Application of Meta-Heuristic Algorithms for Training Neural Networks and Deep Learning Architectures: A Comprehensive Review

Neural Processing Letters, Journal Year: 2022, Volume and Issue: 55(4), P. 4519 - 4622

Published: Oct. 31, 2022

Language: Английский

---

Ensemble learning framework for landslide susceptibility mapping: Different basic classifier and ensemble strategy

Geoscience Frontiers, Journal Year: 2023, Volume and Issue: 14(6), P. 101645 - 101645

Published: June 7, 2023

The application of ensemble learning models has been continuously improved in recent landslide susceptibility research, but most studies have no unified framework. Moreover, few papers discussed the applicability model mapping at township level. This study aims defining a robust framework that can become benchmark method for future research dealing with comparison different models. For this purpose, present work focuses on three basic classifiers: decision tree (DT), support vector machine (SVM), and multi-layer perceptron neural network (MLPNN) two homogeneous such as random forest (RF) extreme gradient boosting (XGBoost). hierarchical construction deep relied leading technologies (i.e., homogeneous/heterogeneous bagging, boosting, stacking strategy) to provide more accurate effective spatial probability occurrence. selected area is Dazhou town, located Jurassic red-strata Three Gorges Reservoir Area China, which strategic economic currently characterized by widespread risk. Based long-term field investigation, inventory counting thirty-three slow-moving polygons was drawn. results show do not necessarily perform better; instance, Bagging based DT-SVM-MLPNN-XGBoost performed worse than single XGBoost model. Amongst eleven tested models, Stacking RF-XGBoost model, ensemble, showed highest capability predicting landslide-affected areas. Besides, factor behaviors DT, SVM, MLPNN, RF reflected characteristics landslides reservoir area, wherein unfavorable lithological conditions intense human engineering activities water level fluctuation, residential construction, farmland development) are proven be key triggers. presented approach could used occurrence prediction similar regions other fields.

Language: Английский

---

Editorial for Advances and applications of deep learning and soft computing in geotechnical underground engineering

Journal of Rock Mechanics and Geotechnical Engineering, Journal Year: 2022, Volume and Issue: 14(3), P. 671 - 673

Published: Jan. 19, 2022

Language: Английский

---

Predicting and validating the load-settlement behavior of large-scale geosynthetic-reinforced soil abutments using hybrid intelligent modeling

Journal of Rock Mechanics and Geotechnical Engineering, Journal Year: 2022, Volume and Issue: 15(3), P. 773 - 788

Published: June 2, 2022

Settlement prediction of geosynthetic-reinforced soil (GRS) abutments under service loading conditions is an arduous and challenging task for practicing geotechnical/civil engineers. Hence, in this paper, a novel hybrid artificial intelligence (AI)-based model was developed by the combination neural network (ANN) Harris hawks' optimisation (HHO), that is, ANN-HHO, to predict settlement GRS abutments. Five other robust intelligent models such as support vector regression (SVR), Gaussian process (GPR), relevance machine (RVM), sequential minimal (SMOR), least-median square (LMSR) were constructed compared ANN-HHO model. The predictive strength, relalibility robustness evaluated based on rigorous statistical testing, ranking criteria, multi-criteria approach, uncertainity analysis sensitivity (SA). Moreover, veracity also substantiated against several large-scale independent experimental studies reported scientific literature. acquired findings demonstrated predicted with reasonable accuracy yielded superior performance comparison counterpart models. Therefore, it becomes one tools employed engineers preliminary decision-making when investigating in-service Finally, has been converted into simple mathematical formulation easy hand calculations, proved cost-effective less time-consuming tests numerical simulations.

Language: Английский

---

Analysis of Heat Transfer Behavior of Porous Wavy Fin with Radiation and Convection by Using a Machine Learning Technique

Symmetry, Journal Year: 2023, Volume and Issue: 15(8), P. 1601 - 1601

Published: Aug. 18, 2023

The impact of convection and radiation on the thermal distribution wavy porous fin is examined in present study. A hybrid model that combines differential evolution (DE) algorithm with an artificial neural network (ANN) proposed for predicting heat transfer fin. equation representing variation reduced to its dimensionless arrangement numerically solved using Rung, e-Kutta-Fehlberg’s fourth-fifth order method (RKF-45). study demonstrates effectiveness this model, results indicate approach outperforms ANN parameters obtained through grid search (GS), showcasing superiority DE-ANN terms accuracy performance. This research highlights potential utilizing DE improved predictive modeling sector. originality it addresses problem by optimizing selection algorithm.

Language: Английский

---

Intelligent prediction model of a polymer fracture grouting effect based on a genetic algorithm-optimized back propagation neural network

Tunnelling and Underground Space Technology, Journal Year: 2024, Volume and Issue: 148, P. 105781 - 105781

Published: April 26, 2024

Language: Английский

---

Metro System Inundation in Zhengzhou, Henan Province, China

Sustainability, Journal Year: 2022, Volume and Issue: 14(15), P. 9292 - 9292

Published: July 29, 2022

In this study, we investigated the flooding accident that occurred on Metro Line 5 in capital city of Zhengzhou, Henan Province, China. On 20 July 2021, owing to an extreme rainstorm, serious inundation Wulongkou parking lot Zhengzhou and its surrounding area. Flooding forced a train stop during operation, resulting 14 deaths. Based our preliminary investigation analysis accident, designed three main control measures reduce occurrence similar accidents mitigate impact future, given increasing number storm weather events recent years: (1) conduct subway flood risk assessments establish early warning system, involving real-time monitoring meteorological information operation construction; (2) improve emergency plans response mechanism for flooding; (3) strengthen safety awareness training ensure orderly evacuation people after accidents.

Language: Английский

---

Shear strength and durability against wetting and drying cycles of lime-stabilised laterite soil as subgrade

Physics and Chemistry of the Earth Parts A/B/C, Journal Year: 2023, Volume and Issue: 132, P. 103479 - 103479

Published: Aug. 26, 2023

Language: Английский

---

Efficient Seismic Stability Analysis of Embankment Slopes Subjected to Water Level Changes Using Gradient Boosting Algorithms

Frontiers in Earth Science, Journal Year: 2021, Volume and Issue: 9

Published: Dec. 2, 2021

Embankments are widespread throughout the world and their safety under seismic conditions is a primary concern in geotechnical engineering community since failure events may lead to disastrous consequences. This study proposes an efficient slope stability analysis approach by introducing advanced gradient boosting algorithms, namely Categorical Boosting (CatBoost), Light Gradient Machine (LightGBM), Extreme (XGBoost). A database consisting of 600 datasets prepared for model calibration evaluation, where factor (FS) regarded as output four influential factors selected inputs. For each dataset, FS corresponding inputs evaluated using commercial software Slide2. As illustration, proposed applied hypothetical embankment example subjected water level changes. comparison, predictive performance CatBoost, LightGBM, XGBoost investigated. Moreover, Shapley additive explanations (SHAP) method used this explore relative importance features. Results show that all three algorithms (i.e., XGBoost) perform well prediction both training dataset testing dataset. Among influencing factors, friction angle φ most important feature variable, followed horizontal coefficient K h , cohesion c saturated permeability k s .

Language: Английский

---

Efficiency of convolutional neural networks (CNN) based image classification for monitoring construction related activities: A case study on aggregate mining for concrete production

Case Studies in Construction Materials, Journal Year: 2022, Volume and Issue: 17, P. e01372 - e01372

Published: Aug. 6, 2022

Monitoring construction activities is an important task for efficiency in site operations thus the topic received a fair amount of attention literature. Optimizing by monitoring and detecting various tasks dependent on size field, which determines tools that can be used job. A performed with high through image classification algorithms training to detect machinery. If area larger, such as related large infrastructural construction, using drone images might become inefficient. We aimed take first step towards cost-efficient system specifically cover territories. Consequently, satellite has been machinery detection this study. utilized different versions well-established convolutional neural network architectures backbone transfer learning method their performances are evaluated. Finally, best performing models determined DenseNet161 ResNet101 0.919 0.903 test accuracies, respectively. model was discussed terms its accuracy case study illegal aggregate mining activity basin Thamirabarani River.

Language: Английский

---