Photovoltaic power plant outputs depend on the daily global solar radiation (DGSR). The main issue with DGSR data is its lack of precision. The potential unavailability of DGSR data for several sites can be attributed to the high cost of measuring instruments and the intermittent nature of time series data due to equipment malfunctions. Therefore, DGSR prediction research is crucial nowadays to produce photovoltaic power. Different artificial neural network (ANN) models will give different DGSR predictions with varying levels of accuracy, so it is essential to compare the different ANN model inputs with various sets of meteorological stochastic variables. In this study, radial basis function neural network (RBFNN), long short-term memory neural network (LSTMNN), modular neural network (MNN), and transformer model (TM) are developed to investigate the performances of these algorithms for the DGSR prediction using different combinations of meteorological stochastic variables. These models employ five stochastic variables: wind speed, relative humidity, minimum, maximum, and average temperatures. The mean absolute relative error for the transformer model with input variables as average, maximum, and minimum temperatures is 1.98. ANN models outperform traditional models in predictive accuracy.

The pathogenesis of musculoskeletal disorders is closely associated with the cumulative damage and fatigue failure behavior of fibrous connective tissues under long-term repetitive loading. However, significant technological challenges remain in real-time dynamic monitoring of ligament fatigue life, particularly the lack of efficient computational mechanics modeling frameworks and precise assessment tools adaptable to real-world movement scenarios. The multimodal integrated framework for ligament fatigue life assessment was proposed in this study. First, the high-accuracy subject-specific musculoskeletal models were developed based on individualized medical imaging data. A coupled hyperelastic-viscoelastic constitutive model was incorporated to accurately characterize the nonlinear mechanical behavior of ligamentous tissues and their fatigue damage evolution under cyclic loading. Furthermore, by integrating continuum damage mechanics theory, a time-dependent cumulative damage evolution equation was established to systematically quantify the coupling relationship between fatigue failure probability and dynamic mechanical loading. In the data-driven prediction module, an innovative deep-learning model that integrates kinematic-dynamic coupling was developed. By integrating wearable inertial measurement units, the model enables real-time inversion of ligament loading force-fatigue failure states and prediction of fatigue life. This approach effectively overcomes the limitations of traditional mechanical modeling in long-term, multi-scenario dynamic monitoring, achieving high-precision and minimally invasive fatigue life evaluation of ligaments. The proposed computational framework breaks the static-loading constraints of conventional fatigue testing, achieving the dynamic biomechanical analysis and fatigue life prediction under real movement conditions. This work not only provides novel theoretical insights into the mechanisms and modeling of ligament fatigue damage, but also provides a generalizable tool for biomechanical injury prevention, rehabilitation planning, and soft tissue fatigue analysis in the musculoskeletal system.

Phase change materials (PCMs) serve as an efficient thermal energy storage mediums across a range of thermal systems, including solar distillations. The selection of an appropriate PCM candidate is a vital integration aspect that affects solar distillation performance. Therefore, the present research introduces a multi-criteria decision-making (MCDM) framework for identifying suitable PCM candidates for application in solar distillation systems. Evaluation indices include eighteen PCM alternatives and seven criteria, which were established from the literature. Criteria importance through intercriteria correlation (CRITIC) method was used to assign objective weights to the criteria, followed by the MAIRCA (multi-attributive ideal-real comparative analysis) approach to rank PCM alternatives. The proposed MCDM model suggests the suitability of paraffin wax followed by soy wax and beeswax PCMs for solar distillation applications, respectively. The comparative analysis, sensitivity analysis, and Kendall rank correlation effectively validated the rankings, demonstrating a robust positive correlation among the results. This study can serve as a preliminary step for experimental and simulation-based investigations aimed at optimizing the selection of PCM in the early stage, thereby reducing the time and costs associated with further analysis.

Background: Single-leg landing (SL) is an essential technique in sports such as basketball, soccer, and volleyball, which is often associated with a high risk of knee-related injury. The ankle motion pattern plays a crucial role in absorbing the load shocks during SL, but the effect on the knee joint is not yet clear. This work aims to explore the effects of different ankle plantarflexion angles during SL on the risk of knee-related injury. Methods: Thirty healthy male subjects were recruited to perform SL biomechanics tests, and one standard subject was selected to develop the finite element model of foot-ankle-knee integration. The joint impact force was used to evaluate the impact loads on the knee at various landing angles. The internal load forces (musculoskeletal modeling) and stress (finite element analysis) around the knee joint were simulated and calculated to evaluate the risk of knee-related injury during SL. To more realistically revert and simulate the anterior cruciate ligament (ACL) injury mechanics, we developed a knee musculoskeletal model that reverts the ACL ligament to a nonlinear short-term viscoelastic mechanical mechanism (strain rate-dependent) generated by the dense connective tissue as a function of strain. Results: As the ankle plantarflexion angle increased during landing, both the peak knee vertical impact force (p = 0.001) and ACL force (p = 0.001) decreased significantly. The maximum von Mises stress of ACL, meniscus, and femoral cartilage decreased as the ankle plantarflexion angle increased. The overall range of variation in ACL stress was small and was mainly distributed in the femoral and tibial attachment regions, as well as in the mid-lateral region. Conclusion: The current findings revealed that the use of larger ankle plantarflexion angles during landing may be an effective solution to reduce knee impact load and the risk of rupture of the medial femoral attachment area in the ACL. The findings of this study have the potential to offer novel perspectives in the optimized application of landing strategies, thus giving crucial theoretical backing for decreasing the risk of knee-related injury.

Background: Patients undergoing anterior cruciate ligament reconstruction (ACLR) are at high risk of osteoarthritis or secondary injuries, with abnormal knee contact forces (KCFs) identified as a key factor in joint degeneration. Traditional KCF assessment relies on expensive lab systems while advances in computer vision and AI now enable low-cost alternatives. However, currently available methods oversimplify knee mechanics and neglect compensatory movements, highlighting the urgent need for intelligent, real-time monitoring tools for personalized rehabilitation. Therefore, the aim of this study was to develop and validate an integrated, non-invasive framework for accurate KCFs prediction in ACLR patients during daily activities. We hypothesized that combining enhanced musculoskeletal modeling with a deep learning architecture incorporating spatiotemporal attention would improve the prediction accuracy across multiple movement tasks. Methods: This study simultaneously recorded three daily movements of 29 post-ACLR patients using both Vicon and OpenCap. Motion trajectories captured by Vicon were imported into OpenSim for musculoskeletal modeling and KCFs calculation. Dataset comprising OpenCap-derived kinematics and OpenSim-computed KCFs was used to train 3 learning models for the prediction of KCFs in ACLR patients across different movements. Results: Among three models, CNN-BiGRU-Attention model demonstrated the best predictive performance across all three movement tasks (R2walking = 0.973 ± 0.003, R2running = 0.982 ± 0.004, R2descending stairs = 0.951 ± 0.007). CNN and self-attention mechanism collectively enhanced the model's ability to capture key features in ACLR patients' movement data, thereby improving KCF prediction accuracy. Furthermore, for the three daily activities, all models showed superior KCFs prediction performance in running and stair-descent tasks compared to walking. Conclusion: The developed framework successfully achieved high-precision prediction of KCFs. This technological breakthrough not only provides a real-time quantitative tool for rehabilitation monitoring in patients with ACLR, but also facilitates a paradigm shift from static laboratory analysis to dynamic real-time monitoring, with broad application prospects in sports medicine, rehabilitation engineering.

The growing global demand for safe and sustainable freshwater production has fueled interest in solar distillation systems. Although solar stills offer environmentally friendly desalination solutions, their low productivity remains a major problem. The incorporation of nanofluids based on oxide nanoparticles has emerged as a promising approach to enhance the thermophysical performance and freshwater yield of solar stills. However, selecting the most suitable nanoparticle is challenging due to conflicting thermophysical, environmental, and economic criteria. To address this decision-making complexity, this study proposes a novel hybrid multi-criteria decision-making (MCDM) framework that integrates entropy and centroidous objective weighting methods with the “Multi-Attributive Ideal-Real Comparative Analysis” (MAIRCA) ranking technique. Twelve widely reported oxide nanoparticles (SiO2, Fe3O4, MgO, ZnO, CuO, Al2O3, GO, TiO2, Co3O4, CeO2, SnO2 and ZrO2) were evaluated against eight criteria: density, thermal conductivity enhancement, specific heat capacity, thermal expansion coefficient, cost, toxicity, stability, and compatibility with the container material. Entropy-centroidous weighting identified thermal conductivity (0.2962) and cost (0.1969) as the most influential criteria, while MAIRCA ranked GO first with a score of 0.0357, followed by Al2O3 (0.0363) and SiO2 (0.0411); ZnO ranked last with a score of 0.0582. Comparative validation across eleven established MCDM methods showed strong agreement, with Spearman correlation coefficients above 0.748, p-values below 0.05, while mean absolute error values not exceeding 1.83. Sensitivity analysis further confirmed that GO remained at the top position in almost all scenarios, except when the importance of thermal conductivity started to decrease compared to its actual weight, resulting in its replacement by Al2O3. The proposed framework provides a systematic and transparent decision-support tool for nanoparticle pre-screening in solar still applications. The entropy-centroidous-MAIRCA framework can be extended to a wide range of problems related to renewable energy and thermal management optimization.