模型优选及融合的高教园区出行生成预测方法.pdfVIP

第10 卷 第1 期 交 通 运 输 工 程 学 报 Vol1 10 No1 1 2010 年2 月 Journal of Traffic and T ransportation Engineering Feb. 2010 : 16 1-163 ( 2010) 01-0066- 06 1 2 2 张文峰 , 张小花, 曾 涛 ( 11 , 100 2; 21 , 510225) : 为了提高高教园区出行生成 测数据的可靠性, 提出了一种基于模型优选及融合的出行生 成 测方法根据选取的模型评价指标, 借助ELECTRE 方法对区域出行产生模型进行优选, 利 用证据理论方法, 对优选模型的权重进行标定, 最后借助标定后的权重对区域交通生成量进行数据 融合 测, 并与实际结果进行了对比分析结果表明: 多模型融合 测相对误差在 10% 以下, 测 结果与实际情况非常接近, 该 测方法有效 : 交通 测; 模型优选; D-S 证据理论; 模型融合; 出行生成 测 : U 491. 14 : A Forecasting method of trip generation for higher education zone based on model selection and integration 1 2 2 ZHANG Wen-feng , ZHAN G Xiao-hua , ZEN G Tao ( 1. School of Automation, Northw est ern Polyt echnical University , Xipan 100 2, Shaanxi, China; 2. School of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, Guangdong, China) Abstract: T o improve the forecasting data reliability of trip generation for higher education zone, a forecasting method of trip generation w as presented based on model selection and model integration. According to the modelps evaluation indices, the trip generation models of zone w ere optimally selected by using ELECT RE method. T he w eights of optimal selected models w ere demarcated by using D-S evidence theory. Based on the w eights, the trip generation of higher education zone w as forecasted by using data fusion, and the forecasting result w as contrasted with actual result. Analysis result ind