ALARM-NET: Wireless Sensor Networks for Assisted-Living and Residential Monitoring

We describe ALARM-NET, a wireless sensor network for assisted-living and residential monitoring. It integrates envi- ronmental and physiological sensors in a scalable, heteroge- neous architecture. A query protocol allows real-time col- lection and processing of sensor data by user interfaces and back-end analysis programs. One such program determines circadian activity rhythms of residents, feeding activity in- formation back into the sensor network to aid context-aware power management, dynamic privacy policies, and data as- sociation. Communication is secured end-to-end to protect sensitive medical and operational information.
The ALARM-NET system has been implemented as a network of MICAz sensors, stargate gateways, iPAQ PDAs, and PCs. Customized infrared motion and dust sensors, and integrated temperature, light, pulse, and blood oxygenation sensors are present. Software components include: TinyOS query processor and security modules for motes; AlarmGate, an embedded Java application for managing power, privacy, security, queries, and client connections; Java resident mon- itoring and sensor data querying applications for PDAs and PCs; and a circadian activity rhythm analysis program.
We show the correctness, robustness, and extensibility of the system architecture through a scenario-based evaluation of the integrated ALARM-NET system, as well as perfor- mance data for individual software components.

Wood, A, G Virone, T Doan, Q Cao, Leo Selavo, Y Wu, L Fang, Z He, S Lin, and Jack Stankovic. "ALARM-NET: Wireless Sensor Networks for Assisted-Living and Residential Monitoring." University of Virginia Dept. of Computer Science Tech Report (2006).