Low-Dimensional Models for Compressed Sensing and Prediction of Large-Scale Traffic Data

Mitrović, Nikola; Asif, Muhammad; Dauwels, Justin; Jaillet, Patrick

doi:10.1109/tits.2015.2411675

Cited by 44 publications

(26 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [28] the authors discuss learning the matrix Φ from the available data. Then when new measurements (now only for the m retained locations) become available the new measurements for the road network as a whole can be given bŷ…”

Section: A Measurement Selectionmentioning

confidence: 99%

“…This measurement vector is then used as the measurement vector in the particle filter as detailed below. Estimates for the state at each location are then provided by the PF rather than the approximation scheme in [28].…”

Section: A Measurement Selectionmentioning

confidence: 99%

“…The authors of [28] use column based matrix decomposition, [29]- [31], in order to give the overall road network in terms of a smaller subnetwork. This involves the singular value decomposition (SVD) of the matrix containing the measurements for the entire traffic network.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Traffic state estimation via a particle filter over a reduced measurement space

Hawes

Amer

Mihaylova

2017

2017 20th International Conference on Information Fusion (Fusion)

View full text Add to dashboard Cite

Abstract-Traffic control and vehicle route planning require accurate estimates of the traffic state in order to be successfully implemented. This estimation problem can be solved by using particle filters in conjunction with macroscopic traffic models such as the stochastic compositional model. The accuracy of the estimates can be decreased for road segments where there are no measurements available. However, the inclusion of measurements for all segment boundaries carries a computational cost associated with the evaluation of the likelihood function required by the particle filter. To solve this problem, this paper proposes using the column based matrix decomposition method to select the most significant locations in the road network. This results in the particle filter being applied over a reduced measurement space, allowing a trade-off between computational efficiency and estimation accuracy to be achieved. A performance evaluation based on a simulated stretch of road is provided to validate the proposed method. It shows that by selecting half the original number of measurements, the computational time is reduced by approximately 9% without significantly decreasing the estimation accuracy. A more significant improvement in terms of savings in computational complexity can be expected when considering larger urban road networks.

show abstract

Section: A Measurement Selectionmentioning

confidence: 99%

Section: A Measurement Selectionmentioning

confidence: 99%

See 1 more Smart Citation

Traffic state estimation via a particle filter over a reduced measurement space

Hawes

Amer

Mihaylova

2017

2017 20th International Conference on Information Fusion (Fusion)

View full text Add to dashboard Cite

show abstract

“…Other examples include Kalman filtering [7], non-parametric regression models [8,9], and Support Vector machines [10,11] for predicting travel time and flow. [12] exploited compressed sensing to reduce the complexity of road networks, then support vector regression (SVR) is used for predicting travel speed on links. A Trajectory Reconstruction Model is used by [13] for travel time estimations.…”

Section: Introductionmentioning

confidence: 99%

Understanding and Predicting Travel Time with Spatio-Temporal Features of Network Traffic Flow, Weather and Incidents

Yang

Qian

2019

IEEE Intell. Transport. Syst. Mag.

View full text Add to dashboard Cite

Travel time on a route varies substantially by time of day and from day to day. It is critical to understand to what extent this variation is correlated with various factors, such as weather, incidents, events or travel demand level in the context of dynamic networks. This helps a better decision making for infrastructure planning and realtime traffic operation. We propose a data-driven approach to understand and predict highway travel time using spatio-temporal features of those factors, all of which are acquired from multiple data sources. The prediction model holistically selects the most related features from a high-dimensional feature space by correlation analysis, principle component analysis and LASSO. We test and compare the performance of several regression models in predicting travel time 30 min in advance via two case studies: (1) a 6-mile highway corridor of I-270N in D.C. region, and (2) a 2.3-mile corridor of I-376E in Pittsburgh region. We found that some bottlenecks scattered in the network can imply congestion on those corridors at least 30 minutes in advance, including those on the alternative route to the corridors of study. In addition, real-time travel time is statistically related to incidents on some specific locations, morning/afternoon travel demand, visibility, precipitation, wind speed/gust and the weather type. All those spatio-temporal information together help improve prediction accuracy, comparing to using only speed data. In both case studies, random forest shows the most promise, reaching a root-mean-squared error of 16.6% and 17.0% respectively in afternoon peak hours for the entire year of 2014.

show abstract

“…In addition, local features are irrelevant with its scale, rotation and translation, which can be used to establish local similarity matching methods, even with complex background or geometric distortion. In recent years, local features draw more attentions [23]. In order to fully express the visual content of images, an image may need thousands of local features, which will increase the image similarity matching process time.…”

mentioning

confidence: 99%