计算机应用研究2018，Vol.35Issue(3)：820-824,5.DOI:10.3969/j.issn.1001-3695.2018.03.037
基于处理器时空势场修正的多城市拥堵并行聚类分析
Parallel clustering analysis of multi-city congestion based on multi-processor and space potential field modification
摘要
Abstract
In order to improve the urban traffic congestion detection and control efficiency,this paper proposed a new clustering analysis method based on multi-processor and space potential field modification for traffic congestion analysis.Firstly,based on the city road congestion spatial-temporal model with GIS four-dimensional spatial temporal data,this paper constructed field correction method for multi-processor parallel clustering method by using parallel Euclidean distance matrix computation,parallel neighborhood radius computing and parallel density index calculation.Secondly,it gave the complexity theorems of the parallel computation procedure,so as to theoretically analysis the computational complexity of the algorithm.Finally,taking Beijing city as a test area,it verified the performance of the algorithm in analyzing the traffic congestion.Experimental results show that the method can achieve effective detection for rapid analysis of urban traffic congestion,which can provide data support for traffic congestion management.关键词
势场修正/时空分析/并行聚类/多处理器/交通拥堵Key words
potential field correction/spatial and temporal analysis/parallel clustering/multi-processor/traffic congestion分类
信息技术与安全科学引用本文复制引用
黄杰,余长庚..基于处理器时空势场修正的多城市拥堵并行聚类分析[J].计算机应用研究,2018,35(3):820-824,5.基金项目
国家自然科学基金资助项目(61540055) （61540055）
深圳市富强光学科技有限公司开发项目(YS2015228) （YS2015228）
贺州学院博士科研启动基金资助项目(HZUBS201506) （HZUBS201506）
广西高校中青年教师基础能力提升项目(KY2016YB454) （KY2016YB454）
