Javascript must be enabled to continue!
Water quality index prediction with hybridized ELM and Gaussian process regression
View through CrossRef
The Department of Environment (DOE) of Malaysia evaluates river water quality based on the water quality index (WQI), which is a single number function that considers six parameters for its determination, namely the ammonia nitrogen (AN), biochemical oxygen demand (BOD), chemical oxygen demand (COD), dissolved oxygen (DO), pH, and suspended solids (SS). The conventional WQI calculation is tedious and requires all parameter values in computing the final WQI. In this study, the extreme learning machine (ELM) and the radial basis function kernel Gaussian process regression (GPR), were enhanced with bootstrap aggregating (bagging) and adaptive boosting (AdaBoost) for the WQI prediction at the Klang River, Malaysia. The global performance indicator (GPI) was used to evaluate the models’ performance. By preparing different input combinations for the WQI prediction, the parameter importance was found in following order: DO > COD > SS > AN > BOD > pH, and all models demonstrated lower prediction accuracy with a lesser number of parameter inputs. The GPR revealed a consistent trend with higher WQI prediction accuracy than ELM. The Adaboost-ELM works better than the bagged-ELM for all input combinations, while the bagging algorithm improved the GPR prediction under certain scenarios. The bagged-GPR reported the highest GPI of 1.86 for WQI prediction using all six parameter inputs.
Title: Water quality index prediction with hybridized ELM and Gaussian process regression
Description:
The Department of Environment (DOE) of Malaysia evaluates river water quality based on the water quality index (WQI), which is a single number function that considers six parameters for its determination, namely the ammonia nitrogen (AN), biochemical oxygen demand (BOD), chemical oxygen demand (COD), dissolved oxygen (DO), pH, and suspended solids (SS).
The conventional WQI calculation is tedious and requires all parameter values in computing the final WQI.
In this study, the extreme learning machine (ELM) and the radial basis function kernel Gaussian process regression (GPR), were enhanced with bootstrap aggregating (bagging) and adaptive boosting (AdaBoost) for the WQI prediction at the Klang River, Malaysia.
The global performance indicator (GPI) was used to evaluate the models’ performance.
By preparing different input combinations for the WQI prediction, the parameter importance was found in following order: DO > COD > SS > AN > BOD > pH, and all models demonstrated lower prediction accuracy with a lesser number of parameter inputs.
The GPR revealed a consistent trend with higher WQI prediction accuracy than ELM.
The Adaboost-ELM works better than the bagged-ELM for all input combinations, while the bagging algorithm improved the GPR prediction under certain scenarios.
The bagged-GPR reported the highest GPI of 1.
86 for WQI prediction using all six parameter inputs.
Related Results
Odd version Mathieu-Gaussian beam based on Green function
Odd version Mathieu-Gaussian beam based on Green function
Like the theoretical pattern of non-diffracting Bessel beams, ideal non-diffracting Mathieu beams also carry infinite energy, but cannot be generated as a physically realizable ent...
A COMPACT OPTIMAL LEARNING MACHINE
A COMPACT OPTIMAL LEARNING MACHINE
Artificial neural networks (ANNs) have been developed and applied to a variety of problems, such as pattern recognition, clustering, function approximation, foreca...
Extreme learning machine for soil temperature prediction using only air temperature as input
Extreme learning machine for soil temperature prediction using only air temperature as input
Abstract
Soil temperature (TS) is a crucial parameter in many fields, especially agriculture. In developing countries like Algeria, the soil temperatures (ST) and the meteo...
Settlement Prediction of Foundation Pit Excavation Based on the GWO‐ELM Model considering Different States of Influence
Settlement Prediction of Foundation Pit Excavation Based on the GWO‐ELM Model considering Different States of Influence
This paper proposes a novel grey wolf optimization‐extreme learning machine model, namely, the GWO‐ELM model, to train and predict the ground subsidence by combining the extreme le...
The Eukaryotic Linear Motif Resource (ELM): Regulatory Sites in Proteins
The Eukaryotic Linear Motif Resource (ELM): Regulatory Sites in Proteins
AbstractLinear motifs are short and evolutionarily variable sequence patterns associated with particular functions often involving post-translational modifications, such as phospho...
Integrated hydrological modelling for sustainable water allocation planning : Mkomazi Basin, South Africa case study
Integrated hydrological modelling for sustainable water allocation planning : Mkomazi Basin, South Africa case study
Allocation of freshwater resources between societal needs and natural ecological systems is of great concern for water managers. This development has challenged decision-makers reg...
Use of Formation Water and Associated Gases and their Simultaneous Utilization for Obtaining Microelement Concentrates Fresh Water and Drinking Water
Use of Formation Water and Associated Gases and their Simultaneous Utilization for Obtaining Microelement Concentrates Fresh Water and Drinking Water
Abstract Purpose: The invention relates to the oil industry, inorganic chemistry, in particular, to the methods of complex processing of formation water, using flare gas of oil and...
Data-driven Warping of Gaussian Processes for Spatial Interpolation of Skewed Data
Data-driven Warping of Gaussian Processes for Spatial Interpolation of Skewed Data
<p>Gaussian processes are a flexible machine learning framework that can be used for spatial interpolation and space-time prediction as well. Gaussian process regress...

