Monitoring and modelling of water quality parameters using artificial intelligence
Rapid population growth leads to an increase in demand for water and spikes levels of water pollution. In this study, a low cost and innovative internet of things (IoT) device was used in the monitoring of water quality parameters. The monitoring system implemented used consists of maker-UNO as the...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Published: |
Inderscience Publishers
2024
|
Subjects: | |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.uniten.dspace-34573 |
---|---|
record_format |
dspace |
spelling |
my.uniten.dspace-345732024-10-14T11:20:46Z Monitoring and modelling of water quality parameters using artificial intelligence Omar D.P.M.A. Hayder G. Hung Y.-T. 58313272000 56239664100 7201351881 artificial intelligence monitoring prediction model water quality Bioremediation Forecasting Global system for mobile communications Internet of things Neural networks Population statistics Redox reactions Support vector machines Water pollution Low-costs Model of water quality Monitoring system Oxidation-reduction potentials Prediction modelling Rapid population growth Solid oxidation Total dissolved solids Treatment systems Water quality parameters Water quality Rapid population growth leads to an increase in demand for water and spikes levels of water pollution. In this study, a low cost and innovative internet of things (IoT) device was used in the monitoring of water quality parameters. The monitoring system implemented used consists of maker-UNO as the core controller, SIM7600-GSM module as the Wi-Fi module and the water quality parameters sensors (total dissolved solids (TDS), oxidation reduction potential (ORP), temperature and turbidity). This study applied five different artificial intelligence (AI) techniques models to predict the water quality parameters. The data were collected from phytoremediation treatment system and modelled by using artificial neural network (ANN), regression trees, support vector machine (SVM), ensemble trees and the Gaussian process regression (GPR). A satisfying prediction models were achieved indicating that early prevention of contamination in the treatment system can be achieved through the application of monitoring and artificial intelligence modelling tools. Copyright � 2023 Inderscience Enterprises Ltd. Final 2024-10-14T03:20:46Z 2024-10-14T03:20:46Z 2023 Article 10.1504/IJEWM.2023.131153 2-s2.0-85161866294 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85161866294&doi=10.1504%2fIJEWM.2023.131153&partnerID=40&md5=66d0a8783982c9400a19f2c01567d34f https://irepository.uniten.edu.my/handle/123456789/34573 31 4 525 533 Inderscience Publishers Scopus |
institution |
Universiti Tenaga Nasional |
building |
UNITEN Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Tenaga Nasional |
content_source |
UNITEN Institutional Repository |
url_provider |
http://dspace.uniten.edu.my/ |
topic |
artificial intelligence monitoring prediction model water quality Bioremediation Forecasting Global system for mobile communications Internet of things Neural networks Population statistics Redox reactions Support vector machines Water pollution Low-costs Model of water quality Monitoring system Oxidation-reduction potentials Prediction modelling Rapid population growth Solid oxidation Total dissolved solids Treatment systems Water quality parameters Water quality |
spellingShingle |
artificial intelligence monitoring prediction model water quality Bioremediation Forecasting Global system for mobile communications Internet of things Neural networks Population statistics Redox reactions Support vector machines Water pollution Low-costs Model of water quality Monitoring system Oxidation-reduction potentials Prediction modelling Rapid population growth Solid oxidation Total dissolved solids Treatment systems Water quality parameters Water quality Omar D.P.M.A. Hayder G. Hung Y.-T. Monitoring and modelling of water quality parameters using artificial intelligence |
description |
Rapid population growth leads to an increase in demand for water and spikes levels of water pollution. In this study, a low cost and innovative internet of things (IoT) device was used in the monitoring of water quality parameters. The monitoring system implemented used consists of maker-UNO as the core controller, SIM7600-GSM module as the Wi-Fi module and the water quality parameters sensors (total dissolved solids (TDS), oxidation reduction potential (ORP), temperature and turbidity). This study applied five different artificial intelligence (AI) techniques models to predict the water quality parameters. The data were collected from phytoremediation treatment system and modelled by using artificial neural network (ANN), regression trees, support vector machine (SVM), ensemble trees and the Gaussian process regression (GPR). A satisfying prediction models were achieved indicating that early prevention of contamination in the treatment system can be achieved through the application of monitoring and artificial intelligence modelling tools. Copyright � 2023 Inderscience Enterprises Ltd. |
author2 |
58313272000 |
author_facet |
58313272000 Omar D.P.M.A. Hayder G. Hung Y.-T. |
format |
Article |
author |
Omar D.P.M.A. Hayder G. Hung Y.-T. |
author_sort |
Omar D.P.M.A. |
title |
Monitoring and modelling of water quality parameters using artificial intelligence |
title_short |
Monitoring and modelling of water quality parameters using artificial intelligence |
title_full |
Monitoring and modelling of water quality parameters using artificial intelligence |
title_fullStr |
Monitoring and modelling of water quality parameters using artificial intelligence |
title_full_unstemmed |
Monitoring and modelling of water quality parameters using artificial intelligence |
title_sort |
monitoring and modelling of water quality parameters using artificial intelligence |
publisher |
Inderscience Publishers |
publishDate |
2024 |
_version_ |
1814061127987888128 |
score |
13.209306 |