摘要
提出一种基于LVQ神经网络的交通事件检测方法。提取上下游的流量和占有率为特征,LVQ神经网络作为分类器进行交通事件自动检测。LVQ网络结构简单,但却表现出比BP神经网络更强的有效性和鲁棒性。为进一步提高神经网络的泛化能力,采用改进的Boosting算法,进行网络集成。运用Matlab进行了仿真分析,结果表明提出的交通事件检测算法具有良好的检测性能。
A novel method is proposed for traffic incidents detection based on LVQ neural network.The features of flow and occupancy rate are extracted from traffic incidents.Then LVQ neural network is used to classify the traffic incidents.LVQ has a simple network structure, but it is very effective and robust in traffic incidents detection.In order to improve the precision of the LVQ neural network for traffic incidents detection,Boosting algorithm is used to build an integration-neural network.Finally the simulation with Matlah shows the algorithm can get better performance.
出处
《计算机工程与应用》
CSCD
北大核心
2008年第34期213-215,218,共4页
Computer Engineering and Applications
基金
浙江省科技厅项目(No.2005F11008
No.2003F11006)
