Permanent supportive housing is an evidence-based approach to addressing homelessness that involves access to community-based housing combined with supportive services, such as access to physical and mental health information and care. Little research has examined technological innovations for providing services in housing for vulnerable populations. This interdisciplinary community-based project brings together investigators from computer science and engineering, public health, and social work, and two large housing initiatives in Southern California. The research team is investigating the social and technical challenges of adopting sensor-based technologies, such as tele-mental health services. The project team is exploring the issues using a combination of surveys and an innovative "lean design" approach. Lean design refers to developing a solution in an iterative way with rapid development of prototypes that can be quickly evaluated and the lessons learned applied to the next iteration. This approach includes the community partners in the design and evaluation of technology prototypes.
The project investigates the social and engineering dimensions of three key technologies that can significantly impact how services are delivered: (1) minimally intrusive environment and user-borne sensors to facilitate tele-mental health services and increase safety, (2) privacy-preserving data sharing algorithms that can be tuned to meet the expectations of multiple stakeholders, and (3) mobile user interfaces for accessing the Internet and remote services. Tunable privacy-preserving data sharing algorithms accommodate the different preferences of the multiple stakeholders in permanent supportive housing. The project identifies the social and technological factors that affect the successful use of remote services and combines them into a general model for predicting when tele-services can be effective. This project will lay the groundwork for community-based research to help meet the mental health needs of PSH residents and influence the design of supportive housing units.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
Abstract
Anand Panangadan
Dr. Anand Panangadan is Associate Professor of Computer Science. He conducts research at CSUF with undergraduate and graduate students in applications of artificial intelligence and machine learning. He is applying techniques from these fields to problems in homelessness, transportation, healthcare, earth science, sensor networks, and robotics. He is also interested in automated analysis of online social media communications for understanding spread of beliefs related to public transportation. He has published over 50 peer-reviewed conference papers and journal articles. He holds two US patents on sensor data processing. He is the Principal Investigator on grants from NSF, USDA, Air Force Research Laboratory, and University of California Center on Economic Competitiveness in Transportation (US Department of Transportation and Caltrans). He has received education-related grants from Cisco Systems and GE Digital. He received the Course Redesign with Technology grant from the CSU Chancellor’s Office and Research, Scholarship and Creative Activity (RSCA) Incentive Grants from CSU Fullerton. He has received the FDC Faculty Recognition in Teaching, Faculty Advisor of Distinction, and Faculty Recognition of Extraordinary and Sustained Service awards at CSUF. He is a recipient of the NASA Space Act Award. Prior to his appointment at CSUF, he was a Senior Research Associate at University of Southern California, a Post-doctoral Affiliate at the NASA Jet Propulsion Laboratory (JPL), and a Research Specialist at the Children’s Hospital Los Angeles.
Performance Period: 10/01/2021 - 09/30/2024
Institution: California State University-Fullerton Foundation
Award Number: 2125654
Project Material
Posters
Partners
Mercy House