Keshu Cai

About

Keshu Cai is a rising researcher in the field of biomedical engineering and human-machine interaction, with a primary focus on lower limb motion prediction using surface electromyography (sEMG). His work addresses the critical challenge of enabling intuitive control for wearable assistive devices, such as exoskeletons designed to reduce physical load for workers and soldiers. Cai’s major contributions center on developing advanced machine learning frameworks to decode complex neuromuscular signals. His most cited work, "sEMG-Based Lower Limb Motion Prediction Using CNN-LSTM with Improved PCA Optimization Algorithm" (2022), has garnered 93 citations for its novel integration of convolutional and recurrent neural networks with optimized feature extraction. He further advanced the field by combining independent component analysis with support vector regression for knee trajectory prediction (12 citations), tackling the persistent difficulty of achieving accurate, real-time signal prediction. Through these innovative algorithms, Cai is helping to bridge the gap between biological intent and robotic response, paving the way for more responsive and effective wearable technologies that can enhance human performance in demanding environments.

Research Focus

Key Achievements

Top Papers

1. 1
   sEMG-Based Lower Limb Motion Prediction Using CNN-LSTM with Improved PCA Optimization Algorithm

   93 citations · 2022
2. 2
   Prediction of knee trajectory based on surface electromyogram with independent component analysis combined with support vector regression

   12 citations · 2022

Key Collaborators

Contact & Links