大型物联网电子设备的海量数据高效挖掘方法研究
|
摘要
当前对大型物联网电子设备数据采用状态模式识别的数据挖掘方式,对具有差异性特征的电子设备数据挖掘无法分类识别,性能不好。在此提出一种基于关联度主特征量提取的大型物联网电子设备的海量数据高效挖掘方法,首先分析了大型物联网中电子设备的数据采集模型,通过对电子设备的原始数据采集,提取电子设备数据信息的关联度主特征量,采用海量数据挖掘最优控制算法实现对大型物联网中的电子设备海量数据的分类挖掘和特征提取。仿真结果表明,采用该算法进行数据挖掘,电子数据的数据差异性特征幅度平稳,数据的关联度区分明显,具有较好的分类识别和数据检测能力且系统运行效率提高。
The current data mining mode of state pattern recognition is used for the electronic equipment data of large-scale IOT,which can not be classified and identified,and the good performance can not be caught. An efficient data mining method for electronic devices in large-scale IOT based on the main feature extraction of association degree is proposed. The data acquirng model of the electronic equipments in large-scale internet of things is analyzed,The main features of association degree of the electronic equipments are extracted by collecting the original data of the electronic equipments. The optimal control algorithm of massive data mining is adopted to realize classification mining and feature extraction of electronic equipment massive data in large-scale IOT. The simulation results show that this algorithm has excellent ability of classification,identification and feature extraction,and the system operation efficiency is improved.
The current data mining mode of state pattern recognition is used for the electronic equipment data of large-scale IOT,which can not be classified and identified,and the good performance can not be caught. An efficient data mining method for electronic devices in large-scale IOT based on the main feature extraction of association degree is proposed. The data acquirng model of the electronic equipments in large-scale internet of things is analyzed,The main features of association degree of the electronic equipments are extracted by collecting the original data of the electronic equipments. The optimal control algorithm of massive data mining is adopted to realize classification mining and feature extraction of electronic equipment massive data in large-scale IOT. The simulation results show that this algorithm has excellent ability of classification,identification and feature extraction,and the system operation efficiency is improved.
引文
[1]陈志,骆平,岳文静,等.一种能量感知的无线传感网拓扑控制算法[J].传感技术学报,2013,26(3):382-387.
[2]王辛果,张信明,陈国良.时延受限且能量高效的无线传感网络跨层路由[J].软件学报,2011,22(7):1626-1640.
[3]欧世峰,高颖,赵晓晖.自适应组合型盲源分离算法及其优化方案[J].电子与信息学报,2011,33(5):1243-1247.
[4]蔡昕烨,牛耘,黄志球,等.一种用于基因调控网络建模的CGP-WPSO混合算法[J].计算机科学,2012,39(9):180-182.
[5]邓异,梁燕,周勇.水声换能器基阵信号采集系统优化设计[J].物联网技术,2015,5(4):36-37.
[6]石鑫,周勇,甘新年,等.机载多源飞行数据资料的非线性检验[J].计算机与数字工程,2013,41(5):729-732.
[7]刘昊晨,梁红.线性调频信号参数估计和仿真研究[J].计算机仿真,2011,28(2):157-159.
[8]罗龙,虞红芳,罗寿西.基于多拓扑路由的无拥塞快速业务迁移算法[J].计算机应用,2015,35(7):1809-1814.
[9]孙超,杨春曦,范莎,等.能量高效的无线传感器网络分布式分簇一致性滤波算法[J].信息与控制,2015,44(3):379-384.
[10]文天柱,许爱强,程恭.基于改进ENN2聚类算法的多故障诊断方法[J].控制与决策,2015,30(6):1021-1026.
[2]王辛果,张信明,陈国良.时延受限且能量高效的无线传感网络跨层路由[J].软件学报,2011,22(7):1626-1640.
[3]欧世峰,高颖,赵晓晖.自适应组合型盲源分离算法及其优化方案[J].电子与信息学报,2011,33(5):1243-1247.
[4]蔡昕烨,牛耘,黄志球,等.一种用于基因调控网络建模的CGP-WPSO混合算法[J].计算机科学,2012,39(9):180-182.
[5]邓异,梁燕,周勇.水声换能器基阵信号采集系统优化设计[J].物联网技术,2015,5(4):36-37.
[6]石鑫,周勇,甘新年,等.机载多源飞行数据资料的非线性检验[J].计算机与数字工程,2013,41(5):729-732.
[7]刘昊晨,梁红.线性调频信号参数估计和仿真研究[J].计算机仿真,2011,28(2):157-159.
[8]罗龙,虞红芳,罗寿西.基于多拓扑路由的无拥塞快速业务迁移算法[J].计算机应用,2015,35(7):1809-1814.
[9]孙超,杨春曦,范莎,等.能量高效的无线传感器网络分布式分簇一致性滤波算法[J].信息与控制,2015,44(3):379-384.
[10]文天柱,许爱强,程恭.基于改进ENN2聚类算法的多故障诊断方法[J].控制与决策,2015,30(6):1021-1026.