Context Quality Impact in Context-Aware Data Mining for Predicting Soil Moisture

Nowadays research has shown that including context-awareness, in a classic data mining (CDM) process can improve the overall results. The current work investigates the impact of context completeness and accuracy over predictive forecasting for soil moisture in a context-aware data mining (CADM) syst...

Full description

Saved in:
Bibliographic Details
Published in:Cybernetics and systems 2020-10, Vol.51 (7), p.668-684
Main Authors: Avram, Anca, Matei, Oliviu, Pintea, Camelia-M., Pop, Petrica C.
Format: Article
Language:English
Subjects:
62-07,68T05
Context-aware data mining
data context quality
machine learning
soil moisture predictions
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Nowadays research has shown that including context-awareness, in a classic data mining (CDM) process can improve the overall results. The current work investigates the impact of context completeness and accuracy over predictive forecasting for soil moisture in a context-aware data mining (CADM) system. Experiments with different levels of noise and missing data in the context were performed using several machine learning algorithms for both CDM and CADM scenarios. The results show that the soil moisture prediction results are improved when using CADM, even if the quality standards are not completely met.
ISSN:0196-9722
1087-6553
DOI:10.1080/01969722.2020.1798642