摘要
基于高速公路交易数据,选取10项表征用户个体特征和出行时空特征的指标构建用户特征模型。采用K-means、模糊C-means以及自组织映射算法对用户特征进行分类,并应用于某路段的ETC数据。研究结果表明,相比于K-means和模糊C-means,SOM模型在用户出行模式分类上具有更优效果;将高速公路出行用户划分为六类具有合理性。基于分类结果,针对性提出了个性化差异收费策略,并通过数值仿真验证了策略的合理性。
Highway transaction data were utilized to select 10 indicators representing user-specific characteristics and the spatiotemporal features of travel,forming the basis for constructing a user characteristic model.To classify highway user characteristics,the K-means,fuzzy C-means,and selforganizing map algorithms were applied to ETC data from a specific road segment.The results indicate that,compared to K-means and fuzzy C-means,the SOM model performs better in classifying user travel patterns and supports the reasonable classification of highway users into six categories.Based on these classification results,a personalized differential tolling strategy is proposed,and its feasibility is validated through numerical simulation.
作者
吕能超
董新雨
罗如意
曾岳凯
徐达
周新聪
LV Nengchao;DONG Xinyu;LUO Ruyi;ZENG Yuekai;XU Da;ZHOU Xincong(Intelligent Transport Systems Research Center,Wuhan University of Technology,Wuhan 430063,China;School of Transportation and Logistics Engineering,Wuhan University of Technology,Wuhan 430063,China;State Key Laboratory of Maritime Technology and Safety,Wuhan 430063,China;Hubei Communications Investment Technology Development Company Limited,Wuhan 430034,China;CCSHCC Traffic Engineering Company Limited,Wuhan 430050,China)
出处
《中山大学学报(自然科学版)(中英文)》
北大核心
2025年第3期129-138,共10页
Acta Scientiarum Naturalium Universitatis Sunyatseni
基金
国家重点研发计划(2023YFB4302600)
国家自然科学基金(52472366,52072290)
湖北省重点研发计划(2024BAB051)。
关键词
ETC数据
聚类算法
出行模式分析
差异化收费
ETC data
clustering algorithm
travel mode analysis
differentiated charges
