基于果蝇算法的空间数据库位置冗余数据查询  

Redundant Data Query of Spatial Database Location Based on Fruit Fly Algorithm

作　　者：姜姗[1] 高远 许玉龙[1] JIANG Shan;GAO Yuan;XU Yu-long(Henan University of Chinese Medicine,Zhengzhou Henan 450046,China)

机构地区：[1]河南中医药大学,河南郑州450046

出　　处：《计算机仿真》2022年第8期437-440,481,共5页Computer Simulation

基　　金：2022年河南省软科学研究项目(222400410603)。

摘　　要：针对当前方法对空间数据库位置冗余数据进行查询时,未考虑冗余数据查询最优解,导致冗余数据查询时间消耗率和空间占用率较高,冗余数据查询效率较低的问题,提出基于果蝇算法的空间数据库位置冗余数据查询方法。采用BP神经网络模型,估计空间数据库中的缺失数据,填补空间数据库中的缺失值。利用粒子群优化算法,挖掘和分类空间数据库中的冗余数据,减少训练样本数目,提高训练速度,得到粒子最优位置。基于果蝇算法对分类后的冗余数据进行搜索,获取冗余数据查询最优解,实现空间数据库位置冗余数据查询。实验结果表明,所提方法的冗余数据查询时间消耗率和空间占用率较低,能够有效提高冗余数据查询效率。Currently,some methods ignore the optimal solution of redundant data query,leading to high time consumption rate and space occupation rate of redundant data query,and low efficiency of redundant data query.Therefore,a method to query the redundant data of spatial database location based on the fruit fly algorithm was proposed.Firstly,BP neural network model was used to estimate the missing data in the spatial database and fill the missing values in the spatial database.Secondly,the particle swarm optimization algorithm was adopted to mine and classify the redundant data in the spatial database,reduce the number of training samples and improve the training speed,thus getting the optimal position of particles.Based on the fruit fly algorithm,the redundant data after classification was searched,and then the optimal solution of redundant data query was obtained.Finally,the redundant data query of spatial database location was achieved.Experimental results prove that the time consumption and space occupation rate of the proposed method are lower than before,so this method can effectively improve the redundant data query efficiency.

关 键 词：果蝇算法 空间数据库 冗余数据 粒子群优化算法 

分 类 号：TP957.52[自动化与计算机技术]