AI system predicts human motion for autonomous telerehabilitation

Researchers have developed a novel telerehabilitation system that combines skeletal motion prediction with joint-level performance assessment. This system uses a self-attentive Bidirectional LSTM for exercise quality classification and a graph-based module for predicting per-joint position errors. The classifier achieved 96.45% accuracy on the PROZIS dataset, while the predictor reached a mean MPJPE of 75.8 mm on Human3.6M, outperforming existing baselines. This framework aims to provide accessible and scalable rehabilitation solutions by enabling autonomous, feedback-driven telerehabilitation. AI

IMPACT This system could improve accessibility and scalability of rehabilitation services through autonomous, feedback-driven solutions.

RANK_REASON The cluster contains an academic paper detailing a new system for telerehabilitation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Human3.6M
• MMD-NCA
• PROZIS

• paper
• product
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →