Yinghu Peng
Papers
3
Total Citations
18
H-Index
2
About
Yinghu Peng is a rising researcher in biomedical engineering and human motion analysis, with a focus on integrating artificial intelligence with biomechanics for lower limb rehabilitation and assistive technologies. His key research areas include surface electromyography (sEMG) signal processing, muscle synergy modeling, and machine learning-driven prediction of joint biomechanics. Peng’s major contributions involve developing novel deep learning frameworks that enhance the accuracy and continuity of lower limb motion recognition. Notably, his 2024 work on integrating multiscale residual neural networks with Gramian angular fields for multi-channel sEMG-based movement recognition has already garnered 12 citations, demonstrating its early impact. He has also advanced the field of total knee arthroplasty by applying both conventional machine learning and deep learning to predict knee biomechanics under different tibial component malrotations, addressing a critical challenge in surgical alignment. His most recent 2025 study introduces a TimesNet method driven by muscle synergies for continuous motion pattern recognition, overcoming the limitations of gait-cycle-dependent approaches. Peng’s work bridges computational modeling and clinical application, offering promising pathways for intelligent prosthetics and personalized rehabilitation.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3