A comparison between neural network based and fuzzy logic models for chlorophll-a estimation

This paper describes the application of two novel computational methods such as fuzzy logic and supervised artificial neural network (ANN) to model algal biomass in tropical Putrajaya Lake and Wetlands (Malaysia). Limnological time series data collected from 2001 until 2004 was utilized using input...

Full description

Saved in:
Bibliographic Details
Main Authors: Malek S., Salleh A., Ahmad S.M.S.
Other Authors: 35069976500
Format: Conference Paper
Published: 2023
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Universiti Tenaga Nasional
id my.uniten.dspace-30691
record_format dspace
spelling my.uniten.dspace-306912024-04-18T10:58:37Z A comparison between neural network based and fuzzy logic models for chlorophll-a estimation Malek S. Salleh A. Ahmad S.M.S. 35069976500 7003809022 24721182400 Aritificial neural network Chlorophyll-a Fuzzy logic Chlorophyll Computer applications Dissolution Dissolved oxygen Fuzzy logic Fuzzy systems Porphyrins Time series Algal biomass Ammoniacal nitrogen Artificial Neural Network Chlorophyll a Feed-forward artificial neural networks Fuzzy logic approach Fuzzy logic model Input parameter Malaysia Nitrate nitrogen Performance measure Root mean square errors Secchi depth Time-series data Water temperatures Neural networks This paper describes the application of two novel computational methods such as fuzzy logic and supervised artificial neural network (ANN) to model algal biomass in tropical Putrajaya Lake and Wetlands (Malaysia). Limnological time series data collected from 2001 until 2004 was utilized using input parameters such as water temperature, pH, secchi depth, dissolved oxygen, ammoniacal nitrogen and nitrate nitrogen. Performance measure for the models developed was in terms of root mean square error (RMSE). Both models developed gave similar result with models developed using fuzzy logic approach performed slightly better compared to feed-forward artificial neural network model. � 2010 IEEE. Final 2023-12-29T07:51:24Z 2023-12-29T07:51:24Z 2010 Conference Paper 10.1109/ICCEA.2010.217 2-s2.0-77952751316 https://www.scopus.com/inward/record.uri?eid=2-s2.0-77952751316&doi=10.1109%2fICCEA.2010.217&partnerID=40&md5=2afced10d66e4dc388de2310f0ba9580 https://irepository.uniten.edu.my/handle/123456789/30691 2 5445667 340 343 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 Aritificial neural network
Chlorophyll-a
Fuzzy logic
Chlorophyll
Computer applications
Dissolution
Dissolved oxygen
Fuzzy logic
Fuzzy systems
Porphyrins
Time series
Algal biomass
Ammoniacal nitrogen
Artificial Neural Network
Chlorophyll a
Feed-forward artificial neural networks
Fuzzy logic approach
Fuzzy logic model
Input parameter
Malaysia
Nitrate nitrogen
Performance measure
Root mean square errors
Secchi depth
Time-series data
Water temperatures
Neural networks
spellingShingle Aritificial neural network
Chlorophyll-a
Fuzzy logic
Chlorophyll
Computer applications
Dissolution
Dissolved oxygen
Fuzzy logic
Fuzzy systems
Porphyrins
Time series
Algal biomass
Ammoniacal nitrogen
Artificial Neural Network
Chlorophyll a
Feed-forward artificial neural networks
Fuzzy logic approach
Fuzzy logic model
Input parameter
Malaysia
Nitrate nitrogen
Performance measure
Root mean square errors
Secchi depth
Time-series data
Water temperatures
Neural networks
Malek S.
Salleh A.
Ahmad S.M.S.
A comparison between neural network based and fuzzy logic models for chlorophll-a estimation
description This paper describes the application of two novel computational methods such as fuzzy logic and supervised artificial neural network (ANN) to model algal biomass in tropical Putrajaya Lake and Wetlands (Malaysia). Limnological time series data collected from 2001 until 2004 was utilized using input parameters such as water temperature, pH, secchi depth, dissolved oxygen, ammoniacal nitrogen and nitrate nitrogen. Performance measure for the models developed was in terms of root mean square error (RMSE). Both models developed gave similar result with models developed using fuzzy logic approach performed slightly better compared to feed-forward artificial neural network model. � 2010 IEEE.
author2 35069976500
author_facet 35069976500
Malek S.
Salleh A.
Ahmad S.M.S.
format Conference Paper
author Malek S.
Salleh A.
Ahmad S.M.S.
author_sort Malek S.
title A comparison between neural network based and fuzzy logic models for chlorophll-a estimation
title_short A comparison between neural network based and fuzzy logic models for chlorophll-a estimation
title_full A comparison between neural network based and fuzzy logic models for chlorophll-a estimation
title_fullStr A comparison between neural network based and fuzzy logic models for chlorophll-a estimation
title_full_unstemmed A comparison between neural network based and fuzzy logic models for chlorophll-a estimation
title_sort comparison between neural network based and fuzzy logic models for chlorophll-a estimation
publishDate 2023
_version_ 1806425760254132224