Fusion and Recognition Model of Traffic State on High-Grade Highway Segment

Abstract

Abstract: In order to provide reasonable and accurate traffic status information for the traffic managers, a novel method for traffic state recognition based on vague set theory is proposed. According to the characteristics of discreteness, fuzziness and time-variant in the detecting units, decision-making information of adjacent detections units at the same level is merged to obtain a sequence of traffic state blocks. A weighted distance formula is proposed to turn the position and length of traffic state block into weights, and based on which, the fusion and recognition model of traffic states information on high-grade highway segment is established. Examples verify the effectiveness of them ode,l wh ich also prov ide a new w ay to recogn ize the traffic state information of high-grade highway segment

Key words: traffic engineering, fusion and recognition, vague set, high-grade highway segment, traffic state decision information

摘要： 为了给区域交通管理者提供合理、准确的交通状态信息,提出了一种全新的可用于识别高等级公路路段交通状态的方法。针对路段中检测单元上交通状态决策信息的离散、模糊和时变特征,将路段内相邻检测单元同类交通状态决策信息合并,得到有序交通状态块;基于vague集理论提出了一种新的加权距离公式,并将合并后各交通状态块在路段中的位置和长度作为权重,建立了基于交通状态块决策信息的路段综合交通状态融合识别模型。通过算例验证了该模型的有效性,为识别高等级公路路段交通状态提供了一种新途径。

关键词: 交通工程, 融合识别, vague集, 高等级公路路段, 交通状态决策信息

CLC Number:

U491

CHEN Hong, ZHANG Miao, WANG Long-fei,ZHAO Yu-qiao. Fusion and Recognition Model of Traffic State on High-Grade Highway Segment[J]. Journal of Chongqing Jiaotong University(Natural Science), 2010, 29(5): 772-775.

陈红, 章渺, 王龙飞, 赵禹乔. 高等级公路路段交通状态融合识别模型[J]. 重庆交通大学学报（自然科学版）, 2010, 29(5): 772-775.

References

[1] Hua J Y,Ardeshir F.Dynamic Traffic Pattern Classification U-sing Artificial Neural Networks[R].Washington D.C.:Trans-portation Research Record,1993:14-19.
[2] 任江涛,欧晓凌,张毅,等.交通状态模式识别研究[J].公路交通科技,2003,20(2):64-67.
[3] 郭伟,姚丹亚,付毅,等.区域交通流特征提取与交通状态评估方法研究[J].公路交通科技,2005,7(22):101-104.
[4] Benjamin A,Coifman R M.Distributed surveillance on freewaysemphasizing incident detection and verification[J].Transporta-tion Research:Part A,2007(41):750-767.
[5] Dipti S,Xin J,Ruey L C.Adaptive neural network models forautomatic incident detection on freeways[J].Neurocomputing,2005(64):473-496.
[6] Wang W,Chen Sh Y,Qu G F.Incident detection algorithmbased on partial least squares regression[J].Transportation Re-search:Part C,2008(16):54-70.
[7] Zadeh L A.Fuzzy sets[J].Information and Control,1965,8(3):338-356.
[8] Gau W L,Buehrer D J.Vague sets[J].IEEE Trans.SystemsMan Cybernetic,1993,23:610-614.
[9] 刘华文.vague集之间的相似度量及其在模式识别中的应用[J].山东大学学报:自然科学版,2004,34(2):110-114.
[10] 周晓光,张强.vague集(值)相似度量的比较和改进[J].系统工程学报,2005,20(6):613-619.
[11] Liu H W.New similarity measures between intuitionistic fuzzysets and between elements[J].Mathematical and computer mod-eling,2005,42:61-70.
[12] Przemyslaw G.Distances between intuitionistic fuzzy sets and/orinterval-valued fuzzy sets based on the hausdor&metric[J].Fuzzy Sets Systems,2004,148:319-328.
[13] Huang W L,Yang M Sh.Similarity measures of intuitionisticfuzzy sets based on Hausdorff distance[J].Pattern RecognitionLetters,2004,25:1603-1611.
[14] 王建宏,李新.基于Vague集的模糊信息融合研究[J].华中科技大学学报:自然科学版,2004,32(8):54-56.
[15] 刘澜,戢晓峰.基于Vague集的道路交通状态决策信息融合[J].公路交通科技,2009,26(5):112-115.