A Discrete Event Oriented Framework for a Smart House Behavior Monitor System
Carlos Pfeiffer, Veralia Gabriela Sánchez, Nils‐Olav Skeie · 2016
A discrete event oriented framework to build a system to automatically monitor the behavior of people living alone, and assist them in case of accidents or abnormal situations, is proposed. The system can acquire information through cameras and other sensors (movement, temperature, humidity and sound sensors among others). The images from the cameras are automatically analyzed to get information about the status of the person, defined by his location inside the house, his position, and the intensity of movement. The images are not permanently stored, nor available for viewing, in order to protect the privacy of the person being monitored. The cameras and other sensors can also be used to get information about the room status (the number of persons in it, the status of windows, doors, lights and other appliances, the room temperature and humidity, etc.) Additional sensors can also be used to get external status information, such as outside temperature and weather conditions. All the information is mapped to discrete set variables that can take a reduced number of values. These variables are used to define the state of the system, activities, and behaviors. This information can be used to build behavior models to characterize the person normal behavior during a training period, and later use this characterization to detect atypical behaviors.