Optimal Missing Value Estimation Algorithm for Groundwater Levels

Optimal Missing Value Estimation Algorithm for Groundwater Levels

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 pro...

Full description

Bibliographic Details
Main Authors: Klemen Kenda, Filip Koprivec, Dunja Mladenić
Format: Article
Language:English
Published: MDPI AG 2018-08-01
Series:Proceedings
Subjects:
missing values
data cleaning
data fusion
sensor fusion
machine learning
ensembles
Online Access:http://www.mdpi.com/2504-3900/2/11/698
id doaj-f9fb66010c494d77836c38ecf6eb01e7
record_format Article
spelling doaj-f9fb66010c494d77836c38ecf6eb01e72020-11-24T21:38:16ZengMDPI AGProceedings2504-39002018-08-0121169810.3390/proceedings2110698proceedings2110698Optimal Missing Value Estimation Algorithm for Groundwater LevelsKlemen Kenda0Filip Koprivec1Dunja Mladenić2Artificial Intelligence Laboratory, Jožef Stefan Institute, Ljubljana 1000, SloveniaArtificial Intelligence Laboratory, Jožef Stefan Institute, Ljubljana 1000, SloveniaArtificial Intelligence Laboratory, Jožef Stefan Institute, Ljubljana 1000, SloveniaIn 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.http://www.mdpi.com/2504-3900/2/11/698missing valuesdata cleaningdata fusionsensor fusionmachine learningensembles
collection DOAJ
language English
format Article
sources DOAJ
author Klemen Kenda
Filip Koprivec
Dunja Mladenić
spellingShingle Klemen Kenda
Filip Koprivec
Dunja Mladenić
Optimal Missing Value Estimation Algorithm for Groundwater Levels
Proceedings
missing values
data cleaning
data fusion
sensor fusion
machine learning
ensembles
author_facet Klemen Kenda
Filip Koprivec
Dunja Mladenić
author_sort Klemen Kenda
title Optimal Missing Value Estimation Algorithm for Groundwater Levels
title_short Optimal Missing Value Estimation Algorithm for Groundwater Levels
title_full Optimal Missing Value Estimation Algorithm for Groundwater Levels
title_fullStr Optimal Missing Value Estimation Algorithm for Groundwater Levels
title_full_unstemmed Optimal Missing Value Estimation Algorithm for Groundwater Levels
title_sort optimal missing value estimation algorithm for groundwater levels
publisher MDPI AG
series Proceedings
issn 2504-3900
publishDate 2018-08-01
description 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.
topic missing values
data cleaning
data fusion
sensor fusion
machine learning
ensembles
url http://www.mdpi.com/2504-3900/2/11/698
work_keys_str_mv AT klemenkenda optimalmissingvalueestimationalgorithmforgroundwaterlevels
AT filipkoprivec optimalmissingvalueestimationalgorithmforgroundwaterlevels
AT dunjamladenic optimalmissingvalueestimationalgorithmforgroundwaterlevels
_version_ 1725935106911109120

Similar Items