Опубликована: Янв. 1, 2024
Язык: Английский
Опубликована: Янв. 1, 2024
Язык: Английский
Applied Sciences, Год журнала: 2025, Номер 15(5), С. 2423 - 2423
Опубликована: Фев. 24, 2025
In predicting slope stability, updating datasets with new cases necessitates retraining traditional machine learning models, consuming substantial time and resources. This paper introduces the Incremental Learning Bayesian (ILB) model, combining incremental theory naive to address this issue. Key parameters—height; angle; unit weight; cohesion; internal friction pore water ratio—are used as predictive indicators. A dataset of 242 from existing literature is compiled for training evaluation. The ILB model’s performance assessed using accuracy, area under ROC curve (AUC), generalization ability, computation compared four common batch models: Random Forest (RF), Gradient Boosting Machine (GBM), Support Vector (SVM), Multi-Layer Perceptron (MLP). Variable importance partial dependence plots are explore relationship between prediction results parameters. Validation performed real Lala Copper Mine in Sichuan Province, China. Results show that (1) accuracy AUC improve grows. (2) model outperforms GBM, SVM, MLP AUC, similar RF. (3) It demonstrates superior lower than models. (4) Internal angle, ratio most important predictors.
Язык: Английский
Процитировано
1Engineering Analysis with Boundary Elements, Год журнала: 2025, Номер 176, С. 106264 - 106264
Опубликована: Апрель 12, 2025
Процитировано
0Earth Science Informatics, Год журнала: 2025, Номер 18(2)
Опубликована: Май 23, 2025
Язык: Английский
Процитировано
0Measurement, Год журнала: 2024, Номер unknown, С. 116477 - 116477
Опубликована: Дек. 1, 2024
Язык: Английский
Процитировано
1Опубликована: Янв. 1, 2024
Язык: Английский
Процитировано
0