The Optimization Method of Dynamic Traffic State Identification on Urban Arterial Road
- DOI
- 10.2991/cmfe-15.2015.98How to use a DOI?
- Keywords
- dynamic traffic state identification; improved FCM algorithm; Data Envelopment Analysis ( DEA); long-time congestion; congestion pre-identification
- Abstract
Dynamic traffic state identification is important to traffic control and guidance on urban arterial road, according to the fuzzy characteristics of the traffic flow, this paper firstly establishes a dynamic traffic state identification model based on improved Fuzzy C-Means (FCM) clustering to divide traffic states into four phases. Secondly, because the FCM algorithm is difficult to distinguish the states good or bad in the same phase, this paper establishes a dynamic traffic state identification model based on Data Envelopment Analysis (DEA), which uses the comprehensive index to evaluate each state sample, and uses similarity between the results of improved FCM and DEA to evaluate this model. Thirdly, this paper analyzes the statistical features of traffic state changes from relative smooth to congestion (congestion to severe congestion) combining with time sequence, and proposes the pre-identification number of long-time congestion. Finally, the actual data of a urban arterial road in H city as an example are verified the effects of the method, the similarity of two models is 86.5%, which illustrates the method of this paper is feasible, and the pre-identification number is three.
- Copyright
- © 2015, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Shuo Tong PY - 2015/07 DA - 2015/07 TI - The Optimization Method of Dynamic Traffic State Identification on Urban Arterial Road BT - Proceedings of the International Conference on Chemical, Material and Food Engineering PB - Atlantis Press SP - 416 EP - 421 SN - 2352-5401 UR - https://doi.org/10.2991/cmfe-15.2015.98 DO - 10.2991/cmfe-15.2015.98 ID - Tong2015/07 ER -