Investigation of temporal freeway traffic patterns in reconstructed state spaces

Lan, Lawrence W.; Sheu, Jiuh‐Biing; Huang, Ying

doi:10.1016/j.trc.2007.06.006

Cited by 38 publications

(17 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RMSE (=1) 5RMSE (=1/2 time delay) 5RMSE (=time delay) 1 , except for one RBF case marked in gray (RMSE_flow_15 min (=time delay) 5RMSE_flow_15 min (¼1=2time delay) ). Compared with the findings of Lan et al (2008a), the above results seem again to indicate that the characteristics of short-interval traffic dynamics extracted from real world detectors measured within 15-min intervals and involving noises are more stochastic than deterministic; therefore, in the prediction of non-linear short-interval traffic dynamics, stochastic characteristics can be stronger than deterministic characteristics similar to the famous Mackey-Glass equation. Nevertheless, the only one exception for RBF model in Table 3 reveals that the 15-min flows have shown a slight tendency towards deterministic characteristics, so a better accuracy of prediction for 15-min flows using a proper time lag (i.e.…”

Section: Prediction Accuracy With Various Lagssupporting

confidence: 46%

“…According to Lan et al (2008a) who also analysed the traffic features at the same stations, the results have indicated that the degrees of variation of traffic series depend on times of day, the early hours (00:00 am-03:00 am) having the largest coefficient of variation (CV) while the evening peak hours (18:00 pm-21:00 pm) having the smallest CV. The degrees of variation will decline with the length of measured time interval.…”

Section: Datamentioning

confidence: 99%

“…hourly or daily traffic) dynamics wherein conspicuous fluctuations have essentially been smoothed out. Lan et al (2008a) revealed that different non-linear traffic patterns could emerge depending on observed time scale, history data and time-of-day. In view of traffic dynamics measured in different ways would provide more informative insights into its complex nature, developing the prediction models to better elucidate its evolution, measured in different time intervals, periods, lags and times of day, deserves in-depth exploration.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Short-term prediction of traffic dynamics with real-time recurrent learning algorithms

2009

Self Cite

View full text Add to dashboard Cite

Short-term prediction of dynamic traffic states remains critical in the field of advanced traffic management systems and related areas. In this article, a novel real-time recurrent learning (RTRL) algorithm is proposed to address the above issue. We dabble in comparing pair predictability of linear method versus RTRL algorithms and simple non-linear method versus RTRL algorithms individually using a first-order autoregressive time-series AR(1) and a deterministic function. A field study tested with flow, speed and occupancy series data collected directly from dual-loop detectors on a freeway is conducted. The numerical results reveal that the performance of RTRL algorithms in predicting short-term traffic dynamics is satisfactorily accepted. Furthermore, it is found that the dynamics of short-term traffic states characterised in different time intervals, collected in diverse time lags and times of day may have significant effects on the prediction accuracy of the proposed algorithms.

show abstract

Section: Prediction Accuracy With Various Lagssupporting

confidence: 46%

Section: Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Short-term prediction of traffic dynamics with real-time recurrent learning algorithms

2009

Self Cite

View full text Add to dashboard Cite

show abstract

“…The observations from several eld studies provide a basis for this assumption; for example, the travel time data collected by Kwon et al 4 over a 6.2 mi segment on I-880; the 13-day tra±c data series observed by Vlahogianni et al 32 in Athens, Greece; the dual-loop detector data collected by Lan et al 33 on a mainline segment of the northbound Sun Yat-Sen Freeway in Taiwan. Based on this assumption, this study considers the actual route travel time as the combination of the historical trend in terms of the median of historical travel times, the variation in travel time, and a model relationship error.…”

Section: Problem Statementmentioning

confidence: 99%

An Adaptive System for Predicting Freeway Travel Times

2012

Int. J. Info. Tech. Dec. Mak.

View full text Add to dashboard Cite

This paper presents an adaptive system that embeds a Bayesian inference-based dynamic model (BDM) for predicting real-time travel time on a freeway corridor. Bayesian forecasting is a learning process that revises sequentially the state of a priori knowledge of travel time based on newly available information. The prediction result is a posterior travel time distribution that can be employed to generate a single-value (typically but not necessarily the mean) travel time as well as a con¯dence interval representing the uncertainty of travel time prediction. To better track travel time°uctuations during nonrecurrent congestion due to unforeseen events (e.g., incidents, accidents, or bad weather), the BDM is integrated into an adaptive control framework that can automatically learn and adjust the system evolution noise level. The experimental results based on real loop detector data of a freeway stretch in Northern Taiwan suggest that the proposed method is able to provide accurate and reliable travel time prediction under both recurrent and nonrecurrent tra±c conditions. availability and quality of real-time travel time information, this study aims at developing an e®ective and robust online travel time prediction method to provide accurate and reliable short-term travel time forecasts of freeway corridors under di®erent tra±c conditions.A rich body of literature has been devoted to the development of short-term travel time prediction approaches over the last three decades. van Hinsbergen et al. 3 conducted a broad literature review on the existing tra±c prediction methodologies. The explored techniques for short-term travel time prediction include three major categories: (i) parametric methods, such as linear regression, 4,5 time series models, 6 and Kalman¯ltering techniques, 7À10 Bayesian models, 11 (ii) nonparametric statistical methods, such as neural network models, 12À17 Support Vector Regression, 18,19 and (iii) hybrid integration methods. 20À23 Recently, to enhance model°exibility and adaptiveness to the underlying tra±c pattern changes, relevant studies have been conducted to update online model parameters based on real-time observations. Yang et al. 24 compared an adaptive recursive least-square (ARLS) method and a Kalman¯lter method for online tra±c speed prediction; both methods recursively adjust the coe±cients of o®line models to achieve better prediction accuracy. Their¯nding showed that the (nonzero) noise covariance matrix is important to a state-space model. Liu et al. 25 extended the state-space neural network (SSNN) by incorporating the extended Kalman¯ltering (EKF) algorithm. They compared their approach with two existing models, namely the Kalman¯ltering method by Chien and Kuchipudi 8 and the neural network model trained by LevenbergÀMarquardt method, and found that their model performance is better in terms of computation time and prediction accuracy. Along the same line, van Lint 15 proposed censored EKF and delayed EKF algorithms for online traveltime prediction by adaptively training t...

show abstract

“…The different plots illustrate macroscopic regularities in the evolution of time series values: relative minima occurring in nocturnal rest and within workday periods, grow to relative maxima occurring at the beginning and at the end of workdays, and for the middle hours of weekend days. At a smaller time scale, a fluctuating component goes along with those macroscopic regularities and causes the phenomenon of “similar but not exactly the same” patterns for successive time series (Lan et al, 2008). For the case of time series of volume data, that fluctuating component noticeabley has different amplitude when congestion, reflected in occupancy rates, is low than when congestion gets higher.…”

Section: Input Data Analysismentioning

confidence: 99%

Wavelet-Based Denoising for Traffic Volume Time Series Forecasting with Self-Organizing Neural Networks

Boto-Giralda

Pernas

González-Ortega

et al. 2010

Computer-Aided Civil and Infrastructure Engineering

114

View full text Add to dashboard Cite

In their goal to effectively manage the use of existing infrastructures, intelligent transportation systems require precise forecasting of near‐term traffic volumes to feed real‐time analytical models and traffic surveillance tools that alert of network links reaching their capacity. This article proposes a new methodological approach for short‐term predictions of time series of volume data at isolated cross sections. The originality in the computational modeling stems from the fit of threshold values used in the stationary wavelet‐based denoising process applied on the time series, and from the determination of patterns that characterize the evolution of its samples over a fixed prediction horizon. A self‐organizing fuzzy neural network is optimized in its configuration parameters for learning and recognition of these patterns. Four real‐world data sets from three interstate roads are considered for evaluating the performance of the proposed model. A quantitative comparison made with the results obtained by four other relevant prediction models shows a favorable outcome.

show abstract

Investigation of temporal freeway traffic patterns in reconstructed state spaces

Cited by 38 publications

References 26 publications

Short-term prediction of traffic dynamics with real-time recurrent learning algorithms

Short-term prediction of traffic dynamics with real-time recurrent learning algorithms

An Adaptive System for Predicting Freeway Travel Times

Wavelet-Based Denoising for Traffic Volume Time Series Forecasting with Self-Organizing Neural Networks

Contact Info

Product

Resources

About