@inproceedings{senger2020unsupervised,
  title={Unsupervised Anomaly Detection on Multisensory Data from Honey Bee Colonies},
  author={Senger, Diren and Johannsen, Carolin and Melemenidis, Alexandros and Goncharskiy, Alexander and Kluss, Thorsten},
  booktitle={2020 IEEE International Conference on Data Mining (ICDM)},
  pages={1238--1243},
  year={2020},
  organization={IEEE},
  abstract="Beekeepers face the situation that the health state of honey bee colonies is inherently difficult to observe without stressing the bees by opening the hive. We address this problem by proposing an approach that relies on a sensor setup to gather multisensory data inside the bee colony and focus on the detection of outliers in the data stream as indicators of critical situations during the colony's development. Based on data recorded during the citizen science project Bee Observer BOB we demonstrate that algorithms exploiting an ARIMA Model and Receiver Operating Characteristics in combination with an underlying multi agent system are well able to detect and classify anomalies in honey bee colonies. In future applications this concept can be used for both - as a stealth monitoring tool in honey bee research as well as a precise technical assistance for minimally invasive, bee friendly practices in hobbyist and professional beekeeping.",
  url="https://ieeexplore.ieee.org/abstract/document/9338279",
  doi="10.1109/ICDM50108.2020.00156"
}