基于改进K-means算法的通勤交通小区识别

Commuting Traffic Analysis Zone Recognition Using Improved K-means Algorithm

通勤是具有周期性和稳定性的城市居民出行行为,是城市发展规划和公共交通管理的重要研究内容。出租车GPS(Global Position System,全球定位系统)轨迹数据在一定程度上反映了城市交通状况和市民出行模式。针对出租车区域性通勤模式识别问题,本文提出一种基于改进K-means算法的通勤交通小区识别方法。该方法主要包括3个步骤:划分交通小区、生成交通小区之间的流量转移矩阵和识别通勤交通小区对。参考现有的交通小区划分方法,本文提出一种基于细粒度单元的自下而上的交通小区划分方法。在通勤交通小区对识别模型中,以高峰时段的流量及其离散系数作为输入特征,基于改进K-means算法识别通勤交通小区对。最后,基于重庆市出租车GPS数据集进行实验验证,结果表明该方法效果显著。

Commuting is a periodical and stable travel behavior of urban residents,which is an important research content of ur⁃ban development planning and public transportation management.Taxi GPS trajectory data reflects urban traffic conditions and citizens’travel patterns to a certain extent.Aiming at the problem of taxi regional commuting pattern recognition,a commuting traffic analysis zone recognition method based on improved K-means algorithm is proposed.This method mainly includes three steps:dividing traffic analysis zones,generating flow transfer matrix between traffic analysis zones,and identifying commuting traffic analysis zone pairs.Referring to the existing traffic analysis zones division methods,a bottom-up division method based on fine-grained elements is proposed.In the recognition model of commuting traffic analysis zone pairs,the traffic flow and its dis⁃persion coefficient during peak hours are taken as input features,and the commuting traffic analysis zone pairs are identified based on the improved K-means algorithm.Finally,an experimental verification is carried out based on the Chongqing taxi GPS data set,and the experimental results show that the method is effective.