Layered Design of an Assisted Living System for Disabled

Assisted living systems for elderly or disabled combine offsprings of telemedicine and surveillance techniques. This report presents a layer-based design of multimodal health monitoring system complying with a paradigm of ubiquitous and personalized medicine. The input layer consists of intelligent sensors issuing a context-based semantic description of the subject. The infrastructure layer is based on a dynamic network using selectable architecture and data carriers. The decision layer applies premise-dedicated restrictions and subject-derived behavioral habits to identify potentially dangerous events and initiate an adequate action. Selected assistance functions are also provided in the system thanks to gesture sequence-based command interpreter. The system was designed and tested in its sensor and infrastructure layers and some experimental setups were made in volunteer's homes. The results confirm that the system adapts to environment-specific relations, provides seamless monitoring with no limit of indoor and outdoor mobility and adapts to subject's habits in recognition of normal, suspected and dangerous events. Further works are aimed to confirm the set of suspicious behavioral patterns in real live conditions and to design wearable prototypes of intelligent sensors.