An important tool for evaluating the health of patients who suffer from mobility-affecting chronic diseases such as MS, Parkinson’s, and Muscular Dystrophy is assessment of how much they walk. Ambulation is a mobility monitoring system that uses Android and Nokia N95 mobile phones to automatically detect the user’s mobility mode. The user’s only required interaction with the phone is turning it on and keeping it with him/her throughout the day, with the intention that it could be used as his/her everyday mobile phone for voice, data, and other applications, while Ambulation runs in the background. The phone uploads the collected mobility and location information to a server and a secure, intuitive web-based visualization of the data is available to the user and any family, friends or caregivers whom they authorize, allowing them to identify trends in their mobility and measure progress over time and in response to varying treatments.

We are deploying a metropolitan scale Wi-Fi mesh network near downtown Los Angeles to support the design and development of a data-centric network-fabric for urban participatory sensing. Participatory sensing employs software and network technology to enable people’s everyday mobile devices to act as credible sensors of the natural, built, and cultural environments. Current research focuses on how to make it easy and secure for both the public and professional users to define sensing ‘campaigns,’ recruit participants to collect data, to help ‘make a case’ with data they collect, and digitally publish the results. To further research in this area, our architecture will enable embedding network–attested location and time context in sensor readings. The network will also provide a research framework for developing policy-based privacy, and related security mechanisms for participatory sensing.

CENS is focusing on three types of health applications. Personalized medicine (AndWellness, AndAmbulation), epidemiological data collection (Project Surya), and personal decision making and awareness (PEIR). Each of these applications uses a similar systems architecture: time, location (GPS), and motion (accelerometer) trace collection on the mobile phone with a user interface, scientific model-based analytics used to draw inferences from the data, and graphical map or calendar based feedback to users. The specifics of each component depend on the type of data collected, the target populations, and the goals of the project. The UI for AndWellness includes an ecological momentary assessment, which is a set of questions a user completes regarding their feelings at that moment; and control over the time, location, and frequency of reminders, which are included to remind users to complete the assessments. The AndWellness UI aims to make the assessment easy to understand and quick to complete. The UI for Project Surya is designed for rural villagers living in India who will likely not know how to read. Therefore the UI will be primarily graphically based, and have little or no text. The specific analytics used for each project differs based on the goal of the project. All four applications use activity classification algorithms in order to infer a user's activity from the GPS and/or accelerometer traces. The similarity ends here. Project Surya uses image analysis algorithms to infer soot levels from images of specialized filters and calibrated color charts. AndWellness uses simple statistical calculations to calculate base-rates for a small set of behaviors that are measured with the ecological momentary assessments. PEIR uses models from the Air Resources Board and other GIS streams to compute users' carbon impact, particulate exposure, and fast food exposure from a location trace. The feedback for each project is presented using a map and/or calendar based interface, based on the data and goals of the project. Because AndWellness users are interested in identifying patterns in space and time across weeks or months, AndWellness presents data in both a calendar and map-based interface, and makes it easy to cross reference any event across either mode. PEIR uses a map to highlight routes and the pollution exposure, and bar graphs to show aggregates for each of the three metrics computed by the analytics. AndAmbulation solely uses a calendar interface because users are most interested in trends over time.

This project asks “what if we had a constantly updated assessment of our own personal impact on the environment?” It explores how models of environmental exposure and impact can be refined with GPS location data to show us the effects of lifestyle choices that we make every day—their contribution to the environment that we live in with our children, parents, and neighbors. This is the personal, real-time equivalent of government-mandated Environmental Impact Reports and Health Impact Assessments, which document the impact of construction and public works projects on our environment and health.

overview poster so no abstract.