Research on null-value estimation algorithm based on predicted value

Author(s):  
Cuncun Qi
Author(s):  
Yuxiang Cai

Multi source fusion of data collected by various sensors to realize accurate perception is the key basic technology of the Internet of things. At present, there are many problems in the fusion of various kinds of data collected by sensors, such as more noise and more null values. In this paper, the fuzzy neural network algorithm is proposed to establish the model, combined with the Delphi method and the null value estimation method based on the prediction value to construct the data fusion system. This method has rich application scenarios in the construction of IOT system in the field of power and energy.


Proceedings ◽  
2018 ◽  
Vol 2 (11) ◽  
pp. 698 ◽  
Author(s):  
Klemen Kenda ◽  
Filip Koprivec ◽  
Dunja Mladenić

In this study an algorithm for missing data imputation is presented. The algorithm uses measurements from neighboring sensors to estimate the missing values. Data-driven approach is used and methodology chooses the optimal available combination of modeling algorithm and available measurements to produce an estimate from the model with lowest error. The methodology was tested on Ljubljana polje aquifer data and has produced close to perfect results.


2014 ◽  
Vol E97.C (4) ◽  
pp. 308-315 ◽  
Author(s):  
Rompei SUGAWARA ◽  
Hao SAN ◽  
Kazuyuki AIHARA ◽  
Masao HOTTA

Sign in / Sign up

Export Citation Format

Share Document