Ali Abbasi

About

Ali Abbasi is a rising researcher in biomedical engineering and human-machine interaction, focusing on the intersection of deep learning and neuromuscular control. His work centers on developing intelligent, attention-driven neural network models to decode complex human movement from surface electromyogram (sEMG) signals. Abbasi’s major contribution lies in advancing continuous, cross-subject estimation of knee joint kinematics—specifically during dynamic activities like running. His most cited paper (2023, 11 citations) introduces an efficient attention-driven deep neural network for real-time knee angle estimation, while a companion study (2023, 3 citations) employs an attention-based bidirectional LSTM model to achieve robust, subject-independent performance. These innovations are critical for improving human-machine interfaces that control rehabilitation robots, enabling more natural and responsive motor function restoration. By tackling the challenge of accurate joint angle prediction during high-impact movements, Abbasi’s work bridges the gap between neural signal processing and practical assistive technology, offering a pathway toward smarter, adaptive prosthetics and exoskeletons. His research is gaining traction for its potential to transform clinical rehabilitation and athletic performance monitoring.

Research Focus

Key Achievements

Top Papers

1. 1
   An efficient attention-driven deep neural network approach for continuous estimation of knee joint kinematics via sEMG signals during running

   11 citations · 2023
2. 2
   An Attention-based Bidirectional LSTM Model for Continuous Cross-Subject Estimation of Knee Joint Angle during Running from sEMG Signals

   3 citations · 2023

Key Collaborators

Contact & Links