Automatic Behavior Learning for Personalized Assisted Living Systems

Abstract

Recently available surveillance systems for assisted living of disabled or elderly are offspring of traditional home care solutions used for remote monitoring of predefined parameters. The commonly used closed architecture design, makes extensions or modification of such systems very difficult. An alternative approach is presented in this paper. The proposed system, based partly on building-embedded and partly on wearable sensor networks includes subject-dependent artificial intelligence-based behavior recognition module to determine potentially dangerous events.