Embedded and pervasive systems seamlessly connect human users to the physical world that is richly and invisibly interwoven with sensors, actuators, displays, and networks embedded in the everyday objects. The pervasive nature of such systems will transform the way people interact with each other and their environment and will revolutionize the way next generation medical services are supplied and consumed. When realized properly, the resulting unparalleled information extracted from these systems enables emerging applications in mobile and remote healthcare, wellness, emergency response, fitness monitoring, elderly care support, long-term preventive chronic care, smart environments, gaming and sports.

In spite of their revolutionary potentials, such embedded systems face a number of challenges in design and architecture that form stumbling blocks in their path to success. In particular, current technologies are difficult to use by non tech-savvy users, and produce unreliable and inconsistent measurements when deployed in uncontrolled environments. These issues lead to underutilization and unsustained adoption of the technology. Furthermore, the data-intensive nature of continuous monitoring requires efficient signal processing and data analytics algorithms for real-time, scalable, reliable, accurate, and secure extraction of relevant information from an overwhelmingly large amount of data. In EPSL, we emphasize a data-processing-driven optimization and knowledge extraction approach that targets exploration of reliable computing, real-time transfer learning, efficient data analytics, and system-level optimization to enhance sustainability and widespread utilization of embedded and pervasive systems in everyday life applications and services.

Our goal is to design future medicine technologies with a special focus on their economic and social dimensions. In particular, we focus on design and development of solutions that improve outcomes, decrease isolation, reduce health disparities, and substantially reduce costs.