摘要
环境监测的无线传感器网络中存在大量监测数据,有效地挖掘数据之间的相关性,可以缩短分析时间,提高分析精度。本文首先介绍了协方差概念和相关性的计算方法;其次,分析了时间序列数据的相关性和多变量的互相关性;最后,对某地的环境监测数据进行了相关性分析。分析结果证明:PM2.5与空气质量指数存在高度相关性;PM2.5与时间无相关性;日照与臭氧含量高度相关。
There are a lot of data in wireless sensor networks for environmental monitoring.If we mine the correlation between these data,we can save analysis time and improve the analysis accuracy.In this paper,we first introduce the concept of the covariance and calculation method of the correlation and analyze the correlation of time series data and multivariable.Then the correlation of environmental monitoring data of a city is analyzed.The analysis results show that there is a high correlation between PM2.5 and the air quality index.The correlation of PM2.5 is independent of time.The multivariate correlation analysis indicates that sunshine is highly correlated with ozone content.
作者
罗宇
李颖
郝昕宇
杨光松
LUO Yu;LI Ying;HAO Xinyu;YANG Guangsong(Radio Transmitting Station 645#of Guizhou Radio and Television Bureau,Guiyang 550200,China;Chengyi Colledge,Jimei University,Xiamen Fujian 361021,China;School of Information Engineering,Jimei University,Xiamen Fujian 361021,China)
出处
《智能计算机与应用》
2022年第2期49-53,共5页
Intelligent Computer and Applications
基金
福建省中青年教师教育科研项目(JT180877)
福建省自然科学基金(2021J01865)
关键词
相关性
时间序列
协方差
互相关
relevance
time series
covariance
cross correlation
