The objective of this research is to develop a theory of ActionWebs, that is, networked embedded sensor-rich systems, which are taskable for coordination of multiple decision-makers. The approach is to first identify models of ActionWebs using stochastic hybrid systems, an interlinking of continuous dynamical physical models with discrete state representations of interconnection and computation. Second, algorithms will be designed for tasking individual sensors, based on information objectives for the entire system. Third, algorithms for ActionWebs will be developed using multi-objective control methods for meeting safety and efficiency objectives. Two grand challenge applications for this research are in Intelligent Buildings for optimal heating, ventilation, air conditioning, and lighting based on occupant behavior and external environment; and Air Traffic Control for mobile vehicle platforms with sensor suites for environmental sensing to enable safe, convenient, and energy efficient routing. The intellectual merit of this research stems from a conceptual shift of ActionWebs away from passive information gathering to an action-orientation. This involves: modeling of ActionWebs using stochastic hybrid systems; taskable, multi-modal, and mobile sensor webs; and multi-scale action-perception hierarchies. The broader impact of the research is in two grand challenge national problems: energy efficient air transportation, and energy efficient, high productivity buildings, and will tackle social, privacy, economic, and usability issues. Integrated with the research is a program of coursework development in networked embedded systems, across stove pipes in EECS, Aero-Astro, Civil, and Mechanical Engineering departments. Outreach objectives include new course design at San Jose State University, and recruiting more women researchers.

The goal of the proposed research is to identify ways to inexpensively provide specific information about energy consumption in buildings and facilitate conservation. Signal processing, machine learning, and data fusion techniques will be developed to extract actionable information from whole-building power meters and other available sensors. The main objectives are: (a) to create a framework for obtaining disaggregated, appliance-specific feedback about electricity consumption in a building by extracting high-value information from low-cost data sources; and (b) to investigate and develop data mining and machine learning algorithms for making use of appliance-specific electricity data, in order to provide users with recommendations on how to optimize their energy consumption and understand the effects of their energy-related decisions. A series of residential buildings in Pittsburgh, PA will serve as a test-bed for evaluating and validating our proposed approach. Blueroof Technologies, a non-profit corporation located in McKeesport, PA that researches, develops and provides affordable senior-citizen housing with integrated sensor networks and building automation systems, will provide access to their Research Cottages for this project. Similarly, Robert Bosch LLC, a leading global provider of consumer goods and building technology, will provide additional technical research assistance and expertise. The main scientific merit of the project is the development of a framework for evaluating energy-use-disaggregation methods according to their value for promoting energy conservation. The resulting data sets will be large enough to produce significant conclusions about the feasibility and effectiveness of the technology, and allow for the development of new models about the trends and patterns of appliance usage in buildings. Broader impacts of this research include providing a foundation for future cyber-physical systems by inexpensively obtaining real-time appliance-level data. Such data can be used to help reduce the energy consumption of buildings by revealing the relationship between users' behavior and electricity consumption in buildings. The proposed industry-university collaborative research effort with Bosch will ensure that the technology and scientific contributions are steered toward innovative solutions that are practical for adoption in the market. Furthermore, the project will have significant diversity contributions by attracting minority students through collaboration with the University of Maryland Eastern Shore, a land-grant, historically black college with a diverse student body. Finally, a series of planned industry seminars, workshops and the publication of journal articles will allow further dissemination of the work.