Multi-modal Sensing for Human Motor Understanding: From Clinic to the Field

PhD Thesis Proposal Defence


Title: "Multi-modal Sensing for Human Motor Understanding: From Clinic to the Field"

by

Mr. Baichen YANG


Abstract:

Human motor function provides a behavioral window into health and functional 
ability, spanning speech, breathing, gait, and athletic movement. The growing 
need for daily and field motor assessment has highlighted limitations in 
conventional approaches, which often rely on prescribed clinical behaviors, 
specialized laboratory devices and controlled environments. This thesis 
addresses these limitations by developing multi-modal mobile sensing systems 
that enable motor assessment beyond clinics and laboratories. We overcome 
critical challenges including (i) the difficulty in extracting subtle 
features from natural behaviors (PDAssess), (ii) the information loss in non- 
standard daily assessment protocol (EasySpiro), (iii) the inter-subject 
heterogeneity in motor functions (KneeGuard), and (iv) the signal degradation 
from high-dynamic field constraints (ACLGuard). By leveraging acoustic and 
biomechanical sensing with learning-based and domain-guided modeling, this 
thesis demonstrates that clinically meaningful motor biomarkers can be 
recovered from low-burden sensing systems. Collectively, these contributions 
enable a multi-modal sensing paradigm that brings clinical assessment to 
daily/field setups.


Date:                   Thursday, 21 May 2026

Time:                   10:00am - 12:00noon

Venue:                  Room 2128B
                        Lift 19

Committee Members:      Prof. Qian Zhang (Supervisor)
                        Prof. Gary Chan (Chairperson)
                        Dr. Xiaojuan Ma