An On-line system for automated recognition of human activities
The recognition of human behaviours is a key challenge in several contexts, such as healthcare and surveillance, providing support for various applications. In particular in the healthcare domain the development of automated techniques for the recognition of human activity allows the improvement of quality of life of elderly people, monitoring their behaviours and preventing dangerous situations.
Advances in technologies allow the introduction of information sources into everyday objects, however, the data gathered from these pervasive devices may contain sensible user information, arising privacy and security issues. Furthermore, a semantic gap exists between these data and the information needed for the recognition process.
We propose ARA (Automated Recogniser of ADLs), a system for the automated and real-time recognition of human activities in sensorised environment, guaranteeing the user's privacy and the data security.