Author/Creator ORCID




Computer Science and Electrical Engineering


Computer Science

Citation of Original Publication


This item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please see http://aok.lib.umbc.edu/specoll/repro.php or contact Special Collections at speccoll(at)umbc.edu
Distribution Rights granted to UMBC by the author.
Access limited to the UMBC community. Item may possibly be obtained via Interlibrary Loan thorugh a local library, pending author/copyright holder's permission.



Today's healthcare system is seeing rapid technological advancements with the availability of vast amounts of information and computing resources. This has led to important developments in the field of smart healthcare for disease prevention and monitoring, diagnosis and treatment, hospital management, and health decision making. Smart healthcare utilizes technology such as internet of things (IoT) and enables physical sensing to collect information that can be processed and intelligently acted on to improve one's health. IoT devices have been used for monitoring physical health such as heartbeat, respiration, and sleep activities to name a few. Devices that must be worn for health monitoring can be uncomfortable and pose health concerns as they are potential carriers of bacteria and viruses. On the other hand, non-contact sensing is advantages by preventing the spread of bacteria and viruses as nothing is worn or touched. However, designing smart health systems that utilize non-contact sensing can be challenging due to environmental factors like noise, obstructions, and multiple people. Thus, in this dissertations we contribute to the field of smart healthcare by showing how useful radar is for non-contact sensing. We showed how radar can preserve privacy, provide continuous monitoring, travel through material and obstructions, sense multiple people, and work well in challenging environments. These advantages are explored through three smart healthcare applications using radar-based non-contact sensing. Our applications use CW and FMCW radar for sensing and machine learning for thinking and driving intelligent decisions. We show how radar-based non-contact sensing systems can be deployed in the operating room for gesture control and at home to monitor coughing, sneezing, and medication tampering with high accuracy. Our three applications are built end-to-end and provide new ways for interaction and monitoring of health.