Visual Programmed IoT Beehive Monitoring for Decision Aid by Machine Learning based Anomaly Detection
- Resource Type
- Conference
- Authors
- Machhamer, Rudiger; Altenhofer, Jannik; Ueding, Kristof; Czenkusch, Levin; Stolz, Florian; Harth, Maximilian; Mattern, Michael; Latif, Azhar; Haab, Swen; Herrmann, Jurgen; Schmeink, Anke; Gollmer, Klaus-Uwe; Dartmann, Guido
- Source
- 2020 9th Mediterranean Conference on Embedded Computing (MECO) Embedded Computing (MECO), 2020 9th Mediterranean Conference on. :1-5 Jun, 2020
- Subject
- Bioengineering
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineering Profession
Robotics and Control Systems
Signal Processing and Analysis
Visualization
Heuristic algorithms
Software algorithms
Machine learning
Voltage
Software
System-on-chip
- Language
- ISSN
- 2637-9511
The global decline of bees is an important ecological and economic issue. Increasing stressors such as pests and pollutants and the increasing lack of diversity due to monocultures are worsening the viability of bees. Beekeepers have great interest in the health of these complex systems and put a lot of work into monitoring them. Unfortunately, they usually do not have resources to engage experts in modern technologies like Internet of Things (IoT) and Machine Learning (ML). To support them, we present a visual programming environment which enables laymen to handle those modern technologies much easier. We are demonstrating our tool by developing an IoT monitoring system that not only collects data but also detects and reports anomalies such as vandalism or diseases on the beehive. This will enable beekeepers to minimise the effort required for beekeeping and will help to investigate the causes of colony problems using IoT and ML without in-depth knowledge of computer science.