標題: Short-term prediction of traffic dynamics with real-time recurrent learning algorithms
作者: Sheu, Jiuh-Biing
Lan, Lawrence W.
Huang, Yi-San
運輸與物流管理系 註:原交通所+運管所
Department of Transportation and Logistics Management
關鍵字: real-time recurrent learning;traffic dynamics;stochastic;deterministic
公開日期: 2009
摘要: 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.
URI: http://hdl.handle.net/11536/18165
http://dx.doi.org/10.1080/18128600802591681
ISSN: 1812-8602
DOI: 10.1080/18128600802591681
期刊: TRANSPORTMETRICA
Volume: 5
Issue: 1
起始頁: 59
結束頁: 83
顯示於類別:會議論文


文件中的檔案:

  1. 000265585700005.pdf

若為 zip 檔案,請下載檔案解壓縮後,用瀏覽器開啟資料夾中的 index.html 瀏覽全文。