Sustainable Smart Education Based on AI Models Incorporating Firefly Algorithm to Evaluate Further Education DOI Open Access
En-Hui Li, Zixi Wang, Jin Liu

и другие.

Sustainability, Год журнала: 2024, Номер 16(24), С. 10845 - 10845

Опубликована: Дек. 11, 2024

With the popularity of higher education and evolution workplace environment, graduate has become a key choice for students planning their future career paths. Therefore, this study proposes to use data processing ability pattern recognition machine learning models analyze relevant information applicants. This explores three different models—backpropagation neural networks (BPNN), random forests (RF), logistic regression (LR)—and combines them with firefly algorithm (FA). Through selection, model was constructed verified. By comparing verification results composite models, whose evaluation were closest actual selected as research result. The experimental show that result BPNN-FA is best, an R value 0.8842 highest prediction accuracy. At same time, influence each characteristic parameter on analyzed. CGPA greatest results, which provides direction evaluators level students’ scientific ability, well providing impetus continue promote combination artificial intelligence.

Язык: Английский

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

и другие.

Polymers, Год журнала: 2025, Номер 17(4), С. 499 - 499

Опубликована: Фев. 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.

Язык: Английский

Процитировано

2
Stabilization of Expansive Soils Using Cement–Zeolite Mixtures: Experimental Study and Lasso Modeling DOI Open Access
Ibrahim Haruna Umar, S. A. R. Abu–Bakar, Aminu K. Bello

и другие.

Materials, Год журнала: 2025, Номер 18(10), С. 2286 - 2286

Опубликована: Май 14, 2025

The stabilization of expansive soils is crucial for the construction projects to mitigate swelling, shrinkage, and bearing capacity issues. This study investigates synergistic effects cement clinoptilolite zeolite on stabilizing high-plasticity clay (CH) soil from Kano State, Nigeria. A total 30 admixture combinations-cement (0-8%) (0-15%)-were tested via standardized laboratory methods evaluate their free swell index (FSI), percentage, pressure, California Bearing Ratio (CBR). Principal component (Lasso) "least absolute shrinkage selection operator" regression modeled interactions between admixtures properties. key results include following: (1) 6% + 12% reduced FSI by 60% (45 → 18); (2) 8% 15% decreased percentage 47.8% (22.5% 11.75%); (3) lowered pressure 54.2% (240 kPa 110 kPa); (4) 50% (5.6% 2.8%); (5) 9% achieved an unsoaked CBR 80.01% soaked 72.79% (resilience ratio: 0.8010). PCLR models explained 93.5% (unsoaked) 75.0% (soaked) variance, highlighting how zeolite's mediation analysis indicates that improves mainly reducing (path coefficient = -0.91429, p < 0.0001), while conditional process modeling provided greater explanatory power (R2 0.745) compared moderation-only 0.618). demonstrates zeolite-cement blends optimize strength resilience in soils, with implications sustainable infrastructure arid semi-arid regions.

Язык: Английский

Процитировано

0
Modeling the strength parameters of agro waste-derived geopolymer concrete using advanced machine intelligence techniques DOI Creative Commons
Ahmed A. Alawi Al-Naghi, Muhammad Nasir Amin, Suleman Ayub Khan

и другие.

REVIEWS ON ADVANCED MATERIALS SCIENCE, Год журнала: 2024, Номер 63(1)

Опубликована: Янв. 1, 2024

Abstract The mechanical strength of geopolymer concrete incorporating corncob ash and slag (SCA-GPC) was estimated by means three distinct AI methods: a support vector machine (SVM), two ensemble methods called bagging regressor (BR), random forest (RFR). developed models were validated using statistical tests, absolute error assessment, the coefficient determination ( R 2 ). importance various modeling factors determined interaction diagrams. When estimating flexural compressive SCA-GPC, values over 0.85 measured between actual predicted findings both individual models. Statistical testing k -fold analysis for evaluation revealed that RFR model outperformed SVM BR in terms accuracy. As demonstrated graphs, characteristics SCA-GPC found to be extremely responsive mix proportions ground granulated blast furnace slag, fine aggregate, ash. This case all components. study highly precise estimations properties can made techniques. Improvements performance achieved implementation such practices.

Язык: Английский

Процитировано

2
Sustainable Smart Education Based on AI Models Incorporating Firefly Algorithm to Evaluate Further Education DOI Open Access
En-Hui Li, Zixi Wang, Jin Liu

и другие.

Sustainability, Год журнала: 2024, Номер 16(24), С. 10845 - 10845

Опубликована: Дек. 11, 2024

With the popularity of higher education and evolution workplace environment, graduate has become a key choice for students planning their future career paths. Therefore, this study proposes to use data processing ability pattern recognition machine learning models analyze relevant information applicants. This explores three different models—backpropagation neural networks (BPNN), random forests (RF), logistic regression (LR)—and combines them with firefly algorithm (FA). Through selection, model was constructed verified. By comparing verification results composite models, whose evaluation were closest actual selected as research result. The experimental show that result BPNN-FA is best, an R value 0.8842 highest prediction accuracy. At same time, influence each characteristic parameter on analyzed. CGPA greatest results, which provides direction evaluators level students’ scientific ability, well providing impetus continue promote combination artificial intelligence.

Язык: Английский

Процитировано

0