Developing an efficient explainable artificial intelligence approach for accurate reverse osmosis desalination plant performance prediction: application of SHAP analysis DOI Creative Commons
Meysam Alizamir, Mo Wang, Rana Muhammad Adnan Ikram

et al.

Engineering Applications of Computational Fluid Mechanics, Journal Year: 2024, Volume and Issue: 18(1)

Published: Nov. 6, 2024

In recent decades, securing drinkable water sources has become a pressing concern for populations in various regions worldwide. Therefore, to address the growing need potable water, contemporary purification technologies can be employed convert saline into supplies. prediction of important parameters desalination plants is key task designing and implementing these facilities. this regard, artificial intelligence techniques have proven powerful assets field. These methods offer an expedited effective means estimating parameters, thus catalyzing their implementation real-world scenarios. study, predictive accuracy six different machine learning models, including Natural Gradient-based Boosting (NGBoost), Adaptive (AdaBoost), Categorical (CatBoost), Support vector regression (SVR), Gaussian Process Regression (GPR), Extremely Randomized Tree (ERT) was evaluated modelling parameter permeate flow as element system efficiency, energy consumption, quality using input combinations feed salt concentration, condenser inlet temperature, rate, evaporator temperature. The next phase research SHAP interpretability method illustrate impact individual variables on model's output. Moreover, performance developed frameworks set five dependable statistical measures: RMSE, NS, MAE, MAPE R2. indicators were utilized provide robust gauging precision forecasts. A comparative analysis outcomes, measured by RMSE criteria, revealed that SVR technique (RMSE = 0.125 L/(h·m2)) exhibited superior compared NGBoost 0.163 L/(h·m2)), AdaBoost 0.219 CatBoost 0.149 GPR 0.156 ERT 0.167 methodologies predicting rates. outcomes obtained during evaluation stage demonstrated efficacy algorithm enhancing forecasts, utilizing relevant variables.

Language: Английский

The development of an efficient artificial intelligence-based classification approach for colorectal cancer response to radiochemotherapy: deep learning vs. machine learning DOI Creative Commons

Fatemeh Bahrambanan,

Meysam Alizamir,

Kayhan Moradveisi

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 2, 2025

Colorectal cancer (CRC) is a form of that impacts both the rectum and colon. Typically, it begins with small abnormal growth known as polyp, which can either be non-cancerous or cancerous. Therefore, early detection colorectal second deadliest after lung cancer, highly beneficial. Moreover, standard treatment for locally advanced widely accepted around world, chemoradiotherapy. Then, in this study, seven artificial intelligence models including decision tree, K-nearest neighbors, Adaboost, random forest, Gradient Boosting, multi-layer perceptron, convolutional neural network were implemented to detect patients responder non-responder radiochemotherapy. For finding potential predictors (genes), three feature selection strategies employed mutual information, F-classif, Chi-Square. Based on models, four different scenarios developed five, ten, twenty thirty features selected designing more accurate classification paradigm. The results study confirm neighbors provided terms accuracy, by 93.8%. Among methods, information F-classif showed best results, while Chi-Square produced worst results. suggested successfully applied robust approach response radiochemotherapy medical studies.

Language: Английский

Citations

1
An Interpretable XGBoost-SHAP Machine Learning Model for Reliable Prediction of Mechanical Properties in Waste Foundry Sand-Based Eco-Friendly Concrete DOI Creative Commons
Meysam Alizamir, Mo Wang, Rana Muhammad Adnan Ikram

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104307 - 104307

Published: Feb. 1, 2025

Language: Английский

Citations

1
Boosting-Based Machine Learning Applications in Polymer Science: A Review DOI Open Access
Ivan Malashin, В С Тынченко, Andrei Gantimurov

et al.

Polymers, Journal Year: 2025, Volume and Issue: 17(4), P. 499 - 499

Published: Feb. 14, 2025

The increasing complexity of polymer systems in both experimental and computational studies has led to an expanding interest machine learning (ML) methods aid data analysis, material design, predictive modeling. Among the various ML approaches, boosting methods, including AdaBoost, Gradient Boosting, XGBoost, CatBoost LightGBM, have emerged as powerful tools for tackling high-dimensional complex problems science. This paper provides overview applications science, highlighting their contributions areas such structure-property relationships, synthesis, performance prediction, characterization. By examining recent case on techniques this review aims highlight potential advancing characterization, optimization materials.

Language: Английский

Citations

1
Extraction of Major Groundwater Ions from Total Dissolved Solids and Mineralization Using Artificial Neural Networks: A Case Study of the Aflou Syncline Region, Algeria DOI Creative Commons

Mohammed Elamin Stamboul,

Habib Azzaz,

Abderrahmane Hamımed

et al.

Hydrology, Journal Year: 2025, Volume and Issue: 12(5), P. 103 - 103

Published: April 25, 2025

Global water demand due to population growth and agricultural development has led widespread overexploitation of groundwater, particularly in semi-arid regions. The traditional hydrochemistry monitoring system still suffers from limited laboratory accessibility high costs. This study aims predict the major ions including Ca2+, Mg2+, Na+, SO42−, Cl−, K+, HCO3−, NO3−, utilizing two field-measurable parameters (i.e., total dissolved solids (TDS) mineralization (MIN)) Aflou syncline region, Algeria. A multilayer perceptron (MLP) model optimized with Levenberg–Marquardt backpropagation (LMBP) provided greatest predictive accuracy for different Cl− R2 = (0.842, 0.980, 0.759, 0.945, 0.895), RMSE (53.660, 12.840, 14.960, 36.460, 30.530) (mg/L), NSE (0.840, 0.978, 0.754, 0.941, 0.892) testing phase, respectively. However, remaining NO3− was supplied as (0.045, 0.366, 0.004), (6.480, 41.720, 40.460) (0.003, 0.361, −0.933), performance our (LMBP-MLP) validated adjacent similar geological locations, Aflou, Madna, Ain Madhi. In addition, LMBP-MLP showed very promising results, that original research region.

Language: Английский

Citations

0
Efficient Computational Investigation on Accurate Daily Soil Temperature Prediction Using Boosting Ensemble Methods Explanation Based on SHAP Importance Analysis DOI Creative Commons
Meysam Alizamir, Mo Wang, Rana Muhammad Adnan Ikram

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 103220 - 103220

Published: Oct. 1, 2024

Language: Английский

Citations

3
Developing an efficient explainable artificial intelligence approach for accurate reverse osmosis desalination plant performance prediction: application of SHAP analysis DOI Creative Commons
Meysam Alizamir, Mo Wang, Rana Muhammad Adnan Ikram

et al.

Engineering Applications of Computational Fluid Mechanics, Journal Year: 2024, Volume and Issue: 18(1)

Published: Nov. 6, 2024

In recent decades, securing drinkable water sources has become a pressing concern for populations in various regions worldwide. Therefore, to address the growing need potable water, contemporary purification technologies can be employed convert saline into supplies. prediction of important parameters desalination plants is key task designing and implementing these facilities. this regard, artificial intelligence techniques have proven powerful assets field. These methods offer an expedited effective means estimating parameters, thus catalyzing their implementation real-world scenarios. study, predictive accuracy six different machine learning models, including Natural Gradient-based Boosting (NGBoost), Adaptive (AdaBoost), Categorical (CatBoost), Support vector regression (SVR), Gaussian Process Regression (GPR), Extremely Randomized Tree (ERT) was evaluated modelling parameter permeate flow as element system efficiency, energy consumption, quality using input combinations feed salt concentration, condenser inlet temperature, rate, evaporator temperature. The next phase research SHAP interpretability method illustrate impact individual variables on model's output. Moreover, performance developed frameworks set five dependable statistical measures: RMSE, NS, MAE, MAPE R2. indicators were utilized provide robust gauging precision forecasts. A comparative analysis outcomes, measured by RMSE criteria, revealed that SVR technique (RMSE = 0.125 L/(h·m2)) exhibited superior compared NGBoost 0.163 L/(h·m2)), AdaBoost 0.219 CatBoost 0.149 GPR 0.156 ERT 0.167 methodologies predicting rates. outcomes obtained during evaluation stage demonstrated efficacy algorithm enhancing forecasts, utilizing relevant variables.

Language: Английский

Citations

1