基于FART神经网络的高速公路交通事件检测法*

作者：董颖颖,杨旭华,王万良 日期：2009-02-23/span> 浏览：3350 查看PDF文档

基于FART神经网络的高速公路交通事件检测法*

董颖颖,杨旭华,王万良
（浙江工业大学 信息工程学院，浙江 杭州 310014）

摘要：突发性交通事件是造成高速公路交通拥堵的主要原因， 为了快速并准确地检测交通事件，有效提高高速公路的利用率和通行能力，将一种模糊论与自适应谐振神经网络相结合的聚类算法—Fuzzy ART神经网络算法用于检测高速公路交通事件。根据高速公路事件检测相关参数之间的关系，选用了交通流密度残差和平均速度残差的组合向量作为神经网络的输入，给出了事件检测的算法步骤和输出判断方法，并进行了仿真实验。仿真结果表明，该算法不仅能够检测出交通事件的发生及其造成的拥堵程度，还可以快速识别已有的交通事件类型，记忆未知的交通事件类型，实现边工作、边学习，且检测结果具有较高的稳定性和准确性。
关键词：模糊ART；神经网络；交通事件；检测
中图分类号：TP183;U491文献标识码：A文章编号：1001-4551(2009)01-0012-05

Highway traffic incident detection method based on FART neural network
DONG Ying-ying，YANG Xu-hua，WANG Wan-liang
（College of Information Engineering，Zhejiang University of Technology，Hangzhou 310014，China）
Abstract: Unexpected traffic incident is the main cause of highway traffic congestion, so detection traffic incidents quickly and accurately can effectively improve the utilization and capacity of highway. A clustering algorithm combined adaptive resonance theory with fuzzy theory—Fuzzy ART neural network algorithm was used to detect highway traffic incidents. According to the relations of detection parameters, the vectors of traffic density differences and average speed differences were selected as network’s input. At the same time, the detection steps and how to judge the output of the network were described. The results of simulations show that, the algorithm can detect occurring and the congestion degree of traffic incidents, and also can quickly identify learned types and store the unlearned types. The neural network(NN) combines work and study,so the results of detection have higer stablility and accuration.
Key words: fuzzy ART(FART); neural network(NN); traffic incident; detection
参考文献(References):
［1］艾小松,黄挚雄，张良春，等.基于Adaboost算法的高速公路事件检测［J］计算机工程与科学,2007,29(12):95-97.
［2］荆便顺.道路交通控制工程［M］.北京：人民交通出版社,1995.
［3］HAGAN M T, DEMUTH H B, BEALE M H. Neural Network Design ［M］. Beijing:China Machine Press,2002.
［4］商同,季立明.模糊ART神经网络的特性分析［C］//2000全国设备诊断技术学术交流会论文集，北京:［s.n.］,2000:226-228.
［5］潘紫微,吴超英.一种应用于故障识别的模糊ART神经网络［J］.机械科学与技术,2002,21(1):134-136.
［6］高翔，于枫，王敏.FART在非监督式网络异常检测中的应用［J］.计算机工程与应用,2006,24(27):144-146.
［7］CARPENTER G A, GROSSBERG S. ART2: Self-organization of stable category recognition codes for analog input patterns ［J］.APPLIED OPTICS,1987,26(23):4919-4930.
［8］王宏山,杨军,俞梦孙,等.模糊ART神经网络在心律失常分析中的应用［J］.中国生物医学工程学报,2004,23(5):410-413.
［9］史忠科,黄辉先.交通控制系统导论［M］.北京:科学出版社,2003.
［10］杨旭华,孙优贤.一种基于ART2神经网络的高速公路交通事件自动检测算法［J］.公路,2005(8):114-117.
［11］CARPENTER G A, GROSSBERG S, ROSEN D B. Fuzzy ART: an Adaptive Resonance Algorithm for Rapid, Stable Classification of Analog Patterns ［C］ // Seattle International Joint Conference,1991:411-416.