Explore the vast range of titles available.

Objective To use routine demographic and clinical data to develop an interpretable individual-level machine learning (ML) model to diagnose knee osteoarthritis (KOA) and to identify highly ranked features. Methods In this retrospective, population-based cohort study, anonymized questionnaire data was retrieved from the Wu Chuan KOA Study, Inner Mongolia, China. After feature selections, participants were divided in a 7:3 ratio into training and test sets. Class balancing was applied to the training set for data augmentation. Four ML classifiers were compared by cross-validation within the training set and their performance was further analyzed with an unseen test set. Classifications were evaluated using sensitivity, specificity, positive predictive value, negative predictive value, accuracy, area under the curve(AUC), G-means, and F1 scores. The best model was explained using Shapley values to extract highly ranked features. Results A total of 1188 participants were investigated in this study, among whom 26.3% were diagnosed with KOA. Comparatively, XGBoost with Boruta exhibited the highest classification performance among the four models, with an AUC of 0.758, G-means of 0.800, and F1 scores of 0.703. The SHAP method reveals the top 17 features of KOA according to the importance ranking, and the average of the experience of joint pain was recognized as the most important features. Conclusions Our study highlights the usefulness of machine learning in unveiling important factors that influence the diagnosis of KOA to guide new prevention strategies. Further work is needed to validate this approach.

We propose Reinforcement Learning Contrastive Optimization (RLCO), a novel quadruped robot locomotion control framework that synergistically integrates contrastive learning with reinforcement learning. This framework addresses two critical limitations of existing reinforcement learning methods in quadruped motion control: low sample efficiency and insufficient stability in action sequences. To meet the temporal coherence requirements of motion policies in complex environments, we develop a history–prediction action alignment mechanism through contrastive learning. This approach ensures that an action sequence is consistent over time. It does this by reducing the difference between past actions and predicted actions. This approach greatly enhances the stability and reliability of motion control. The proposed co-optimization mechanism preserves reinforcement learning’s exploration capability for complex tasks while improving the physical plausibility and predictability of action sequences. Experimental results demonstrate that our method achieves notable improvements in motion control precision and environmental adaptability in unstructured terrains. Through comparative analysis of different training strategies, we systematically validate the effectiveness of the RLCO framework. Field tests in outdoor environments with stairs, slopes, and grassy terrain confirm the robot’s capabilities. The quadruped robot rapidly adapts to diverse ground conditions.

Data-driven surrogate models have become increasingly important in aerospace engineering for the rapid prediction of aerodynamic characteristics. However, when modelling aerodynamic data with varying flight conditions and complex shape parameters, traditional surrogates - such as kriging and fully connected neural network (FCNN) - face major challenges, including high dimensionality, large variable disparities, and limited data availability. Specifically, kriging models suffer from inefficient training processes, while FCNN models struggle with diminished prediction accuracy when confronted with diverse input sets. To address these challenges, this paper introduces two improved surrogate models by incorporating variable sensitivity into the kriging and FCNN models. They employ the analysis of variance to identify the global sensitivity of input variables and utilise K-means clustering to group variables based on their sensitivities. For the kriging model, auxiliary parameters corresponding to the number of clusters are introduced to replace hyperparameters, accelerating model training while maintaining high accuracy. For the FCNN model, input variables are grouped based on their sensitivities, with specialised expert networks handling each group, and a gating network combining their outputs to improve prediction accuracy. The effectiveness of these methods is demonstrated through numerical function examples and two aerodynamic data modelling scenarios: the FDL-5A hypersonic vehicle and the Saenger aerospace plane carrier wing. Results indicate that the proposed approaches significantly enhance the kriging model's training efficiency, achieving a 98% reduction in hyperparameter tuning time compared to conventional method, with minimal sacrifice in accuracy. Simultaneously, the modifications to the FCNN model not only improve its prediction accuracy but also increase its overall practical utility in engineering applications.