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...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-08-01
|
Series: | Proceedings |
Subjects: | |
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 |