Improvements in the Explicit Estimation of Pollutant Dispersion Coefficient in Rivers by Subset Selection of Maximum Dissimilarity Hybridized With ANFIS-Firefly Algorithm (FFA)
In this paper, a new hybrid model is proposed using Subset Selection by Maximum Dissimilarity (SSMD) and adaptive neuro-fuzzy inference system (ANFIS) hybridized with the firefly algorithm (FFA) to predict the longitudinal dispersion coefficient (K<sub>x</sub>). The proposed framework (A...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9031409/ |
id |
doaj-95a165c2d15a475a82150ee470af76a8 |
---|---|
record_format |
Article |
spelling |
doaj-95a165c2d15a475a82150ee470af76a82021-03-30T01:31:28ZengIEEEIEEE Access2169-35362020-01-018603146033710.1109/ACCESS.2020.29799279031409Improvements in the Explicit Estimation of Pollutant Dispersion Coefficient in Rivers by Subset Selection of Maximum Dissimilarity Hybridized With ANFIS-Firefly Algorithm (FFA)Hossien Riahi-Madvar0https://orcid.org/0000-0002-5902-4985Majid Dehghani1https://orcid.org/0000-0001-9850-4204Kulwinder Singh Parmar2https://orcid.org/0000-0002-7589-7364Narjes Nabipour3https://orcid.org/0000-0003-3882-3179Shahaboddin Shamshirband4https://orcid.org/0000-0002-6605-498XDepartment of Water Science and Engineering, Faculty of Agriculture, Vali-e-Asr University of Rafsanjan, Rafsanjan, IranDepartment of Civil Engineering, Faculty of Technical and Engineering, Vali-e-Asr University of Rafsanjan, Rafsanjan, IranDepartment of Mathematics, I. K. Gujral Punjab Technical University, Jalandhar-Kapurthala, IndiaInstitute of Research and Development, Duy Tan University, Da Nang, VietnamDepartment for Management of Science and Technology Development, Ton Duc Thang University, Ho Chi Minh City, VietnamIn this paper, a new hybrid model is proposed using Subset Selection by Maximum Dissimilarity (SSMD) and adaptive neuro-fuzzy inference system (ANFIS) hybridized with the firefly algorithm (FFA) to predict the longitudinal dispersion coefficient (K<sub>x</sub>). The proposed framework (ANFIS-FFA), combines the specific structures and strengths of both ANFIS and FFA approaches. The FFA is used to derive the optimum ANFIS parameters. The K<sub>x</sub> data set includes 503 cross-sectional data point from small to large rivers. For pre-processing of the data set, the SSMD method is used, which is superior to the classical trial and error method. The database covers a wide range of river width (0.2867 m), and depths (0.03419.9 m). Fifteen different combinations of river width (B), depth (H), flow velocity (U) and shear velocity (U<sub>*</sub>) are implemented as inputs to create fifteen estimative models. The output of the ANFIS-FFA model is compared with the ANFIS and previously published equations to check the performance of the proposed model. The results show that the highest accuracy is attained by the M1 model, with all geometric and hydrodynamic parameters as input variables in comparison with ANFIS and previous equations. The R<sup>2</sup> value, RMSE, MAE and NSE for ANFIS-FFA model are 0.67, 113.14 m<sup>2</sup>/s, 48 m<sup>2</sup>/s, and 0.63 for proposed dimensional model, and 0.35, 874.5, 520.8, and 0.1 in non-dimensional ANFIS-FFA model, respectively. These values were 0.37, 463.34 m<sup>2</sup>/s, 85.69 m<sup>2</sup>/s, and -5.19 for dimensional ANFIS model, and 0.11, 3269.88, 1932.09 and -11.54 for non-dimensional ANFIS model, respectively. Overall, hybridization caused 81%, 75%, 76% improvement in R<sup>2</sup>, RMSE and MAE. In another contribution of the paper, by using the matrix form of developed ANFIS-FFA optimized parameters, a novel explicit calculation procedure for estimation of K<sub>x</sub> is derived. Based on the results, the proposed ANFIS-FFA model exhibits significant improvements than the classical ANFIS and highlights that optimizing by nature-inspired optimization algorithms plays a critical role in strengthening the ANFIS estimations generality.https://ieeexplore.ieee.org/document/9031409/Longitudinal dispersion coefficientANFIS-FFAmaximum dissimilarity methodnatural riversadaptive neuro-fuzzy inference system |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hossien Riahi-Madvar Majid Dehghani Kulwinder Singh Parmar Narjes Nabipour Shahaboddin Shamshirband |
spellingShingle |
Hossien Riahi-Madvar Majid Dehghani Kulwinder Singh Parmar Narjes Nabipour Shahaboddin Shamshirband Improvements in the Explicit Estimation of Pollutant Dispersion Coefficient in Rivers by Subset Selection of Maximum Dissimilarity Hybridized With ANFIS-Firefly Algorithm (FFA) IEEE Access Longitudinal dispersion coefficient ANFIS-FFA maximum dissimilarity method natural rivers adaptive neuro-fuzzy inference system |
author_facet |
Hossien Riahi-Madvar Majid Dehghani Kulwinder Singh Parmar Narjes Nabipour Shahaboddin Shamshirband |
author_sort |
Hossien Riahi-Madvar |
title |
Improvements in the Explicit Estimation of Pollutant Dispersion Coefficient in Rivers by Subset Selection of Maximum Dissimilarity Hybridized With ANFIS-Firefly Algorithm (FFA) |
title_short |
Improvements in the Explicit Estimation of Pollutant Dispersion Coefficient in Rivers by Subset Selection of Maximum Dissimilarity Hybridized With ANFIS-Firefly Algorithm (FFA) |
title_full |
Improvements in the Explicit Estimation of Pollutant Dispersion Coefficient in Rivers by Subset Selection of Maximum Dissimilarity Hybridized With ANFIS-Firefly Algorithm (FFA) |
title_fullStr |
Improvements in the Explicit Estimation of Pollutant Dispersion Coefficient in Rivers by Subset Selection of Maximum Dissimilarity Hybridized With ANFIS-Firefly Algorithm (FFA) |
title_full_unstemmed |
Improvements in the Explicit Estimation of Pollutant Dispersion Coefficient in Rivers by Subset Selection of Maximum Dissimilarity Hybridized With ANFIS-Firefly Algorithm (FFA) |
title_sort |
improvements in the explicit estimation of pollutant dispersion coefficient in rivers by subset selection of maximum dissimilarity hybridized with anfis-firefly algorithm (ffa) |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
In this paper, a new hybrid model is proposed using Subset Selection by Maximum Dissimilarity (SSMD) and adaptive neuro-fuzzy inference system (ANFIS) hybridized with the firefly algorithm (FFA) to predict the longitudinal dispersion coefficient (K<sub>x</sub>). The proposed framework (ANFIS-FFA), combines the specific structures and strengths of both ANFIS and FFA approaches. The FFA is used to derive the optimum ANFIS parameters. The K<sub>x</sub> data set includes 503 cross-sectional data point from small to large rivers. For pre-processing of the data set, the SSMD method is used, which is superior to the classical trial and error method. The database covers a wide range of river width (0.2867 m), and depths (0.03419.9 m). Fifteen different combinations of river width (B), depth (H), flow velocity (U) and shear velocity (U<sub>*</sub>) are implemented as inputs to create fifteen estimative models. The output of the ANFIS-FFA model is compared with the ANFIS and previously published equations to check the performance of the proposed model. The results show that the highest accuracy is attained by the M1 model, with all geometric and hydrodynamic parameters as input variables in comparison with ANFIS and previous equations. The R<sup>2</sup> value, RMSE, MAE and NSE for ANFIS-FFA model are 0.67, 113.14 m<sup>2</sup>/s, 48 m<sup>2</sup>/s, and 0.63 for proposed dimensional model, and 0.35, 874.5, 520.8, and 0.1 in non-dimensional ANFIS-FFA model, respectively. These values were 0.37, 463.34 m<sup>2</sup>/s, 85.69 m<sup>2</sup>/s, and -5.19 for dimensional ANFIS model, and 0.11, 3269.88, 1932.09 and -11.54 for non-dimensional ANFIS model, respectively. Overall, hybridization caused 81%, 75%, 76% improvement in R<sup>2</sup>, RMSE and MAE. In another contribution of the paper, by using the matrix form of developed ANFIS-FFA optimized parameters, a novel explicit calculation procedure for estimation of K<sub>x</sub> is derived. Based on the results, the proposed ANFIS-FFA model exhibits significant improvements than the classical ANFIS and highlights that optimizing by nature-inspired optimization algorithms plays a critical role in strengthening the ANFIS estimations generality. |
topic |
Longitudinal dispersion coefficient ANFIS-FFA maximum dissimilarity method natural rivers adaptive neuro-fuzzy inference system |
url |
https://ieeexplore.ieee.org/document/9031409/ |
work_keys_str_mv |
AT hossienriahimadvar improvementsintheexplicitestimationofpollutantdispersioncoefficientinriversbysubsetselectionofmaximumdissimilarityhybridizedwithanfisfireflyalgorithmffa AT majiddehghani improvementsintheexplicitestimationofpollutantdispersioncoefficientinriversbysubsetselectionofmaximumdissimilarityhybridizedwithanfisfireflyalgorithmffa AT kulwindersinghparmar improvementsintheexplicitestimationofpollutantdispersioncoefficientinriversbysubsetselectionofmaximumdissimilarityhybridizedwithanfisfireflyalgorithmffa AT narjesnabipour improvementsintheexplicitestimationofpollutantdispersioncoefficientinriversbysubsetselectionofmaximumdissimilarityhybridizedwithanfisfireflyalgorithmffa AT shahaboddinshamshirband improvementsintheexplicitestimationofpollutantdispersioncoefficientinriversbysubsetselectionofmaximumdissimilarityhybridizedwithanfisfireflyalgorithmffa |
_version_ |
1724186922666950656 |