沈阳农业大学学报Issue(6)：121-125,5.DOI:10.3969/j.issn.1000-1700.2015.06.020
基于人工蜂群改进的BP神经网络移动用户行为分析及预测方法
Improved BP Neural Network Algorithm Based on Artificial Bee Colony of Mobile User Behavior Analysis and Forecasting
摘要
Abstract
It is the mainstream of development technology for current mobile application service to provide accurate and personalized service for mobile users based on different usersˊ behavior. This paper proposes an algorithm to improve BP neural network based on artificial bee colony in order to solve BP neural network algorithm slow convergence and inaccurate prediction. To test the accuracy of the improved algorithm, this paper uses Matlab programming experiment simulation. This paper outputs prediction and the actual user behavior through the black box testing method. Only twice were failed in 18 times forecast and the success rate was more than 80%.In order to validate the efficiency of the improved BP neural network algorithm, this paper tests the convergence by initializing total group number 1000. Results showed that the improved BP neural network algorithm based on artificial colony algorithm could effectively improve the efficiency and accuracy of the mobile user behavior analysis. It is very important to locate userˊs demand to Internet accurately and promote the power of competition in the marketing of enterprises during the process of the construction of analysis model based on the mobile usersˊbehavior.关键词
BP神经网络/人工蜂群/移动用户行为/分析预测/MatlabKey words
BP neural network/artificial bee colony/mobile user behavior/analysis and forecasting/Matlab分类
信息技术与安全科学引用本文复制引用
罗海艳,杨勇,王珏,于海龙..基于人工蜂群改进的BP神经网络移动用户行为分析及预测方法[J].沈阳农业大学学报,2015,(6):121-125,5.基金项目
国家科技支撑计划项目(2012BAJ26B00)；北京农业信息技术研究中心开放课题项目(2013) （2012BAJ26B00）
