Automatic Health Monitoring Using Anonymous , Binary Sensors

Elderly individuals living independently (often in rural areas) face challenges staying connected to friends, relatives, and caretakers. Automatic health monitoring supports the goal of ”aging in place”, or keeping elders independent and not institutionalized by providing crucial information to key individuals. Automatic monitoring can improve the accuracy of pharmacologic interventions, track illness progression, and lower caretaker stress levels [2]. Additionally, carefully filtered day-to-day information could link elders to important people in their lives. The basic goals of ubiquitous computing are aligned with the needs of automatic health monitoring. They include identifying people, tracking people as they move, and knowing what activities people are engaged in. More challenging goals include recognizing when people deviate from regular patterns of behavior and predicting future behavior. This research uses machine learning and ubiquitous computing for simultaneous tracking and activity recognition. Identity is collected once, upon entry and exit of the home, via a single radio frequency identification (RFID) reader. Elsewhere, tracking is performed with many anonymous, binary sensors. We envision a system that unobtrusively collects information vital to maintain ties between independent elders and family, friends, and caretakers. Here is a scenario: A man has an elderly mother living alone one hour away. Last week she knocked the phone off the hook and was unavailable for an entire day. The man walks into a hardware store and emerges with a large brown box. It contains several dozen nondescript, quarter-sized sensors that stick to any surface. Following directions, the man attaches sensors to doors, drawers, and chairs. He pulls out a CD-ROM and installs software on a personal computer and plugs a device into a USB port. The software instructs him to perform a quick walk-through of the house, touching every sensor. Later that week the man logs onto the Internet, types a password, and checks to see that his mother has eaten lunch. One week later he checks that she has been cooking and eating meals. One month later he checks whether her activity levels are steady. The system reports that activity levels are abnormally low today. He calls and finds that his mother has the flu.