A Multi-Module Explainable Artificial Intelligence Framework for Project Risk Management: Enhancing Transparency in Decision-making

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 148, С. 110427 - 110427

Опубликована: Март 8, 2025

Язык: Английский

---

A novel hybrid group method of data handling and Levenberg Marquardt model for estimating total organic carbon in source rocks with explainable artificial intelligence

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 144, С. 110137 - 110137

Опубликована: Янв. 27, 2025

Язык: Английский

---

Prediction of soil arsenic concentration in European soils: a dimensionality reduction and ensemble learning approach

Journal of Hazardous Materials Advances, Год журнала: 2025, Номер 17, С. 100604 - 100604

Опубликована: Янв. 15, 2025

Язык: Английский

---

Failure mode identification in reinforced concrete flat slabs using advanced ensemble neural networks

Multiscale and Multidisciplinary Modeling Experiments and Design, Год журнала: 2024, Номер 7(6), С. 5759 - 5773

Опубликована: Июль 30, 2024

Язык: Английский

---

Hybrid machine learning algorithms for estimating shear strength of steel-reinforced concrete composite shear walls

Multiscale and Multidisciplinary Modeling Experiments and Design, Год журнала: 2025, Номер 8(2)

Опубликована: Янв. 30, 2025

Язык: Английский

---

Repeated impact failure mechanisms in valve port for water hydraulic high-speed on/off valve: Experimental and numerical analysis

Engineering Failure Analysis, Год журнала: 2025, Номер unknown, С. 109503 - 109503

Опубликована: Март 1, 2025

Язык: Английский

---

Comprehensive analysis of structural parameters influencing the fundamental period of steel-braced RC buildings using machine learning interpretability

AI in Civil Engineering, Год журнала: 2025, Номер 4(1)

Опубликована: Март 10, 2025

Язык: Английский

---

Developing an explainable artificial intelligent (XAI) model for predicting pile driving vibrations in Bangkok’s subsoil

Neural Computing and Applications, Год журнала: 2025, Номер unknown

Опубликована: Апрель 21, 2025

Язык: Английский

---

The impact of rainfall and slope on hillslope runoff and erosion depending on machine learning

Frontiers in Environmental Science, Год журнала: 2025, Номер 13

Опубликована: Апрель 24, 2025

Introduction Soil erosion is a critical issue faced by many regions around the world, especially in purple soil hilly areas. Rainfall and slope, as major driving factors of erosion, pose significant challenge quantifying their impact on hillslope runoff sediment yield. While existing studies have revealed effects rainfall intensity slope comprehensive analysis interactions between different types still lacking. To address this gap, study, based machine learning methods, explores type, amount, maximum 30-min (I30), depth (H) erosion-induced yield (S), unveils among these factors. Methods The K-means clustering algorithm was used to classify 43 events into three types: A-type, B-type, C-type. A-type characterized long duration, large amounts, moderate intensity; B-type short small high C-type intermediate B-type. Random Forest (RF) employed assess impacts yield, along with feature importance analysis. Results results show that amount has most Under types, ranking I30 H S follows: (C>A>B), (A>B>C). follows trend first increasing then decreasing, varying degrees influence depending type. Discussion novelty study lies combining techniques systematically evaluate, for time, type This research not only provides theoretical basis control but also offers scientific support precise prediction management conservation measures regions.

Язык: Английский

---

Enhancing Traffic Accident Severity Prediction: Feature Identification Using Explainable AI

Vehicles, Год журнала: 2025, Номер 7(2), С. 38 - 38

Опубликована: Апрель 28, 2025

The latest developments in Advanced Driver Assistance Systems (ADAS) have greatly enhanced the comfort and safety of drivers. These technologies can identify driver abnormalities like fatigue, inattention, impairment, which are essential for averting collisions. One important aspects this technology is automated traffic accident detection prediction, may help saving precious human lives. This study aims to explore critical features related prevention. A public US dataset was used aforementioned task, where various machine learning (ML) models were applied predict accidents. ML included Random Forest, AdaBoost, KNN, SVM. compared their accuracies, Forest found be best-performing model, providing most accurate reliable classification accident-related data. Owing black box nature models, best-fit model executed with explainable AI (XAI) methods such as LIME permutation importance understand its decision-making given task. unique aspect introduction artificial intelligence enables us human-interpretable awareness how operate. It provides information about inner workings directs improvement feature engineering detection, more dependable. analysis identified features, including sources, descriptions weather conditions, time day (weather timestamp, start time, end time), distance, crossing, signals, significant predictors probability an occurring. Future ADAS development anticipated impacted by study’s conclusions. adjusted different driving scenarios identifying comprehending dynamics make sure that systems precise, reliable, suitable real-world circumstances.

Язык: Английский

---