A central focus of the lab is the development of robust signal-processing pipelines and intelligent computational frameworks for extracting meaningful features from complex and often noisy biosignals. We employ advanced techniques from digital signal processing, statistical modeling, and machine learning—including deep learning approaches—to interpret physiological data with high accuracy and reliability. These methodologies enable us to identify patterns, assess functional recovery, and derive clinically relevant insights that can support diagnosis, monitoring, and therapeutic interventions. 

Positioned at the intersection of biomedical engineering, applied physiology, and computational intelligence, the BSRR Lab addresses critical challenges in rehabilitation science. Our research is driven by practical and translational questions: How can recovery be quantified more precisely and objectively? How can assistive and rehabilitative devices be controlled in a more intuitive and human-centric manner? And how can rehabilitation protocols be adapted dynamically to suit individual patient needs? 

Through this work, we aim to contribute to the development of personalized, data-driven rehabilitation systems that enhance patient outcomes, improve quality of life, and support clinicians in delivering more effective and responsive care. The lab also actively fosters collaboration across disciplines, encouraging innovation at the convergence of engineering, medicine, and human-centered design