摘要
为描述短时交通量数据中隐藏的非线性与非平稳特性,提高短时交通量的预测精度,进而更好地构建智能交通平台,提出了一种基于时变滤波经验模态分解(TVF-EMD)与最小二乘支持向量机(LSSVM)的混合预测模型,即TVF-EMD-LSSVM模型。其中:TVF-EMD方法主要用来降低数据中暗含的非平稳性对预测结果影响;LSSVM模型是为了描摹数据中包含的非线性信息演化趋势。研究结果表明:相比经验模态分解(EMD)方法而言,TVF-EMD方法的分解结果更加适合交通流预测;该分解技术与LSSVM模型的结合可提供更好的预测结果,相比LSSVM模型而言,其平均绝对误差、平均相对百分比误差、均方根误差和均方根相对误差分别降低了9.186、18.947%、13.591、0.316%,且均等系数提高了0.0821。
In order to describe the hidden non-linear and non-stationary characteristics in the short-time traffic data,improve the prediction accuracy of short-time traffic,and then better build an intelligent transportation platform,a hybrid prediction model based on time-varying filtered empirical modal decomposition(TVF-EMD)and least-squares support vector machine(LSSVM),i.e.,the TVF-EMD-LSSVM model,was proposed.Among the TVF-EMD-LSSVM model,the TVF-EMD method was mainly used to reduce the influence of the non-stationarity implied in the data on the prediction results,while the LSSVM model was designed to trace the evolutionary trend of the non-linear information contained in the data.The research results show that compared with empirical mode decomposition(EMD),the decomposition results of TVF-EMD method are more suitable for traffic flow prediction.Meanwhile,the combination of this decomposition technique and LSSVM model can provide better prediction results.Compared with LSSVM model,the mean absolute error,mean relative percentage error,root mean square error and root mean square relative error of the proposed model are reduced by 9.186,18.947%,13.591 and 0.316%respectively,and its equalization coefficient is increased by 0.0821.
作者
赵磊娜
王延鹏
邵毅明
李淑庆
温欣雨
ZHAO Leina;WANG Yanpeng;SHAO Yiming;LI Shuqing;WEN Xinyu(School of Mathematics and Statistics,Chongqing Jiaotong University,Chongqing 400074,China;School of Traffic and Transportation,Chongqing Jiaotong University,Chongqing 400074,China)
出处
《重庆交通大学学报（自然科学版）》
CAS
CSCD
北大核心
2022年第3期37-44,共8页
Journal of Chongqing Jiaotong University(Natural Science)
基金
国家重点研发计划项目(2018YFB1601000,2018YFB601001)
重庆市自然科学基金项目(cstc2018jcyjAX0288)。
