A Lightweight Skeleton-Based Human Motion Correctness Detection Framework for Mechatronic Perception
Human motion perception is an important function in intelligent electromechanical systems, especially in human-computer interaction, rehabilitation training, and safety monitoring. Existing skeleton-based deep learning methods can model spatial and temporal motion patterns, but they usually require large datasets and relatively high computational resources. This limits their use in small-sample and lightweight deployment scenarios. This study examines whether compact temporal features extracted from skeleton coordinates can be used for efficient correctness detection of human movements. A cross-subject skeleton motion dataset containing 2,589 samples was used, and the task was to classify actions as correct or incorrect. Three coordinate-based feature representations were compared: flattened original XY coordinates, flattened standardized XY coordinates, and XY- based temporal statistical features. A graph-based ST-GCN model was also introduced as a deep learning baseline. The results show that the XY temporal statistical features achieved the best overall performance with only 400 features, reaching a balanced accuracy of 0.8061 and a macro F1 score of 0.7985. Under the same evaluation conditions, this method outperforms the two coordinate flattening representation methods as well as the ST-GCN baseline model. These findings indicate that lightweight statistical features can provide an efficient and interpretable method for motion accuracy assessment in electromechanical systems.