Energy-efficient classification for anomaly detection: The wireless channel as a helper

Anomaly detection has various applications including condition monitoring and fault diagnosis. The objective is to sense the environment, learn the normal system state, and then periodically classify whether the instantaneous state deviates from the normal one or not. Wireless sensor networks provide a flexible and cost-effective way of monitoring a system state. In traditional wireless sensor networks, sensors encode their observations and transmit them to a fusion center using some interference avoiding channel access method. The fusion center decodes all the data and then classifies the corresponding system state. As this approach is in general highly inefficient, this paper proposes a transmission scheme that, instead of avoiding the interference, exploits it for carrying out the anomaly detection directly in the air. In other words, the wireless channel helps the fusion center to retrieve the sought classification outcome immediately from the channel output. To achieve this, the chosen learning model is a linear support vector machine. After proving the reliability of the proposed scheme, numerical examples are presented that demonstrate its ability to reduce the energy consumption for anomaly detection by up to 53 % compared to a strategy that uses time division multiple-access.