Deep Convolutional Mesh RNN for Urban Traffic Passenger Flows Prediction

Zou, Zhene; Peng, Hao; Liu, Lin; Xiong, Guixi; Du, Bowen; Bhuiyan, Zakirul Alam; Long, Yuntao; Li, Da

doi:10.1109/smartworld.2018.00227

Cited by 25 publications

(16 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…APTN [25] considering not only temporal characteristics but also spatial characteristics only applicable to regular Euclidean datasets GATCN [9], T-GCN [10], GCN [26] applicable to irregular non-Euclidean datasets assume that adjacent regions have the same effect on the predicted region Many data-driven studies were carried out using time series models due to the periodicity and tendency of urban traffic flow in the time dimension. Parametric models and deep learning models are two types of prediction research based on time series features.…”

Section: Models Contribution Shortcomingsmentioning

confidence: 99%

“…Gu et al proposed an improved Bayesian combination model with deep learning (IBCM-DL) for traffic flow prediction and proved it outperforms other state-of-the-art methods in terms of accuracy and stability [10]. Deep learning models, such as Artificial Neural Network [11], Recurrent Neural Network (RNN) [26], Long Short-term Memory (LSTM) [27], etc., have also performed well in terms of prediction.…”

Section: Models Contribution Shortcomingsmentioning

confidence: 99%

See 1 more Smart Citation

Region-Level Traffic Prediction Based on Temporal Multi-Spatial Dependence Graph Convolutional Network from GPS Data

2022

View full text Add to dashboard Cite

Region-level traffic information can characterize dynamic changes of urban traffic at the macro level. Real-time region-level traffic prediction help city traffic managers with traffic demand analysis, traffic congestion control, and other activities, and it has become a research hotspot. As more vehicles are equipped with GPS devices, remote sensing data can be collected and used to conduct data-driven region-level-based traffic prediction. However, due to dynamism and randomness of urban traffic and the complexity of urban road networks, the study of such issues faces many challenges. This paper proposes a new deep learning model named TmS-GCN to predict region-level traffic information, which is composed of Graph Convolutional Network (GCN) and Gated Recurrent Unit (GRU). The GCN part captures spatial dependence among regions, while the GRU part captures the dynamic change of traffic within the region. Model verification and comparison are carried out using real taxi GPS data from Shenzhen. The experimental results show that the proposed model outperforms both the classic time series prediction model and the deep learning model at different scales.

show abstract

Section: Models Contribution Shortcomingsmentioning

confidence: 99%

Section: Models Contribution Shortcomingsmentioning

confidence: 99%

Region-Level Traffic Prediction Based on Temporal Multi-Spatial Dependence Graph Convolutional Network from GPS Data

2022

View full text Add to dashboard Cite

show abstract

“…In contrast, we can easily obtain implicit feedback information, and the data covers most users and objects; thus, it can mitigate the problem of sparse data to some extent [65][66][67]. We obtain a top-N recommendation list via modeling with a recommendation algorithm according to historic explicit and implicit feedback information.…”

Section: Problem Definitionmentioning

confidence: 99%

A Top-N Movie Recommendation Framework Based on Deep Neural Network with Heterogeneous Modeling

Gong

Zhang

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

To provide more accurate and stable recommendations, it is necessary to combine display information with implicit information and to dig out potential information. Existing methods only consider explicit feedback information or implicit feedback information unilaterally and ignore the potential information of explicit feedback information and implicit feedback information, which is also crucial to the accuracy of the recommendation system. However, the traditional Heterogeneous Information Networks (HIN) recommendation ignores the attribute information in the meta-path and the interaction between the user and the item and, instead, only considers the linear characteristics of the user-object often ignoring its non-linear characteristics. Aiming at the potential information acquisition problem from assorted feedback, we propose a new top-N recommendation method MFDNN for Heterogeneous Information Networks (HINs). First, we consider explicit and implicit feedback information to determine the potential preferences of users and the potential features of the product. Then, matrix factorization (MF) and a deep neural network (DNN) are fused to learn independent feature embeddings through MF and DNN, and fully considering the linear and non-linear characteristics of the user-object. MFDNN was tested on several real data sets, such as Movie-Lens, and compared with benchmark experiments. MFDNN significantly improved the hit ratio (HR) and normalized discounted cumulative gain (NDCG). Further research showed that the meta-path bias had an excellent effect on the gain of potential information mining and the fusion of explicit and implicit information in the accuracy and stability of user interest classification.

show abstract

“…Wang and Xu proposed an LSTM-RNN-based time series prediction model for urban highway traffic flow in a deep learning framework, which reconstructed the traffic time series by the integrated spatiotemporal correlation of traffic flow, so that the LSTM-RNN gains and enhances data mining capability. Zhene et al (2018 ) proposed a deep learning model based on CNN and RNN, using matrix traffic as input, extracting traffic features using CNN, predicting feature evolution using RNN, and mixing the two models to achieve traffic flow prediction. Although these methods considered spatiotemporal correlation, they did not address the long-term memory problem and the gradient problem in backpropagation.…”

Section: Introductionmentioning

confidence: 99%

Traffic Flow Prediction Model Based on the Combination of Improved Gated Recurrent Unit and Graph Convolutional Network

Zhao

Han

2022

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

With the rapid economic growth and the continuous increase in population, cars have become a necessity for most people to travel. The increase in the number of cars is accompanied by serious traffic congestion. In order to alleviate traffic congestion, many places have introduced policies such as vehicle restriction, and intelligent transportation systems have gradually been put into use. Due to the chaotic complexity of the traffic road network and the short-term mobility of the population, traffic flow prediction is affected by many complex factors, and an effective traffic flow forecasting system is very challenging. This paper proposes a model to predict the traffic flow of Wenyi Road in Hangzhou. Wenyi Road consists of four crossroads. The four intersections have the same changing trend in traffic flow at the same time, which indicates that the roads influence each other spatially, and the traffic flow has spatial and temporal correlation. Based on this feature of traffic flow, we propose the IMgru model to better extract the traffic flow temporal characteristics. In addition, the IMgruGcn model is proposed, which combines the graph convolutional network (GCN) module and the IMgru module, to extract the spatiotemporal features of traffic flow simultaneously. Finally, according to the morning and evening peak characteristics of Hangzhou, the Wenyi Road dataset is divided into peak period and off-peak period for prediction. Comparing the IMgruGcn model with five baseline models and a state-of-the-art method, the IMgruGcn model achieves better results. Best results were also achieved on a public dataset, demonstrating the generalization ability of the IMgruGcn model.

show abstract

Deep Convolutional Mesh RNN for Urban Traffic Passenger Flows Prediction

Cited by 25 publications

References 14 publications

Region-Level Traffic Prediction Based on Temporal Multi-Spatial Dependence Graph Convolutional Network from GPS Data

Region-Level Traffic Prediction Based on Temporal Multi-Spatial Dependence Graph Convolutional Network from GPS Data

A Top-N Movie Recommendation Framework Based on Deep Neural Network with Heterogeneous Modeling

Traffic Flow Prediction Model Based on the Combination of Improved Gated Recurrent Unit and Graph Convolutional Network

Contact Info

Product

Resources

About