CRIS :: Universidad UTE

Now showing 1 - 3 of 3

Some of the metrics are blocked by your
consent settings
Prediction of consolidation behavior of modified clayey soil reinforced with artificial geo-fibers using explainable artificial intelligence
(Elsevier BV, 2026-04)
Mohammed Faisal Noaman
;
Moinul Haq
;
Sanjog Chhetri Sapkota
;
Mehboob Anwer Khan
;
Kausar Ali
The present study illustrates an experimental, machine learning (ML), and explainable artificial intelligence integrated framework for the prediction of swelling pressure and consolidation characteristics of polypropylene geo-fiber (PPGF) reinforced clayey soil. A dataset of laboratory consolidation tests that included PPGF content, coefficient of consolidation (Cv), coefficient of compressibility (av), compression index (Cc), coefficient of volume change (mv), settlement (S), and swelling pressure values (ps) was compiled. The experimental observations revealed that the Cc, mv, and S was averagely decreased by about 39.5%, 45.31%, and 90%, respectively, at the optimum PPGF content of 0.3%, thus demonstrating the effectiveness of reinforcing fibers in restraining time-dependent deformation. Six machine learning models, including KNN, SVM, ANN, DT, RF, and XGB, were developed using five folds cross-validation. The XGB regressor proved to have the best predictive performances, having an R2 of 0.994 (with RMSE of 3.14) on training and generalizability in testing, with an R2 of 0.913 (having RMSE of 14.05). The remaining models demonstrated comparatively weaker performance, with ANN and DT exhibiting pronounced overfitting, while KNN and SVM failed to adequately capture the nonlinear swelling response of the gels. The XAI analysis using SHAP indicates that polypropylene geofiber content is the most influential factor governing swelling pressure, followed by mv and soil compressibility. An interactive graphical user interface was built based on the optimized XGB model to predict and visualize swelling pressure in real time from given user inputs. The proposed model integrates experimental validation with robust predictive capability and interpretability, and is complemented by a user-friendly interface and a reliable decision-support system for geotechnical design and soil improvement.
Some of the metrics are blocked by your
consent settings
Delamination, frequency, and bending analysis of GPLRC curved panel with initial crack via machine learning and three-dimensional layerwise theory
(Elsevier BV, 2025-12)
Xinrong Cao
;
Xiaohong Yang
;
Linyuan Fan
;
HABIBI, MOSTAFA
;
Ibrahim Albaijan
In the present study, the thermal stability of graphene-reinforced composite laminates (GPL-RC) with diverse functional gradients and width delamination layers is examined. In this regard, various models of laminated GPL-RC are considered with different geometrical and material parameters. Utilizing the physics-informed neural networks (PINN), we calculate the energy release rate (ERR) at the cleavage boundary, aiming to gauge cleavage growth potential. This study also delves effects of various graphene reinforcement distributions and delamination configurations on the vibrational attributes of delaminated GPL-RC sheets, with an emphasis on pre/post heat bending modalities. Solutions are grounded in the third-order shear strain theory (TSDT), integrating von Karman geometric nonlinearity. Using the principle of minimal potential energy, the nonlinear equilibrium equations are tackled using PINN. Theoretical insights obtained are verified via a comparison to other published studies. Notably, parametric experiments indicate that the ERR in the FGX configuration in which most reinforcement material located adjacent to the upper and lower surfaces of the plate, is double that of the FGA, in which most reinforcement material adjacent to the lower surface of the plate. Moreover, while the FGX sheet's fundamental frequency surpasses other graphene configurations at the primary temperature, its natural frequency in the post-buckling modality is notably the least compared to the entire sample set.
Some of the metrics are blocked by your
consent settings
Supervised learning for improving the accuracy of robot-mounted 3D camera applied to human gait analysis
(Elsevier BV, 2024-02)
GUFFANTI MARTINEZ, DIEGO ANDRES
;
Alberto Brunete
;
Miguel Hernando
;
David Álvarez
;
Javier Rueda
Background and Objective: the use of 3D cameras for gait analysis has been highly questioned due to the low accuracy they have demonstrated in the past. The objective of the study presented in this paper is to improve the accuracy of the estimations made by robot-mounted 3D cameras in human gait analysis by applying a supervised learning stage. Methods: the 3D camera was mounted in a mobile robot to obtain a longer walking distance. This study shows an improvement in detection of kinematic gait signals and gait descriptors by post-processing the raw estimations of the camera using artificial neural networks trained with the data obtained from a certified Vicon system. To achieve this, 37 healthy participants were recruited and data of 207 gait sequences were collected using an Orbbec Astra 3D camera. There are two basic possible approaches for training and both have been studied in order to see which one achieves a better result. The artificial neural network can be trained either to obtain more accurate kinematic gait signals or to improve the gait descriptors obtained after initial processing. The former seeks to improve the waveforms of kinematic gait signals by reducing the error and increasing the correlation with respect to the Vicon system. The second is a more direct approach, focusing on training the artificial neural networks using gait descriptors directly. Results: the accuracy of the 3D camera to objectify human gait was measured before and after training. In both training approaches, a considerable improvement was observed. Kinematic gait signals showed lower errors and higher correlations with respect to the ground truth. The accuracy of the system to detect gait descriptors also showed a substantial improvement, mostly for kinematic descriptors rather than spatio-temporal. When comparing both training approaches, it was not possible to define which was the absolute best. Conclusions: supervised learning improves the accuracy of 3D cameras but the selection of the training approach will depend on the purpose of the study to be conducted. This study reveals the great potential of 3D cameras and encourages the research community to continue exploring their use in gait analysis.

CRIS

Browse

Filters

Settings

Sort By

Results per page

Search Results