Emilia Farcas

Emilia Farcas, Ph.D., has research interests in software-engineering methodologies for managing the complexity of cyber-physical systems, focusing on modeling requirements, architectures, and service-oriented engineering, while addressing concerns such as governance and reliability. Her research is applied in various cyber-infrastructure projects at UC San Diego in the fields of health sciences and clinical trials, large-scale oceanographic observatories, and fail-safe automotive systems.

Farcas received her Ph.D. from the University of Salzburg, Austria, in 2006 in the area of component models, programming languages, and scheduling algorithms for real-time distributed systems. Her research on network scheduling algorithms received the best paper award for Factory Automation at the 2007 IEEE Conference on Emerging Technologies and Factory Automation.

After she joined UC San Diego in fall 2006, she focused on integrating large-scale systems and foundations for service-oriented architectures. Until 2010, she was subsystem lead architect for the Cyber-infrastructure and also the Sensing and Acquisition components of the Ocean Observatories Initiative (OOI) project. There, she researched governance, messaging infrastructures, scientific data models, and novel methods for data distribution and control of oceanographic experiments. Since 2010 she has been leading the requirements engineering, architecture, and development for the CYCORE project, to deliver an innovative cyber-infrastructure that meets stakeholders’ needs. She has also been researching value-based engineering and quality assurance in cyber-infrastructures.

Her research has also extended to voice assistants and machine learning. She was the principal investigator (PI) on the National Institutes of Health grant Voice Assistant for Quality of Life and Healthcare Improvement in Aging Populations (VOLI) and has been researching how to design a personalized and context-aware voice-based digital assistant to improve the healthcare management of older adults. Her research covers needs finding work, collecting Ecological Momentary Assessments with voice assistants, question-answering natural language processing systems, and analyzing Electronic Health Records (EHR). Recently, she is also the PI of the National Science Foundation-funded MS-ADAPT: Multi-Sensor Adaptive Data Analytics for Physical Therapy. She is researching the design of a sensor system and machine learning that support monitoring and feedback on how well patients with low back pain are performing activities recommended by their physical therapist.

For more information, see QI news stories “NSF Awards More than $1 Million to Interdisciplinary Research Team to Study Chronic Low Back Pain” and “Making Voice Assistants Accessible for Older Patients.”

Email: efarcas@ucsd.edu