Exploiting the Human Factor in a WSN-Based System for Ambient Intelligence

Abstract

Practical applications of ambient intelligence cannot leave aside requirements about ubiquity, scalability, and transparency to the user. An enabling technology to comply with this goal is represented by wireless sensor networks (WSNs); however, although capable of limited in-network processing, they lack the computational power to act as a comprehensive intelligent system. By taking inspiration from the sensory processing model of complex biological organisms, we propose here a cognitive architecture able to perceive, decide upon, and control the environment of which the system is part. WSNs act as a transparent interface that allows the system to understand human requirements through implicit feedback, and consequently adapt its behavior. A central unit will carry on symbolic reasoning based on the concepts extracted from sensory inputs collected and pre-processed by pervasively deployed WSNs.