Real-time and Energy-efficient Detection of Anomalies in Sensor Networks KU Leuven
The key idea underlying this doctoral research work is to devise a model which detects anomalous activities learning continuously from past activity and current changes. The model should be able to learn in real-time and incremental fashion from the incoming streams of individual data. As this stream could be very large, it should keep a bounded memory footprint to avoid storage issues. Furthermore, in wireless sensor networks case not only ...