skip to Main Content

University of Hawaii

Electrical Engineering

A Non-Contact Continuous Identity Authentication in Multiple-Subject Environments

Date: 2019-05-02           Add to Google Calendar
Time: 2:00PM-4:00PM
Location: Holmes Hall 389
Speaker: Shekh Md Mahmudul Islam


†††† An unobtrusive and non-contact continuous authentication system can potentially improve security throughout a login session. Traditional user authentication procedures such as fingerprint, password, or facial identification typically provide only an initial spot-check of identity at the start of a user session, potentially allowing undesired access to personal information (e. g. social security number) at some later point in an apparently continuous user session. The research goal is to create a non-contact continuous authentication system based on Doppler radar, which analyzes back-scattered RF signals which carry body motion information indicating a human subjectís vital signs (breathing rate, heart rate) and associated unique patterns. An additional advantage to this radar technique is that continuous authentication is achieved without intrusive video imaging. Reported prior results are focused solely on use of respiratory motion to identify a single isolated subject. Simultaneous measurement of multiple subject is a critical challenge. In realistic environments (home, airport security, etc.) the presence of multiple subjects in front of the radar system is likely. To make this technology effective into the real world, isolation of one particular subjectís breathing pattern from their combined mixture of motion for multiple subjects is essential.†

†††† This presentation will describe research on investigation on separation methods for individual respiratory signatures from a combined mixture of radar captured breathing motion for multiple subjects. A 24-GHz phase comparison Monopulse radar module (K-MC4) has been integrated with a system to estimate the Direction of Arrival (DOA) for the physiological motion signals of well-spaced subjects at the edge of the beamwidth of the transceiver. DOA is inherently limited to the main beamwidth of the transceiver so when the subjects get closer, crossing the edge of the beamwidth, an additional Independent Component Analysis with the JADE Algorithm (ICA-JADE) process has been integrated to isolate individual respiratory signatures. Experimental results have demonstrated that when subjects are close to the radar and closely spaced, then the ICA-JADE method can efficiently separate two distinct respiratory signatures from two subjects. Furthermore, when subjects are well-spaced (at the edge of the beamwidth) the phase comparison monopulse technique takes over to estimate the angle of arrival more accurately. This method can be scaled to work for larger number of subjects, by scanning an area and first isolating subjects or groups by DOA and then further isolating subjects through ICA-JADE.