• A Survey on Modern Deep Neural Network for Traffic Prediction: Trends, Methods and Challenges (2020, methodology): “[66] used a Gated Recurrent Unit to learn feature representation from an attention model which are then fused with the CNN spatial component.”
• Optimization under Uncertainty in the Era of Big Data and Deep Learning: When Machine Learning Meets Mathematical Programming (2019, methodology): “Although CNNs are mainly used for image classification, they have been used to learn spatial features of traffic flow data at nearby locations which exhibit strong spatial correlations [201].”
• Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting (2018, background): “To deal with different types of features, multi-stream deep learning models [14], [39]–[41] have also been well studied and tested for traffic forecasting problems.”
• Graph Neural Network for Traffic Forecasting: A Survey (2021, background): “Similar concerns exist in the traffic forecasting tasks [246], [247], which has not been fully solved for deep learning models, not”
• High-Order Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting (2018, background): “To deal with different types of features, multi-stream deep learning models [15][40][41][42] have also been well studied and tested for traffic forecasting problems.”
• Traffic transformer: Capturing the continuity and periodicity of time series for traffic forecasting (2020, methodology): “…computing, and novel deep learning models, recent work has pushed the envelope on learning spatio-temporal dependency models for accurate traffic forecasting (Cui, Ke, & Wang, 2018; Jin, Lin, Wu, & Wan, 2018; Wu et al., 2018; Yao, Tang, Wei, Zheng, & Li, 2019; Yu, Yin, & Zhu, 2017).”
• Machine Remaining Useful Life Prediction via an Attention-Based Deep Learning Approach (2021, background): “The attention mechanism has been successfully applied for a number of applications, such as language translation [36] and time-series prediction [37].”