二维局部非负矩阵分解的路网态势算法

Evaluation of Network-Level Traffic State Using 2D-LNMF Algorithm

针对路网态势评测算法存在限于断面、依赖单一指标等的不足,在解析测量指标和测量断面的相关性及局部非负矩阵分解(LNMF)算法的基础上,提出了二维局部非负矩阵分解2DLNMF算法,通过选择合适参数对路网数据进行降维处理,提取路网特征数据,从而实现路网态势评测.仿真结果表明,使用2D-LNMF算法路网态势评测结果更加准确,而在线评测准确性达到95.69%.

Network-level traffic state reflects the macroscopical conditions of the road network.The exesting evaluation algorithms have some shortcomings such as their applicable conditions are limited to section and they just depend on a single index.As a result,based on the analysis of the correlation between the measuring index and sections and the local non-negative matrix factorization（LNMF）algorithm,the algorithm of 2D-LNMF was proposed and the features of the traffic data were extracted by choosing appropriate parameters to reduce the numbers of dimensions of the road network data.The simulation results indicate that the evaluation of 2D-LNMF is more accurate and its online accuracy is up to 95.69%.