Quantifying uncertainty in short-term traffic prediction and its application to optimal staffing plan development

Lin, Lei; Handley, John C.; Gu, Ying; Zhu, Lei; Wen, Xuejin; Sadek, Adel W.

doi:10.1016/j.trc.2018.05.012

Cited by 51 publications

(26 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Third, the GCNN models can also be applied to solve other transportation problems that can be represented by graphs such as subway station demand prediction, network traffic state estimation, and so on. Fourth, the GCNN model can be extended to capture uncertainties in predictions (Lin et al, 2018a). Fifth, the GCNN model can be considered as a component in a comprehensive framework for dynamic bike rebalancing.…”

Section: Conclusion and Future Research Directionsmentioning

confidence: 99%

Predicting station-level hourly demand in a large-scale bike-sharing network: A graph convolutional neural network approach

Lin

Peeta

2018

Transportation Research Part C: Emerging Technologies

Self Cite

376

184

View full text Add to dashboard Cite

This study proposes a novel Graph Convolutional Neural Network with Data-driven Graph Filter (GCNN-DDGF) model that can learn hidden heterogeneous pairwise correlations between stations to predict station-level hourly demand in a large-scale bike-sharing network. Two architectures of the GCNN-DDGF model are explored; GCNNreg-DDGF is a regular GCNN-DDGF model which contains the convolution and feedforward blocks, and GCNNrec-DDGF additionally contains a recurrent block from the Long Short-term Memory neural network architecture to capture temporal dependencies in the bike-sharing demand series. Furthermore, four types of GCNN models are proposed whose adjacency matrices are based on various bikesharing system data, including Spatial Distance matrix (SD), Demand matrix (DE), Average Trip Duration matrix (ATD), and Demand Correlation matrix (DC). These six types of GCNN models and seven other benchmark models are built and compared on a Citi Bike dataset from New York City which includes 272 stations and over 28 million transactions from 2013 to 2016.Results show that the GCNNrec-DDGF performs the best in terms of the Root Mean Square Error, the Mean Absolute Error and the coefficient of determination (R 2 ), followed by the GCNNreg-DDGF. They outperform the other models. Through a more detailed graph network analysis based on the learned DDGF, insights are obtained on the "black box" of the GCNN-DDGF model. It is found to capture some information similar to details embedded in the SD, DE and DC matrices. More importantly, it also uncovers hidden heterogeneous pairwise correlations between stations that are not revealed by any of those matrices.

show abstract

Section: Conclusion and Future Research Directionsmentioning

confidence: 99%

Predicting station-level hourly demand in a large-scale bike-sharing network: A graph convolutional neural network approach

Lin

Peeta

2018

Transportation Research Part C: Emerging Technologies

Self Cite

376

184

View full text Add to dashboard Cite

show abstract

“…GJR-GARCH allows the conditional variance to respond differently to the past negative and positive innovations, which is inspiring for this article. Lin et al [32] used quantile regression to deal with the heteroscedasticity problem, which used asymmetric loss functions for prediction intervals calculation of short-term traffic volume.…”

Section: Literature Reviewmentioning

confidence: 99%

Short‐Term Traffic Volume Forecasting with Asymmetric Loss Based on Enhanced KNN Method

Wang

2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Short-term traffic volume forecasting is one of the most essential elements in Intelligent Transportation System (ITS) by providing prediction of traffic condition for traffic management and control applications. Among previous substantial forecasting approaches, K nearest neighbor (KNN) is a nonparametric and data-driven method popular for conciseness, interpretability, and real-time performance. However, in previous related researches, the limitations of Euclidean distance and forecasting with asymmetric loss have rarely been focused on. This research aims to fill up these gaps. This paper reconstructs Euclidean distance to overcome its limitation and proposes a KNN forecasting algorithm with asymmetric loss. Correspondingly, an asymmetric loss index, Imbalanced Mean Squared Error (IMSE), has also been proposed to test the effectiveness of newly designed algorithm. Moreover, the effect of Loess technique and suitable parameter value of dynamic KNN method have also been tested. In contrast to the traditional KNN algorithm, the proposed algorithm reduces the IMSE index by more than 10%, which shows its effectiveness when the cost of forecasting residual direction is notably different. This research expands the applicability of KNN method in short-term traffic volume forecasting and provides an available approach to forecast with asymmetric loss.

show abstract

“…This is especially true if we consider complex traffic behaviors and heterogeneous data sources that rely on noisy sensors such as the one considered in this article. However, with a few notable exceptions such as Tsekeris & Stathopoulos (2009) and Chen et al (2011), who explore the use of GARCH volatility models, and Lin et al (2018), who consider the direct estimation of prediction intervals, the heteroscedastic treatment of traffic phenomena, like the one proposed in this article, has been studied to a much smaller extent.…”

Section: Heteroscedastic Time-series Modelingmentioning

confidence: 99%

Heteroscedastic Gaussian processes for uncertainty modeling in large-scale crowdsourced traffic data

Rodrigues

Pereira

2018

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

Accurately modeling traffic speeds is a fundamental part of efficient intelligent transportation systems. Nowadays, with the widespread deployment of GPS-enabled devices, it has become possible to crowdsource the collection of speed information to road users (e.g. through mobile applications or dedicated in-vehicle devices). Despite its rather wide spatial coverage, crowdsourced speed data also brings very important challenges, such as the highly variable measurement noise in the data due to a variety of driving behaviors and sample sizes. When not properly accounted for, this noise can severely compromise any application that relies on accurate traffic data. In this article, we propose the use of heteroscedastic Gaussian processes (HGP) to model the time-varying uncertainty in large-scale crowdsourced traffic data. Furthermore, we develop a HGP conditioned on sample size and traffic regime (SRC-HGP), which makes use of sample size information (probe vehicles per minute) as well as previous observed speeds, in order to more accurately model the uncertainty in observed speeds. Using 6 months of crowdsourced traffic data from Copenhagen, we empirically show that the proposed heteroscedastic models produce significantly better predictive distributions when compared to current state-of-the-art methods for both speed imputation and short-term forecasting tasks.

show abstract

Quantifying uncertainty in short-term traffic prediction and its application to optimal staffing plan development

Cited by 51 publications

References 57 publications

Predicting station-level hourly demand in a large-scale bike-sharing network: A graph convolutional neural network approach

Predicting station-level hourly demand in a large-scale bike-sharing network: A graph convolutional neural network approach

Short‐Term Traffic Volume Forecasting with Asymmetric Loss Based on Enhanced KNN Method

Heteroscedastic Gaussian processes for uncertainty modeling in large-scale crowdsourced traffic data

Contact Info

Product

Resources

About