基于数据挖掘的图书馆借阅量预测研究  

Research on Library Borrowing Volume Prediction Based on Data Mining

作　　者：邓敏[1] 卢宁[2] DENG Min;LU Ning(LibraryGuangdong Polytechnic of Science and Technology,Zhuhai 519000,China;Computer Engineering Technical College(Artificial Intelligence College),Guangdong Polytechnic of Science and Technology,Zhuhai 519000,China)

机构地区：[1]广东科学技术职业学院图书馆,广东珠海519000 [2]广东科学技术职业学院计算机工程技术学院(人工智能学院),广东珠海519000

出　　处：《微型电脑应用》2023年第11期221-224,共4页Microcomputer Applications

摘　　要：图书馆借阅量受多种因素影响,导致传统基于线性回归和灰色理论的预测方法预测精度较低。针对该问题,引入数据挖掘理论和方法,提出一种基于因子分析(FA)模型联合粒子群(PSO)优化BP神经网络的图书馆借阅量预测模型。利用FA对借阅量原始数据进行建模分析,确定与借阅量密切相关的公共因子,将公共因子作为BP神经网络模型的输入神经元,进而建立预测模型实现对未来借阅量的预测,同时针对BP神经网络模型初始参数设置难题,提出改进的粒子群算法进行全局寻优,提升预测精度。仿真实现表明,所提模型相对于对比方法预测精度更高,整体预测性能更加优越。Library borrowing volume is affected by many factors.These features result in the low prediction accuracy of traditional prediction methods which are based on linear regression and grey theory.To solve this problem,this paper introduces the theory and method of data mining,and proposes a prediction model of library borrowing volume based on factor analysis(FA)model,particle swarm optimization(PSO),and BP neural network.FA is used to model and analyze the original data of borrowing volume,and the main common factors closely related to borrowing volume are determined.The main common factors are taken as the input of the BP neural network model,and then the prediction model is established to predict the future borrowing volume.At the same time,to solve the problem of initial parameter setting of BP neural network model,an improved particle swarm optimization algorithm is proposed for global optimization to improve the prediction accuracy.Simulation results show that the proposed model has higher prediction accuracy and better overall prediction performance than the comparison method.

关 键 词：图书管理系统 借阅量 数据挖掘 因子分析 预测模型 

分 类 号：TN911.1-34[电子电信—通信与信息系统] TP391[电子电信—信息与通信工程]