This study presents a three-dimensional finite element (FE) analysis of the human foot bone structure under mid-stance loading during race walking. A subject-specific biomodel comprising 26 bones and over 40 ligaments was reconstructed from computed tomography (CT) data using Materialise Mimics Research 21.0 and 3-Matic Research 13.0, and subsequently analyzed in ANSYS Workbench 2024 R1. The model included explicit cortical, trabecular, and ligamentous volumes, each assigned linear-elastic, isotropic material properties based on biomechanical literature data. Boundary conditions simulated the mid-stance phase of race walking, applying a distributed plantar pressure of 0.25 MPa over the metatarsal and phalangeal regions. Numerical simulations yielded maximum total displacements of 0.00018 mm, maximum von Mises stresses of 0.171 MPa, and maximum strains of 2.5 × 10⁻⁵, all remaining well within the elastic range of bone tissue. The results confirm the model’s numerical stability, geometric fidelity, and capacity to represent physiologically realistic loading responses. The developed framework demonstrates the potential of high-resolution, image-based finite element modelling for investigating stress–strain patterns of the foot during athletic gait, and establishes a reproducible reference for future analyses involving pathological gait, orthotic optimisation, and musculoskeletal load assessment in sports biomechanics.

Background/Objectives: Human gait analysis is essential for identifying biomechanical alterations associated with pathological conditions. However, conventional laboratory systems that combine optical motion capture and force plates remain costly, space-demanding, and difficult to implement in routine or accessible settings. This study proposes a dual-model artificial intelligence framework designed to bridge kinematics and dynamics and subsequently support gait health-status classification from motion data. Methods: The first model was developed to estimate ground reaction forces (GRF) and center of pressure (CoP) signals from kinematic inputs. Public datasets containing synchronized kinematics and dynamics were used to train and evaluate long short-term memory (LSTM) and one-dimensional convolutional neural network (CNN1D) architectures. A robustness stage further adapted the dynamic prediction model to markerless-like kinematic inputs through domain-adaptation training. The second model was implemented as a multichannel convolutional classifier using normalized GRF/CoP signals and metadata. Three variants were compared: signals only, signals with minimal metadata, and signals with rich metadata. Finally, a bridge block connected both models, and a proof-of-concept deployment was performed using markerless kinematics obtained with Move AI and Blender. Results: The final dynamic prediction model achieved an overall RMSE of 0.0676, with reconstructed-signal RMSE of 0.0500 and reconstructed contact accuracy of 0.9736. The best classification variant achieved a balanced accuracy of 0.9608, while the minimal-metadata variant was selected for pipeline integration due to its compatibility with accessible data acquisition. In the full pipeline evaluation, the predicted dynamics correctly classified the healthy-control samples. In the Move AI/Blender proof-of-concept, all five healthy participants were classified as healthy controls, with a mean non-pathological classification probability consistent with this outcome. Conclusions: The proposed dual-model framework demonstrates the operational feasibility of linking kinematic acquisition, dynamic prediction, and gait classification within a single artificial intelligence pipeline. The Move AI/Blender stage represents a preliminary proof of concept rather than clinical validation, and further evaluation with pathological participants and synchronized force-plate measurements is required.

El lavado industrial de botellas de vidrio es esencial para las industrias de alimentos y bebidas, asegurando la limpieza y la sanitización de los envases. Asimismo, manteniendo la calidad del producto final. Sin embargo, este proceso consume grandes cantidades de agua, planteando desafíos significativos para la sostenibilidad y conservación de recursos hídricos. La propuesta del sistema diseñado y fabricado que se presenta en este trabajo, es completamente automático y es capaz de manipular variables, como; velocidad de motores, tiempo de cepillado y enjuague. Esta línea de lavado, actualmente procesa 720 botellas por hora, reduciendo significativamente el consumo de agua, en comparación con métodos tradicionales. Así como, se aplicaron tecnologías avanzadas de automatización y programación, con el objetivo principal de mejorar la eficiencia y sostenibilidad del proceso.