Evaluating Recycling Initiatives for Landfill Diversion in Developing Economies Using Integrated Machine Learning Techniques DOI Creative Commons
Muyiwa Lawrence Adedara, Ridwan Taiwo, Olusola Olaitan Ayeleru

et al.

Recycling, Journal Year: 2025, Volume and Issue: 10(3), P. 100 - 100

Published: May 19, 2025

This study investigates the effectiveness of Lagos Recycle Initiative (LRI) on landfill diversion (LFD) in Lagos, Nigeria, where evidence-based assessments such initiatives are lacking. It evaluates recycling rate (RDR) household recyclables (HSRs) across local government areas using field surveys and population data. Machine learning algorithms (logistic regression, random forest, XGBoost, CatBoost) refined with Bayesian optimisation were employed to predict motivation. The findings reveal a low RDR 0.37%, indicating that only approximately 2.47% (31,554.25 metric tonnes) recovered annually compared targeted 50% (638,750 tonnes). optimised CatBoost model (accuracy F1 score 0.79) identified collection time absence overflowing HSR bins as key motivators for via SHapley Additive exPlanations (SHAP) framework. concludes current LRI efforts insufficient meet targets. recommends expanding recovery addressing operational challenges faced by registered recyclers improve outcomes. policy implications this suggest need stricter enforcement regulations, coupled financial incentives both households boost participation, thereby enhancing overall waste under LRI. research provides benchmark assessing urban (RIs) rapidly growing African cities.

Language: Английский

Strength and durability predictions of ternary blended nano-engineered high-performance concrete: Application of hybrid machine learning techniques with bio-inspired optimization DOI
Vikrant S. Vairagade, Boskey V. Bahoria, Haytham F. Isleem

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 148, P. 110470 - 110470

Published: March 6, 2025

Language: Английский

Citations

1
Compressive strength of nano concrete materials under elevated temperatures using machine learning DOI Creative Commons
Abdullah M. Zeyad,

Alaa A. Mahmoud,

Alaa A. El‐Sayed

et al.

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

Published: Oct. 16, 2024

In this study, four Artificial intelligence (AI) - based machine learning models were developed to estimate the Residual compressive strength (RCS) value of concrete supported with nano additives Nanocarbon tubes (NCTs) and Nano alumina (NAl), after exposure elevated temperatures ranging from 200 800 degrees. These via adapting meta- heuristic including Water cycle algorithm (WCA), Genetic (GA), classical AI neural networks (ANNs), Fuzzy logic (FLM), in addition statistical method Multiple linear regression (MLR). 156 post heating experimental results available as a literature data (represents input parameters temperature change, heat duration, nanomaterial type, replacement proportion) are used achieve study's objective. Results demonstrated that ANN FLM have strong potential predicting RCS. However, it is often infeasible generate practical equations relate output variables these models. Upon analysing WCA GA, was found yielded most accurate predictions on all performance indicators. Furthermore, RCS prediction superior accuracy derived utilizing meta-heuristic Mean absolute errors (MAEs) 3.09 kg/cm² 3.53 for training, 1.91 2.72 validation, testing sets, respectively. Additionally, sensitivity analysis weights SHAP investigation performed reveals impact relationship variables. Both techniques reveal degree time had highest positive value, followed by NAl NCTs, order.

Language: Английский

Citations

6
Prediction and deployment of compressive strength of high-performance concrete using ensemble learning techniques DOI
Ridwan Taiwo, Abdul‐Mugis Yussif,

Adesola Habeeb Adegoke

et al.

Construction and Building Materials, Journal Year: 2024, Volume and Issue: 451, P. 138808 - 138808

Published: Oct. 28, 2024

Language: Английский

Citations

4
Genetic Programming-based Algorithms Application in Modeling the Compressive Strength of Steel Fiber-Reinforced Concrete Exposed to Elevated Temperatures DOI Creative Commons
Mohsin Ali, Li Chen, Qadir Bux alias Imran Latif

et al.

Composites Part C Open Access, Journal Year: 2024, Volume and Issue: unknown, P. 100529 - 100529

Published: Oct. 1, 2024

Language: Английский

Citations

3
Evaluating Recycling Initiatives for Landfill Diversion in Developing Economies Using Integrated Machine Learning Techniques DOI Creative Commons
Muyiwa Lawrence Adedara, Ridwan Taiwo, Olusola Olaitan Ayeleru

et al.

Recycling, Journal Year: 2025, Volume and Issue: 10(3), P. 100 - 100

Published: May 19, 2025

This study investigates the effectiveness of Lagos Recycle Initiative (LRI) on landfill diversion (LFD) in Lagos, Nigeria, where evidence-based assessments such initiatives are lacking. It evaluates recycling rate (RDR) household recyclables (HSRs) across local government areas using field surveys and population data. Machine learning algorithms (logistic regression, random forest, XGBoost, CatBoost) refined with Bayesian optimisation were employed to predict motivation. The findings reveal a low RDR 0.37%, indicating that only approximately 2.47% (31,554.25 metric tonnes) recovered annually compared targeted 50% (638,750 tonnes). optimised CatBoost model (accuracy F1 score 0.79) identified collection time absence overflowing HSR bins as key motivators for via SHapley Additive exPlanations (SHAP) framework. concludes current LRI efforts insufficient meet targets. recommends expanding recovery addressing operational challenges faced by registered recyclers improve outcomes. policy implications this suggest need stricter enforcement regulations, coupled financial incentives both households boost participation, thereby enhancing overall waste under LRI. research provides benchmark assessing urban (RIs) rapidly growing African cities.

Language: Английский

Citations

0