Traditional music learning path recommendation systems often fail to model multidimensional correlations within knowledge structures, resulting in incomplete path coverage and limited adaptability. This study proposes a learning path optimization system integrating GraphSAGE and Dueling DQN. A heterogeneous music knowledge graph is first constructed to represent knowledge points, skills, styles, and their prerequisite or coupling relationships. GraphSAGE with an LSTM aggregator is then used to dynamically fuse multimodal features into unified node embeddings. On this basis, the Dueling DQN algorithm uses cognitive state vectors, including mastery level and cognitive load, to optimize path strategies under coverage-gain and load-penalty constraints. Experiments show that the recommended paths achieve 89.6% knowledge coverage with an average length of 12.4 steps for beginners. Compared with standard DQN, Dueling DQN improves coverage by 3.3%. The system increases the path completion rate of beginners to 94.2%, outperforming traditional models such as DySAT, and achieves an average ABRSM score of 128.3. By combining heterogeneous graph modeling with reinforcement learning, the proposed framework improves path coverage, reduces route redundancy, and may provide methodological reference for graph-based optimization in electromagnetic-system training and wireless network planning.
Martial arts routines are highly dynamic, multi-pose, and fast-paced, posing significant challenges to automated recognition and scoring. Such complex spatiotemporal characteristics are also representative of intelligent sensing tasks in advanced electromagnetic-aware environments, where robust human motion perception is essential for integrated visual and wireless monitoring systems. This paper proposes a joint framework combining YOLOv8 and time-optimized OpenPose to mitigate pose estimation jitter and detection inaccuracies caused by rapid motion and occlusion in human motion analysis. YOLOv8 first performs high-precision human target detection using bounding boxes to define regions of interest, after which the cropped images are processed by OpenPose to extract 17 keypoints, with IoU matching ensuring cross-frame identity association for temporal consistency. The keypoint sequence is modeled as a multi-channel time series and refined through a bidirectional LSTM network to predict smooth pose trajectories. The optimized keypoints are further used to calculate joint angles and movement velocities, which are integrated with dynamic thresholds for motion segmentation. DTW-based alignment and similarity matching with a standard motion library are subsequently employed to evaluate posture accuracy, motion amplitude, and rhythmic consistency, producing a comprehensive scoring result. Experimental results demonstrate average mAP@0.5 values of 0.863–0.942 (FPS 115.2–124.3), average PCK values of 88.7%–90.3% under occlusion (average MPJPE 48.2–51.6 pixels), and Pearson correlation coefficients of 0.925–0.941 for scoring consistency across diverse martial arts routines. The proposed framework provides an effective solution for intelligent motion analysis and offers technical reference for multimodal perception and dynamic scene understanding in advanced electromagnetic sensing applications.
D. Zhao, Y. Q. Ma· Advanced Electromagnetics· 0 citations
