Short-Term Traffic Prediction Based on Dynamic Tensor Completion

Tan, Huachun; Wu, Yao; Shen, Bin; Jin, Peter J.; Ran, Bin

doi:10.1109/tits.2015.2513411

Cited by 215 publications

(72 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dauwels, Aslam, Asif, and Zhao (2014) combined tensor decomposition and the support vector regression (SVR) method to solve the traffic prediction problem. Tan, Wu, Shen, Jin, and Ran (2016) proposed a novel dynamic tensor completion (DTC) method by taking the multimode information of traffic data into consideration for short-term traffic prediction. Most of the existing methods predict traffic flows using historical check-out/in data in a bike system.…”

Section: Rel Ated Workmentioning

confidence: 99%

A reliable traffic prediction approach for bike‐sharing system by exploiting rich information with temporal link prediction strategy

Zhou

Zhu

et al. 2019

Transactions in GIS

View full text Add to dashboard Cite

Bike‐sharing systems have been widely used in major cities across the world. As bike borrowing and return at different stations in different periods are not balanced, the bikes in a bike‐sharing system need to be redistributed frequently to rebalance the system. Therefore, traffic flow forecasting of the bike‐sharing system is an important issue, as this is conducive to achieving rebalancing of the bike system. In this article, we present a new traffic flow prediction approach based on the temporal links in dynamic traffic flow networks. A station clustering algorithm is first introduced to cluster stations into groups. A temporal link prediction method based on the dynamic traffic flow network method (STW+M) is then proposed to predict the traffic flow between stations. In our method, the non‐negative tensor decomposition and time‐series analysis model capture the rich information (temporal variabilities, spatial characteristics, and weather information) of the across‐clusters transition. Then, a temporal link prediction strategy is used to forecast potential links and weights in the traffic flow network by investigating both the network structure and the results of tensor computations. In order to assess the methods proposed in this article, we have used the data of bike‐sharing systems in New York and Washington, DC to conduct bike traffic prediction and the experimental results have shown that our method produces the lowest root mean square error (RMSE) and mean square error (MSE). Compared to four prediction methods from the literature, our RMSE and MSE of the two datasets have been lowered by an average of 2.55 (Washington, DC) and 2.41 (New York) and 3.35 (Washington, DC) and 2.96 (New York), respectively. The results show that the proposed approach improves predictions of traffic flow.

show abstract

Section: Rel Ated Workmentioning

confidence: 99%

A reliable traffic prediction approach for bike‐sharing system by exploiting rich information with temporal link prediction strategy

Zhou

Zhu

et al. 2019

Transactions in GIS

View full text Add to dashboard Cite

show abstract

“…The future traffic prediction problem becomes particularly challenging in regions with diverse modes of transport, such as in India, where ETA calculations must account for the multimodal nature of traffic [24], [25]. For instance the ETA calculations for buses should not only use traffic data meant for cars.A class of pertinent approaches have sought to visualize the traffic data as an incomplete matrix or tensor, and exploited this correlation to fill-in the missing entries [19], [26]- [28]. Complementary to these approaches, time-series modeling focuses on learning the temporal dynamics of traffic and generate predictions in an online manner [29].…”

Section: B Applicationsmentioning

confidence: 99%

Online Variational Bayesian Subspace Filtering

Charul

Bhatt

Biyani

et al. 2019

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Matrix completion and robust principal component analysis have been widely used for the recovery of data suffering from missing entries or outliers. In many real-world applications however, the data is also time-varying, and the naive approach of per-snapshot recovery is both expensive and sub-optimal. This paper develops generative Bayesian models that fit sequential multivariate measurements arising from a low-dimensional time-varying subspace. A variational Bayesian subspace filtering approach is proposed that learns the underlying subspace and its state-transition matrix. Different from the plethora of deterministic counterparts, the proposed approach utilizes automatic relevance determination priors that obviate the need to tune key parameters such as rank and noise power. We also propose a forward-backward algorithm that allows the updates to be carried out at low complexity. Extensive tests over traffic and electricity data demonstrate the superior imputation, outlier rejection, and temporal prediction prowess of the proposed algorithm over the state-of-the-art matrix/tensor completion algorithms.

show abstract

“…This also requires that the data required by the vehicle Internet have a high spatiotemporal resolution. However, in reality, a large amount of missing data and low‐quality data often appear 21,22 . Missing data usually have a very wide impact.…”

Section: Introductionmentioning

confidence: 99%

A novel approach of tensor‐based data missing estimation for Internet of Vehicles

Zhang

Gao

et al. 2020

Int J Communication

View full text Add to dashboard Cite

Summary In the face of the current huge amount of intelligent traffic data, collecting and statistical processing is a necessary and important process. But the inevitable data missing problem is the current research focus. In this paper, a novel approach of tensor‐based data missing estimation for Internet of Vehicles is proposed for the problem of missing the Internet of Vehicles data: Integrated Bayesian tensor decomposition (IBTD). In the data model construction stage, the random sampling principle is used to randomly extract the missing data to generate a subset of data. And the optimized Bayesian tensor decomposition algorithm is used for interpolation. Introduce the integration idea, analyze, and sort the error results after multiple interpolations, consider the space‐time complexity, and choose the optimal average to get the best result. The performance of the proposed model was evaluated by mean absolute percentage error (MAPE) and root mean square error (RMSE). The experimental results show that the proposed method can effectively interpolate the traffic data sets with different missing quantities and get good interpolation results.

show abstract

Short-Term Traffic Prediction Based on Dynamic Tensor Completion

Cited by 215 publications

References 59 publications

A reliable traffic prediction approach for bike‐sharing system by exploiting rich information with temporal link prediction strategy

A reliable traffic prediction approach for bike‐sharing system by exploiting rich information with temporal link prediction strategy

Online Variational Bayesian Subspace Filtering

A novel approach of tensor‐based data missing estimation for Internet of Vehicles

Contact Info

Product

Resources

About