Semester of Graduation
Summer 2026
Degree Type
Thesis
Degree Name
Master of Science in Information Technology
Department
Information Technology - College of Computing and Software Engineering
Committee Chair/First Advisor
Dr. Nazmus Sakib
Second Advisor
Dr. Maria Valero
Third Advisor
Dr. Liang Zhao
Abstract
Alzheimer’s disease and related dementias (ADRD) present significant safety challenges, as affected individuals may experience falls, wandering, agitation, and a progressive decline in independence. Although continuous monitoring can enable timely intervention, many existing systems rely on cameras or wearable devices, which may introduce concerns related to privacy, comfort, and sustained use. This thesis explores privacy-preserving and non-intrusive remote monitoring through two complementary studies. The first study presents an ambient Wi-Fi channel state information framework for recognizing agitation and eight daily activities. The proposed approach translates behavioral and physiological markers commonly captured by wearable sensors into the Wi-Fi sensing domain. The framework achieved an overall accuracy of 52.9%, demonstrating the feasibility of contactless agitation monitoring while identifying opportunities for improved data collection, feature representation, and model development. The second study introduces a 60–64 GHz multiple-input multiple-output radar dataset collected from six standardized patients portraying movement patterns associated with AD/ADRD. To improve generalizability across sensing environments and participant groups, a multi-source domain adaptation approach integrated public 5.8 GHz radar data, 60–64 GHz data from healthy volunteers, and standardized patient simulations. Under leave-one-subject-out validation, the proposed model achieved 98.2% accuracy, 98.5% sensitivity, and 98.1% specificity in fall classification. Collectively, these studies demonstrate the potential of ambient Wi-Fi and radar sensing as complementary technologies for privacy-conscious monitoring in dementia care. The findings provide a foundation for scalable systems that can improve patient safety, support timely caregiver response, and reduce the burden associated with continuous supervision
Comments
Dr. Sumit Chakravarty also served as a member of this thesis committee.