An empirical studies on online gender-based violence: Classification analysis utilizing XGBOOST

AIP conference proceedings, Journal Year: 2025, Volume and Issue: 3248, P. 040003 - 040003

Published: Jan. 1, 2025

Language: Английский

---

Design of sustainable mortar incorporating construction and demolition waste through adaptive experiments accelerated by machine learning

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104264 - 104264

Published: Feb. 1, 2025

Language: Английский

---

Framework for investigating structure cracking using real engineering data combined with physics constraints

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

Published: Feb. 21, 2025

Accurate description of the condition engineering structures is important for ensuring structural safety. Traditional analysis methods based on simplified physical mechanisms cannot accurately characterize and neglect value large amount data generated during construction process. This paper proposes a data-driven framework that combines principles, dimensionality reduction techniques ensemble learning models to trace back deep-seated connections between data, achieving multi-factor defects. Using concrete cracks in certain project as an example, considers full life-cycle including material, environment, processes, construct assessment model. The results show by establishing mapping relationship condition, integrating cumulative indicators from different stages, reference describing safety can be provided some extent, along with optimization suggestions, offering analytical perspective solving complex problems engineering.

Language: Английский

---

Novel approaches in prediction of tensile strain capacity of engineered cementitious composites using interpretable approaches

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

Published: Jan. 1, 2025

Abstract The performance and durability of conventional concrete (CC) are significantly influenced by its weak tensile strength strain capacity (TSC). Thus, the intrusion fibers in cementitious matrix forms ductile engineered composites (ECCs) that can cater to this area CC. Moreover, ECCs have become a reasonable substitute for brittle plain due their increased flexibility, ductility, greater TSC. prediction ECC is crucial without need laborious experimental procedures. achieve this, machine learning approaches (MLAs), namely light gradient boosting (LGB) approach, extreme (XGB) artificial neural network (ANN), k -nearest neighbor (KNN), were developed. data gathered from literature comprise input parameters which fiber content, length, cement, diameter, water-to-binder ratio, fly ash (FA), age, sand, superplasticizer, TSC as output utilized. assessment models gauged with coefficient determination ( R 2 ), statistical measures, uncertainty analysis. In addition, an analysis feature importance carried out further refinement model. result demonstrates ANN XGB perform well train test sets > 0.96. Statistical measures show all give fewer errors higher , depict robust performance. Validation via K -fold confirms showing correlation determination. reveals FA major contribution ECC. graphical user interface also developed help users/researchers will facilitate them estimate practical applications.

Language: Английский

---

Reinforcement effects of bonding Fe-SMA in steel bridge diaphragms based on machine learning

Structures, Journal Year: 2025, Volume and Issue: 76, P. 108984 - 108984

Published: April 25, 2025

Language: Английский

---

Study on the degradation models based on the experiments considering the coupling effect of freeze-thaw and carbonation

Structures, Journal Year: 2024, Volume and Issue: 64, P. 106659 - 106659

Published: May 31, 2024

Language: Английский

---

Understanding and predicting micro-characteristics of ultra-high performance concrete (UHPC) with green porous lightweight aggregates: Insights from machine learning techniques

Construction and Building Materials, Journal Year: 2024, Volume and Issue: 446, P. 138021 - 138021

Published: Aug. 28, 2024

Language: Английский

---

Energy-saving optimization of air-conditioning water system based on machine learning and improved bat algorithm

Energy and Buildings, Journal Year: 2025, Volume and Issue: unknown, P. 115333 - 115333

Published: Jan. 1, 2025

Language: Английский

---

Integrating PCA and XGBoost for Predicting UACLC of Steel-Reinforced Concrete-Filled Square Steel Tubular Columns at Elevated Temperatures

Case Studies in Construction Materials, Journal Year: 2025, Volume and Issue: unknown, P. e04456 - e04456

Published: Feb. 1, 2025

Language: Английский

---

Data driven design of ultra high performance concrete prospects and application

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

Published: March 18, 2025

Ultra-high performance concrete (UHPC) is a specialized class of cementitious composites that increasingly used in various applications, including bridge decks, connections between precast components, piers, columns, overlays, and the repair strengthening elements. The mechanical durability properties UHPC are significantly influenced by factors such as low water-to-binder ratios, inclusion supplementary materials (SCMs), fiber reinforcement. Machine learning (ML) has been employed to predict optimize its mixture designs using raw materials. This study first provides comprehensive review ML applications UHPC, focusing on predicting workability, mechanical, thermal properties. use data crossing, generative AI, physics-guided models, field-applicable software explored practical directions for future research. also develops models compressive strength database containing 1300 data-records. influence input variables evaluated SHapley Additive exPlanations (SHAP), revealing chemical compositions have relatively minor impacts, given material types used. By excluding insignificant variables, enhance both efficiency accuracy strength. advancement facilitates optimized design prediction while reducing experimental workload required inform models. Adding more diverse could further generalizability proposed

Language: Английский

---