Autonomic Wireless Sensor/Actuator Networks for Tracking Environment Control Behaviors

Abstract

To develop energy-saving environment control systems, we propose autonomic wireless sensor/actuator networks that classify a user’s behaviors in relation to environment control such as lighting, and that configure themselves depending on sensor node selection. In our system, a wireless remote control node monitors a user’s actions with respect to environment control, and occupancy sensor networks simultaneously detect the user’s movement. The system learns the relationship between the responses of the remote control node and the occupancy sensor networks to classify the user’s behaviors with only the occupancy sensor networks. The system chooses informative sensor nodes for this behavior classification based on an information gain criterion. These chosen nodes have a high sensing cost. Sensor network routing is controlled based on the sensing cost and communication cost metric. In the resultant sensor networks, the sensing performance is the same as that in the original network, but the resources are successfully allocated to the nodes. In addition, less informative and redundant nodes are identified. We demonstrate tracking environment control behaviors and sensor node selection using the sensor/actuator networks testbed.