Soroosh Shahtalebi
Papers
3
Total Citations
22
H-Index
2
About
Soroosh Shahtalebi is a researcher at the forefront of assistive and rehabilitation technologies, specializing in the characterization and extraction of pathological hand tremor (PHT). His work addresses a critical need for patients with neurological movement disorders like Parkinson’s disease and essential tremor. Shahtalebi’s major contributions lie in developing advanced signal processing and deep learning frameworks to filter and predict involuntary hand motion in real-time. His most cited work, "HMFP-DBRNN: Real-Time Hand Motion Filtering and Prediction via Deep Bidirectional RNN" (2019, 17 citations), introduces a deep bidirectional recurrent neural network that fuses multimodal data to accurately separate tremor from voluntary movement, a key requirement for robotic rehabilitation and assistive devices. He has also proposed a multi-rate, auto-adjustable wavelet decomposition method for tremor extraction, demonstrating a systematic approach to improving clinical assessment and treatment evaluation. Though early in his career, Shahtalebi’s research has already influenced the design of intelligent, adaptive systems that can enhance the quality of life for individuals with movement disorders, bridging the gap between neural signal processing and practical rehabilitation engineering.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3