Anomaly Detection in Beehives: An Algorithm Comparison

TL;DR

This paper compares various machine learning models for detecting anomalies in beehive sensor data, highlighting the deep recurrent autoencoder as the most effective across different hive conditions.

Contribution

It provides a comparative analysis of multiple anomaly detection algorithms specifically applied to beehive monitoring data, identifying the most suitable model for practical use.

Findings

Deep Recurrent Autoencoder outperforms other models in detection accuracy.

Evaluation conducted on real-world datasets from different hives.

Autoencoder shows versatility for various anomaly types.

Abstract

Sensor-equipped beehives allow monitoring the living conditions of bees. Machine learning models can use the data of such hives to learn behavioral patterns and find anomalous events. One type of event that is of particular interest to apiarists for economical reasons is bee swarming. Other events of interest are behavioral anomalies from illness and technical anomalies, e.g. sensor failure. Beekeepers can be supported by suitable machine learning models which can detect these events. In this paper we compare multiple machine learning models for anomaly detection and evaluate them for their applicability in the context of beehives. Namely we employed Deep Recurrent Autoencoder, Elliptic Envelope, Isolation Forest, Local Outlier Factor and One-Class SVM. Through evaluation with real world datasets of different hives and with different sensor setups we find that the autoencoder is the best multi-purpose anomaly detector in comparison.