Human action recognition has been applied in many fields, such as video surveillance and human computer interaction, where it helps to improve performance. Numerous reviews of the literature have been done, but rarely have these reviews concentrated on skeleton-graph-based approaches. Connecting the skeleton joints as in the physical appearance can naturally generate a graph. This paper provides an up-to-date review for readers on skeleton graph-neural-network-based human action recognition. After analyzing previous related studies, a new taxonomy for skeleton-GNN-based methods is proposed according to their designs, and their merits and demerits are analyzed. In addition, the datasets and codes are discussed. Finally, future research directions are suggested.
Recognizing human actions can help in numerous ways, such as health monitoring, intelligent surveillance, virtual reality and human–computer interaction. A quick and accurate detection algorithm is required for daily real-time detection. This paper first proposes to generate a lightweight graph neural network by self-distillation for human action recognition tasks. The lightweight graph neural network was evaluated on the NTU-RGB+D dataset. The results demonstrate that, with competitive accuracy, the heavyweight graph neural network can be compressed by up to . Furthermore, the learned representations have denser clusters, estimated by the Davies–Bouldin index, the Dunn index and silhouette coefficients. The ideal input data and algorithm capacity are also discussed.
Dynamic errors in robotic machining can degrade part quality, particularly in flexible platforms that are susceptible to both geometric and inertial disturbances. This work introduces a data-driven digital twin for pointwise prediction of circular trajectory errors in a hexapod-based machining cell, using a compact sensing configuration that combines ballbar measurements with tri-axial vibration signals. Deviations measured by ballbar, acceleration data, and CMM-measured profiles are synchronized in the angular domain via a unified pipeline for denoising, resampling, and phase alignment. Sliding-window vibration statistics and the ballbar path error are used as inputs to XGBoost, multilayer perceptron, and random forest regressors. Model performance is evaluated under a deployment-relevant leave-one-run-out protocol and a conventional random 70:30 point split. XGBoost achieves micrometer-level accuracy on unseen runs, with RMSE around 5 µm, R2 exceeding 0.80, and near-complete coverage within a ±20 µm tolerance band. Compared to baseline models, it also provides improved suppression of extreme residuals. Feature importance and ablation studies show that the ballbar path error captures the dominant geometric component, while compact hybrid feature sets—combining this anchor with selected vibration descriptors—retain most of the predictive accuracy and enable practical offline batch-level compensation.
31 March 2025 in CIRP Journal of Manufacturing Science and Technology
The resolution of the products of numerical weather prediction is limited by the resolution of numerical models and computing resources, which can be improved accurately by a well-chosen interpolation algorithm. This paper is intended to improve the accuracy of spatial interpolation towards wind fields. A new composited multi-scale anisotropic kernel function for weather processes using two-dimensional space information is proposed. To fix the underfitting in this kernel caused by unilateral space information, multiple variables (wind direction, air temperature, and atmospheric pressure) are introduced, which generates a multivariate correction model based on the novel kernel function and Gaussian process regression. Focusing on different weather processes, two multivariate correction models are designed. The new models pave a new way to employ multi-scale local information, and extract the anisotropy and structure information. The experiments on 10 m wind fields for the weather processes without cyclones and for the weather processes with cyclones validate the efficiency. The mean RMSE of the multivariate correction model for the weather processes without cyclones is reduced by around 15% for the u wind component compared with that of a simple composited kernel. For the weather processes with cyclones, the mean RMSE of the novel model declines by around 55% compared to that of spline, and by about 95% compared to that of back propagation neural networks.