Metaheuristic optimization algorithms-based prediction modeling for titanium dioxide-Assisted photocatalytic degradation of air contaminants

Results in Engineering, Journal Year: 2024, Volume and Issue: 23, P. 102637 - 102637

Published: July 29, 2024

Airborne contaminants pose significant environmental and health challenges. Titanium dioxide (TiO2) has emerged as a leading photocatalyst in the degradation of air compared to other photocatalysts due its inherent inertness, cost-effectiveness, photostability. To assess effectiveness, laboratory examinations are frequently employed measure photocatalytic rate TiO2. However, this approach involves time-consuming requirements, labor-intensive tasks, high costs. In literature, ensemble or standalone models commonly used for assessing performance TiO2 water contaminants. Nonetheless, application metaheuristic hybrid potential be more effective predictive accuracy efficiency. Accordingly, research utilized machine learning (ML) algorithms estimate photo-degradation constants organic pollutants using nanoparticles exposure ultraviolet light. Six metaheuristics optimization algorithms, namely, nuclear reaction (NRO), differential evolution algorithm (DEA), human felicity (HFA), lightning search (LSA), Harris hawks (HHA), tunicate swarm (TSA) were combined with random forest (RF) technique establish models. A database 200 data points was acquired from experimental studies model training testing. Furthermore, multiple statistical indicators 10-fold cross-validation examine established model's robustness. The TSA-RF demonstrated superior prediction among six suggested models, achieving an impressive correlation (R) 0.90 lower root mean square error (RMSE) 0.25. contrast, HFA-RF, HHA-RF, NRO-RF exhibited slightly R-value 0.88, RMSE scores 0.32. DEA-RF LSA-RF while effective, showed marginally 0.85, values 0.45 0.44, respectively. Moreover, SHapley Additive exPlanation (SHAP) results indicated that rates through photocatalysis most notably influenced by factors such reactor sizes, dosage, humidity, intensity.

Language: Английский

---

Soft computing models for prediction of bentonite plastic concrete strength

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Aug. 5, 2024

Bentonite plastic concrete (BPC) is extensively used in the construction of water-tight structures like cut-off walls dams, etc., because it offers high plasticity, improved workability, and homogeneity. Also, bentonite added to mixes for adsorption toxic metals. The modified design BPC, as compared normal concrete, requires a reliable tool predict its strength. Thus, this study presents novel attempt at application two innovative evolutionary techniques known multi-expression programming (MEP) gene expression (GEP) boosting-based algorithm AdaBoost 28-day compressive strength ( ) BPC based on mixture composition. MEP GEP algorithms expressed their outputs form an empirical equation, while failed do so. were trained using dataset 246 points gathered from published literature having six important input factors predicting. developed models subject error evaluation, results revealed that all satisfied suggested criteria had correlation coefficient (R) greater than 0.9 both training testing phases. However, surpassed terms accuracy demonstrated lower RMSE 1.66 2.02 2.38 GEP. Similarly, objective function value was 0.10 0.176 0.16 MEP, which indicated overall good performance techniques. Shapley additive analysis done model gain further insights into prediction process, cement, coarse aggregate, fine aggregate are most predicting BPC. Moreover, interactive graphical user interface (GUI) has been be practically utilized civil engineering industry

Language: Английский

---

Development of machine learning models for forecasting the strength of resilient modulus of subgrade soil: genetic and artificial neural network approaches

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Aug. 6, 2024

Accurately predicting the Modulus of Resilience (MR) subgrade soils, which exhibit non-linear stress–strain behaviors, is crucial for effective soil assessment. Traditional laboratory techniques determining MR are often costly and time-consuming. This study explores efficacy Genetic Programming (GEP), Multi-Expression (MEP), Artificial Neural Networks (ANN) in forecasting using 2813 data records while considering six key parameters. Several Statistical assessments were utilized to evaluate model accuracy. The results indicate that GEP consistently outperforms MEP ANN models, demonstrating lowest error metrics highest correlation indices (R2). During training, achieved an R2 value 0.996, surpassing (R2 = 0.97) 0.95) models. Sensitivity SHAP (SHapley Additive exPlanations) analysis also performed gain insights into input parameter significance. revealed confining stress (21.6%) dry density (26.89%) most influential parameters MR. corroborated these findings, highlighting critical impact on predictions. underscores reliability as a robust tool precise prediction applications, providing valuable performance significance across various machine-learning (ML) approaches.

Language: Английский

---

Optimized prediction modeling of micropollutant removal efficiency in forward osmosis membrane systems using explainable machine learning algorithms

Journal of Water Process Engineering, Journal Year: 2024, Volume and Issue: 66, P. 105937 - 105937

Published: Aug. 19, 2024

Language: Английский

---

Modeling an artificial neural network to estimate cement consumption in clayey waste-cement mixtures based on curing temperature, mechanical strength, and resilient modulus

Construction and Building Materials, Journal Year: 2025, Volume and Issue: 467, P. 140376 - 140376

Published: Feb. 12, 2025

Language: Английский

---

A Systematic Evaluation of the Empirical Relationships Between the Resilient Modulus and Permanent Deformation of Pavement Materials

Buildings, Journal Year: 2025, Volume and Issue: 15(5), P. 663 - 663

Published: Feb. 20, 2025

The resilient modulus (Mr) and permanent deformation of subgrade soils are key indicators for assessing pavement performance under repeated traffic loads. Although numerous studies have confirmed their importance in design prediction, a systematic review empirical relationships scientific knowledge is lacking, resulting insufficient integration application current findings. To address these issues, this study systematically reviews laboratory field-testing methods based on over 200 published papers, summarizes common equations, focuses the feasibility advantages integrating AI to predict Mr. Meanwhile, by examining main factors that influence Mr deformation, synthesizes evaluates existing research identify potential gaps. Findings indicate field tests effectively capture mechanical behavior materials, incorporating technology prediction enhances accuracy efficiency while managing complex influencing factors. However, equations not been fully integrated with emerging technologies validation optimization, some predictive models remain limited terms applicability generalizability. This highlights need refine using stochastic techniques, thereby facilitating more comprehensive latest testing computational tools. great significance advancing sustainable design, optimizing maintenance strategies, guiding future directions.

Language: Английский

---

GEP-Graph4MD: An Automatic Molecular Generation Method Based on Gene Expression Programming with Graph-Based Modeling

Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 182 - 193

Published: Jan. 1, 2025

Language: Английский

---

Tensile behavior evaluation of two-stage concrete using an innovative model optimization approach

REVIEWS ON ADVANCED MATERIALS SCIENCE, Journal Year: 2025, Volume and Issue: 64(1)

Published: Jan. 1, 2025

Abstract Two-stage concrete (TSC) is a sustainable material produced by incorporating coarse aggregates into formwork and filling the voids with specially formulated grout mix. The significance of this study to improve predictive accuracy TSC’s tensile strength, which essential for optimizing its use in construction applications. To achieve objective, novel reliable models were developed using advanced machine learning algorithms, including random forest (RF) gene expression programming (GEP). performance these was evaluated important evaluation metrics, coefficient determination ( R 2 ), mean absolute error (MAE), squared error, root square (RMSE), after they trained on comprehensive dataset. results suggest that RF model outperforms GEP model, as evidenced higher value 0.94 relative 0.91 reduced MAE RMSE values. This suggests has superior capability. Additionally, sensitivity analyses SHapley Additive ExPlanation analysis revealed water-to-binder (W/B) ratio most influential input parameter, accounting 51.01% outcomes presented model. research emphasizes TSC design, enhancing performance, promoting sustainable, cost-effective construction.

Language: Английский

---

Data-driven evolutionary programming for evaluating the mechanical properties of concrete containing plastic waste.

Case Studies in Construction Materials, Journal Year: 2024, Volume and Issue: unknown, P. e03763 - e03763

Published: Sept. 1, 2024

Language: Английский

---

Shear wave Velocity-Based Machine Learning Modeling for Prediction of Liquefaction Potential of Soil

Indian geotechnical journal, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 12, 2024

Language: Английский

---