Real‐time road traffic forecasting using regime‐switching space‐time models and adaptive LASSO

Kamarianakis, Yiannis; Shen, Wei; Wynter, Laura

doi:10.1002/asmb.1937

Cited by 100 publications

(56 citation statements)

References 56 publications

(83 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In agreement with previous studies, it has been found that regularised methods perform well, due to their ability to simultaneously shrink and select variables. Of the three methods tested here, the LASSO exhibits the best performance, supporting the findings of (Kamarianakis et al, 2012), but is generally comparable with the MCP and SCAD. Due to the increased model parsimony offered by the MCP method, it is recommended that MCP is used where explanatory power is required in the model.…”

Section: Discussionsupporting

confidence: 75%

“…Nonzero elements can be viewed as conditionally independent and remain in the model. In a related approach, (Kamarianakis et al, 2012) used the least absolute shrinkage and selection operator (LASSO) to estimate a time varying threshold regression model, tailored to different traffic states. The aforementioned approaches do not make assumptions about the nature of the spatio-temporal relationship between locations, instead learning it from the data.…”

Section: Space-time Forecastingmentioning

confidence: 99%

See 1 more Smart Citation

A Comparison of Neighbourhood Selection Techniques in Spatio-Temporal Forecasting Models

Haworth

Cheng

2014

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Spatio-temporal neighbourhood (STN) selection is an important part of the model building procedure in spatio-temporal forecasting. The STN can be defined as the set of observations at neighbouring locations and times that are relevant for forecasting the future values of a series at a particular location at a particular time. Correct specification of the STN can enable forecasting models to capture spatio-temporal dependence, greatly improving predictive performance. In recent years, deficiencies have been revealed in models with globally fixed STN structures, which arise from the problems of heterogeneity, nonstationarity and nonlinearity in spatio-temporal processes. Using the example of a large dataset of travel times collected on London's road network, this study examines the effect of various STN selection methods drawn from the variable selection literature, varying from simple forward/backward subset selection to simultaneous shrinkage and selection operators. The results indicate that STN selection methods based on penalisation are effective. In particular, the maximum concave penalty (MCP) method selects parsimonious models that produce good forecasting performance.* Corresponding author. This is useful to know for communication with the appropriate person in cases with more than one author.

show abstract

Section: Discussionsupporting

confidence: 75%

Section: Space-time Forecastingmentioning

confidence: 99%

A Comparison of Neighbourhood Selection Techniques in Spatio-Temporal Forecasting Models

Haworth

Cheng

2014

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…GWR has been applied widely to various spatially oriented issues, including water quality [37,38], forestry [39], economics [40,41], remote sensing [42], and urban studies [43]. According to Nunes et al [44], GWR can improve forest fire regime predictions by considering regression as a non-stationary spatial process.…”

Section: Introductionmentioning

confidence: 99%

Examining Spatial Variation in the Effects of Japanese Red Pine (Pinus densiflora) on Burn Severity Using Geographically Weighted Regression

2017

View full text Add to dashboard Cite

Abstract:Burn severity has profound impacts on the response of post-fire forest ecosystems to fire events. Numerous previous studies have reported that burn severity is determined by variables such as meteorological conditions, pre-fire forest structure, and fuel characteristics. An underlying assumption of these studies was the constant effects of environmental variables on burn severity over space, and these analyses therefore did not consider the spatial dimension. This study examined spatial variation in the effects of Japanese red pine (Pinus densiflora) on burn severity. Specifically, this study investigated the presence of spatially varying relationships between Japanese red pine and burn severity due to changes in slope and elevation. We estimated conventional ordinary least squares (OLS) and geographically weighted regression (GWR) models and compared them using three criteria; the coefficients of determination (R 2 ), Akaike information criterion for small samples (AICc), and Moran's I-value. The GWR model performed considerably better than the OLS model in explaining variation in burn severity. The results provided strong evidence that the effect of Japanese red pine on burn severity was not constant but varied spatially. Elevation was a significant factor in the variation in the effects of Japanese red pine on burn severity. The influence of red pine on burn severity was considerably higher in low-elevation areas but became less important than the other variables in high-elevation areas. The results of this study can be applied to location-specific strategies for forest managers and can be adopted to improve fire simulation models to more realistically mimic the nature of fire behavior.

show abstract

“…It indicates that not all of these spatiotemporal variables are predictive or informative in terms of traffic flow forecasting at target site. 19,21 Directly fitting an LSSVR model to the traffic data including much redundant and/or noisy information will dramatically increase the complexity of forecasting model. Consequently, it may lead to overfitting and thus influence the effectiveness of model.…”

Section: Intelligent Transportation System (Its)mentioning

confidence: 99%

“…On the whole, 10 sites are related to the target site 21 besides itself, which are 5,7,8,11,13,14,18,19,23, and 24. Among them, sites 8, 11, and 23 contribute to the target site 21 as the role of direct upstream sites.…”

Section: Interpretation Of Spatiotemporal Variablesmentioning

confidence: 99%

Spatiotemporal variable and parameter selection using sparse hybrid genetic algorithm for traffic flow forecasting

Chen

Wei

Liu

et al. 2017

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Short-term traffic flow forecasting is a difficult yet important problem in intelligent transportation systems. Complex spatiotemporal interactions between the target road segment and other road segments can provide important information for the accurate forecasting. Meanwhile, spatiotemporal variable selection and traffic flow prediction should be solved in a unified framework such that they can benefit from each other. In this article, we propose a novel sparse hybrid genetic algorithm by introducing sparsity constraint and real encoding scheme into genetic algorithm in order to optimize shortterm traffic flow prediction model based on least squares support vector regression. This method can integrate spatiotemporal variable selection, parameter selection as well as traffic flow prediction in a unified framework, indicating that the ''goodness,'' that is, contribution, of selected spatiotemporal variables and optimized parameters directly depends on the final traffic flow prediction accuracy. The real-world traffic flow data are collected from 24 observation sites located around the intersection of Interstate 205 and Interstate 84 in Portland, OR, USA. The experimental results show that the proposed sparse hybrid genetic algorithm-least square support vector regression prediction model can produce better performance but with much fewer spatiotemporal variables in comparison with other related models.

show abstract

Real‐time road traffic forecasting using regime‐switching space‐time models and adaptive LASSO

Cited by 100 publications

References 56 publications

A Comparison of Neighbourhood Selection Techniques in Spatio-Temporal Forecasting Models

A Comparison of Neighbourhood Selection Techniques in Spatio-Temporal Forecasting Models

Examining Spatial Variation in the Effects of Japanese Red Pine (Pinus densiflora) on Burn Severity Using Geographically Weighted Regression

Spatiotemporal variable and parameter selection using sparse hybrid genetic algorithm for traffic flow forecasting

Contact Info

Product

Resources

About