Event detection is a major issue for applications of wireless sensor networks. In order to detect an event, a sensor network has to identify which application-specific incident has occurred based on the raw data gathered by individual sensor nodes. In this context, an event may be anything from a malfunction of monitored machinery to an intrusion into a restricted area. The goal is to provide high-accuracy event detection at minimal energy cost in order to maximize network lifetime. In this paper, we present a system for collaborative event detection directly on the sensor nodes. The system does not require a base station for centralized coordination or processing, and is fully trainable to recognize different classes of application-specific events. Communication overhead is reduced to a minimum by processing raw data directly on the sensor nodes and only reporting which events have been detected. The detection accuracy is evaluated using a 100node sensor network deployed as a wireless alarm system on the fence of a real-world construction site.

The main purpose of wireless sensor networks (WSNs) is to obtain information about their environment. However, WSNs often produce imprecise and incorrect sensor data, e.g. because of sensor failure or unreliable radio communication. We propose a system for WSN applications that allows to assess the quality of sensor data and further allows to fuse data based on their estimated quality. Our system comprises local and distributed heuristics to estimate the quality of sensor data, with a focus on data accuracy and data consistency. In the fusion step, the most plausible value of the measured quantity is inferred from multiple sensor readings by use of the Dempster-Shafer theory of evidence. Both quality assessment and data fusion are carried out within the network and thus do not rely on a powerful sink node. We demonstrate the effectiveness of our system by means of a wireless game controller for the game Pong, built from multiple sensor nodes. The controller can detect and reject incorrect sensor readings and thus improve the player's control over the in-game paddle.

In order to avoid transmitting raw data to a base station, sensor nodes are trained to cooperatively recognize deployment-specific events based on the data sampled by their sensors. As both training and event detection are performed without the need for central coordination or processing, only information about the detected event needs to be reported.