基于压缩感知的航空货运量模型研究  

Compressed Sensing Model of Air Cargo Volume

作　　者：游庆山[1,2] 徐海文[1] 雷开洪[1] 王丽[1] 

机构地区：[1]中国民用航空飞行学院计算机学院,四川广汉618307 [2]电子科技大学电子工程学院,四川成都611731

出　　处：《四川师范大学学报（自然科学版）》2014年第3期402-407,共6页Journal of Sichuan Normal University（Natural Science）

基　　金：国家自然科学基金民航联合基金(U1233105)资助项目

摘　　要：最近十几年，压缩感知（CS）理论得到快速发展，并广泛应用于图像重建、信道估计以及谱估计等不同领域．主要研究压缩感知理论在我国航空货运量建模中的应用，以1991～2006年我国航空货运量的统计数据为基础，利用压缩感知理论对我国航空货运量建模，并通过正交匹配追踪（OMP）算法得到我国航空货运量的压缩感知模型．通过拟合误差指标的比较可知，基于压缩感知理论的航空货运量模型具有模型相对比较简洁，拟合精度高于基于灰色GM（1，1）以及基于回归分析法的航空货运量模型等优点．实验证明，此方法可应用于短期内我国航空货运量的预测，为航空货运市场调控提供有效理论依据．Recently, much attention has been drawn to the problem of recovering a sparse solution from a small set of linear measurements, which can be found in many different fields, such as image processing, channel estimation, spectrum estimation. In this paper, we mainly studied the application of compressed sensing in the field of air cargo volume. According to air cargo volume statistical data in China from the year 1991 to 2006, an air cargo volume combination forecasting model was established by the orthogonal matching pursuit, based on compressed sensing. The test result showed that this model was more suitable than GM （ 1,1 ） model and regression analysis model. Compressed sensing model of air cargo volume can be used to forecast short-term aeronautic cargo capacity, and even can provide some effective theory evidence to supervise the native aeronautic cargo market.

关 键 词：压缩感知 航空货运量预测 灰色GM(1 1) 回归分析法 诱导有序几何加权平均 

分 类 号：F562[经济管理—产业经济]