Short-term prediction of traffic dynamics with real-time recurrent learning algorithms
顯示簡易詮釋資料 統計資料| 欄位 | 內容 | 語言 |
|---|---|---|
dc.citation.epage |
83 | en_US |
dc.citation.issue |
1 | en_US |
dc.citation.spage |
59 | en_US |
dc.citation.volume |
5 | en_US |
dc.contributor.author |
Sheu, Jiuh-Biing | en_US |
dc.contributor.author |
Lan, Lawrence W. | en_US |
dc.contributor.author |
Huang, Yi-San | en_US |
dc.contributor.department |
運輸與物流管理系 註:原交通所+運管所 | zh_TW |
dc.contributor.department |
Department of Transportation and Logistics Management | en_US |
dc.date.accessioned |
2014-12-08T15:25:45Z | |
dc.date.available |
2014-12-08T15:25:45Z | |
dc.date.issued |
2009 | en_US |
dc.description.abstract |
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. | en_US |
dc.identifier.doi |
10.1080/18128600802591681 | en_US |
dc.identifier.issn |
1812-8602 | en_US |
dc.identifier.journal |
TRANSPORTMETRICA | en_US |
dc.identifier.uri |
http://dx.doi.org/10.1080/18128600802591681 | en_US |
dc.identifier.uri |
https://ir.lib.nycu.edu.tw/handle/11536/18165 | |
dc.identifier.wosnumber |
WOS:000265585700005 | |
dc.language.iso |
en_US | en_US |
dc.subject |
real-time recurrent learning | en_US |
dc.subject |
traffic dynamics | en_US |
dc.subject |
stochastic | en_US |
dc.subject |
deterministic | en_US |
dc.title |
Short-term prediction of traffic dynamics with real-time recurrent learning algorithms | en_US |
dc.type |
Article; Proceedings Paper | en_US |
檔案
- 000265585700005.pdf (801.5 KB, Adobe PDF)
所屬典藏: 會議論文
引用此條目
Sheu, J.-B., Lan, L. W., & Huang, Y.-S. (2009). Short-term prediction of traffic dynamics with real-time recurrent learning algorithms. TRANSPORTMETRICA, 5(1), 59–83. https://doi.org/10.1080/18128600802591681
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/18165