This paper introduces a system for recognizing activities in the home using simple, low-cost state-change sensors that are easy to install and use. The sensors are designed to be "tape on and forget" devices, allowing them to be quickly and ubiquitously installed in home environments. The system offers an alternative to more invasive sensors such as cameras and microphones. Preliminary results on a small dataset show that it is possible to recognize activities of interest to medical professionals, such as toileting, bathing, and grooming, with detection accuracies ranging from 25% to 89% depending on the evaluation criteria. The system's goal is to enable a large number of simple, low-cost sensors to be easily taped on objects throughout an environment, allowing a computing system to detect specific activities of the occupant. This could provide new context-aware services in the home, such as proactive care for the aging. Medical professionals believe that detecting changes in activities of daily living (ADLs), instrumental ADLs (IADLs), and enhanced ADLs (EADLs) can help identify emerging medical conditions before they become critical. The paper discusses two categories of everyday activities in the home: those requiring repetitive motion and those that can be recognized by observing patterns in how people interact with objects. The system focuses on the latter, using simple sensors to detect changes in the state of objects and devices. While progress has been made in algorithms for monitoring scenes and interpreting signals from complex sensors, the recognition inference problem is often underconstrained. The system explores the potential of deploying a large number of simple sensors, which can provide powerful clues about activity. Examples include switch sensors in the bed suggesting sleep and pressure mat sensors for tracking movement and position. The system has been tested in multiple real homes with non-researcher occupants, showing promise for detecting and monitoring ADLs in existing homes.This paper introduces a system for recognizing activities in the home using simple, low-cost state-change sensors that are easy to install and use. The sensors are designed to be "tape on and forget" devices, allowing them to be quickly and ubiquitously installed in home environments. The system offers an alternative to more invasive sensors such as cameras and microphones. Preliminary results on a small dataset show that it is possible to recognize activities of interest to medical professionals, such as toileting, bathing, and grooming, with detection accuracies ranging from 25% to 89% depending on the evaluation criteria. The system's goal is to enable a large number of simple, low-cost sensors to be easily taped on objects throughout an environment, allowing a computing system to detect specific activities of the occupant. This could provide new context-aware services in the home, such as proactive care for the aging. Medical professionals believe that detecting changes in activities of daily living (ADLs), instrumental ADLs (IADLs), and enhanced ADLs (EADLs) can help identify emerging medical conditions before they become critical. The paper discusses two categories of everyday activities in the home: those requiring repetitive motion and those that can be recognized by observing patterns in how people interact with objects. The system focuses on the latter, using simple sensors to detect changes in the state of objects and devices. While progress has been made in algorithms for monitoring scenes and interpreting signals from complex sensors, the recognition inference problem is often underconstrained. The system explores the potential of deploying a large number of simple sensors, which can provide powerful clues about activity. Examples include switch sensors in the bed suggesting sleep and pressure mat sensors for tracking movement and position. The system has been tested in multiple real homes with non-researcher occupants, showing promise for detecting and monitoring ADLs in existing homes.