当前位置>主页 > 期刊在线 > 计算机技术 >

计算机技术22年6期

基于 EEMD-SSA-LSSVR 的短期交通流预测
李俊,胡婷
( 重庆工商大学 工商管理学院,重庆 400067)

摘  要:为了提高物流的配送效率,寻求合理的配送路径,通过分析短期历史交通流量,使用集合经验模态分解去噪,以拟合优度最大化为目标,运用麻雀搜索算法优化惩罚参数和核函数参数的最小二乘支持向量机回归预测短期交通流。结果表明集合经验模态分解能有效去除短期交通流中的噪声,构建的 EEMD-SSA-LSSVR 模型可以高效地预测短期交通流量。


关键词:麻雀搜索算法;集合经验模态分解;短时交通流预测;最小二乘支持向量机回归



DOI:10.19850/j.cnki.2096-4706.2022.06.023


基金项目:重庆工商大学研究生创新型科研项目 (yjscxx2021-112-14、yjscxx2021-112-15)


中图分类号:TP18                                        文献标识码:A                                      文章编号:2096-4706(2022)06-0093-04


Short Term Traffic Flow Prediction Based on EEMD-SSA-LSSVR

LI Jun, HU Ting

(School of Business Administration, Chongqing Technology and Business University, Chongqing 400067, China)

Abstract: To improve the distribution efficiency of logistics and find the reasonable distribution route, the ensemble empirical mode is used to decompose noise signals by analyzing the short-term historical traffic flow. Aiming at maximizing the goodness of fit, the sparrow search algorithm is used to optimize the least squares support vector machine regression of penalty parameters and kernel function parameters to predict the short-term traffic flow. The results show that the ensemble empirical mode decomposition can effectively remove the noise in the short-term traffic flow, and the constructed EEMD-SSA-LSSVR model can effectively predict the short-term traffic flow.

Keywords: SSA; EEMD; short term traffic flow prediction;


参考文献:

[1] WU Z H, HUANG N E. ENSEMBLE EMPIRICAL MO DEDECOMPOSITION:ANOISE-ASSISTED DATA ANALYSIS METHOD [J].Advances in Adaptive Data Analysis,2009,1(1):1-44.

[2] SUYKENS J A,VANDEWALLE J,MOOR B D. Optimal control by least squares support vector machines [J].Neural Networks, 2001,14(1):23-35.

[3] XUE J K,SHEN B. A novel swarm intelligence optimization approach:sparrow search algorithm [J].Systems Science & Control Engineering,2020,8(1):23-24.

[4] 曹成涛,徐建闽 . 基于 PSO-SVM 的短期交通流预测方法[J]. 计算机工程与应用,2007(15):12-14.

[5] ZHANG Q Y,QIAN H,CHEN Y P, et al. A short-term traffic forecasting model based on echo state network optimized by improved fruit fly optimization algorithm [J].Neurocomputing,2020,416:117-124.


作者简介:李俊 (1998—),男,汉族,江西九江人,中级物流师,硕士研究生,研究方向:智能算法;胡婷 (1996—),女,汉族,四川遂宁人,硕士研究生在读,研究方向:智能算法。