Edge-Based Detection of Varroosis in Beehives with IoT Devices with Embedded and TPU-Accelerated Machine Learning
Source abstract
Abstract
One of the causes of mortality in bees is varroosis, a bee disease caused by the Varroa destructor mite. Varroa destructor mites may occur suddenly in beehives, spread across them, and impair bee colonies, which finally die. Edge IoT (Internet of Things) devices capable of processing video streams in real-time, such as the one we propose, may allow for the monitoring of beehives for the presence of Varroa destructor. Additionally, centralization of monitoring in the Cloud data center enables the prevention of the spread of this disease and reduces bee mortality through monitoring entire apiaries. Although there are various IoT or non-IoT systems for bee-related issues, such comprehensive and technically advanced solutions for beekeeping and Varroa detection barely exist or perform mite detection after sending the data to the data center. The latter, in turn, increases communication and storage needs, which we try to limit in our approach. In the paper, we show an innovative Edge-based IoT solution for Varroa destructor detection. The solution relies on Tensor Processing Unit (TPU) acceleration for machine learning-based models pre-trained in the hybrid Cloud environment for bee identification and Varroa destructor infection detection. Our experiments were performed in order to investigate the effectiveness and the time performance of both steps, and the study of the impact of the image resolution on the quality of detection and classification processes prove that we can effectively detect the presence of varroosis in beehives in real-time with the use of Edge artificial intelligence invoked for the analysis of video streams.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Insect and Pesticide Research · Plant and animal studies · Insect and Arachnid Ecology and Behavior
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Applied Informatics, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland
Department of Distributed Systems and Informatic Devices, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland
Funding
Silesian University of Technology · European Social Funds
References (53)
Show source-provided references
1. The internet of things in healthcare: An overview
2. Review of IoT applications in agro-industrial and environmental fields10.1016/j.compag.2017.09.015 ↗
3. Krzhizhanovskaya, V.V., Závodszky, G., Lees, M.H., Dongarra, J.J., Sloot, P.M.A., Brissos, S., and Teixeira, J. (2020, January 3–5). IoT-Based Cow Health Monitoring System. Proceedings of the Computational Science—ICCS 2020, Amsterdam, The Netherlands.10.1007/978-3-030-50436-6 ↗
4. Neonicotinoids, bee disorders and the sustainability of pollinator services10.1016/j.cosust.2013.05.007 ↗
5. An Estimate of Managed Colony Losses in the Winter of 2006–2007: A Report Commissioned by the Apiary Inspectors of America
6. A national survey of managed honey bee 2014–2015 annual colony losses in the USA10.1080/00218839.2016.1153294 ↗
7. Varroa destructor is the main culprit for the death and reduced populations of overwintered honey bee (Apis mellifera) colonies in Ontario, Canada10.1051/apido/2009076 ↗
8. Cornman, R.S., Tarpy, D.R., Chen, Y., Jeffreys, L., Lopez, D., Pettis, J.S., van Engelsdorp, D., and Evans, J.D. (2012). Pathogen Webs in Collapsing Honey Bee Colonies. PLoS ONE, 7.10.1371/journal.pone.0043562 ↗
9. vanEngelsdorp, D., Traynor, K.S., Andree, M., Lichtenberg, E.M., Chen, Y., Saegerman, C., and Cox-Foster, D.L. (2017). Colony Collapse Disorder (CCD) and bee age impact honey bee pathophysiology. PLoS ONE, 12.10.1371/journal.pone.0179535 ↗
10. Death of the bee hive: Understanding the failure of an insect society10.1016/j.cois.2015.04.004 ↗
11. Video Monitoring of a Mite in Honeybee Cells10.4028/www.scientific.net/AMR.664.1107 ↗
12. Bees under stress: Sublethal doses of a neonicotinoid pesticide and pathogens interact to elevate honey bee mortality across the life cycle10.1111/1462-2920.12426 ↗
13. Francis, R.M., Nielsen, S.L., and Kryger, P. (2013). Varroa-Virus Interaction in Collapsing Honey Bee Colonies. PLoS ONE, 8.10.1371/journal.pone.0057540 ↗
14. Biology and control of Varroa destructor10.1016/j.jip.2009.07.016 ↗
15. Rinkevich, F.D., Danka, R.G., and Healy, K.B. (2017). Influence of Varroa Mite (Varroa destructor) Management Practices on Insecticide Sensitivity in the Honey Bee (Apis mellifera). Insects, 8.10.3390/insects8010009 ↗
16. Colony collapse disorder in Europe10.1111/j.1758-2229.2011.00312.x ↗
17. Gates, B.N. (2021, September 19). The Temperature of the Bee Colony, Available online: https://www.biodiversitylibrary.org/bibliography/64474.
18. Dunham, W. (1931). Hive Temperatures for Each Hour of a Day, The Department of Zoology and Entomology.
19. System Architectures for Real-time Bee Colony Temperature Monitoring10.1016/j.procs.2014.12.012 ↗
20. Zogovic, N., Mladenovic, M., and Rašić, S. (2017, January 12–15). From Primitive to Cyber-Physical Beekeeping. Proceedings of the 7th International Conference on Information Society and Technology, Kopaonik, Serbia.
21. Zacepins, A., Kviesis, A., Pecka, A., and Osadcuks, V. (2017, January 28–31). Development of Internet of Things concept for Precision Beekeeping. Proceedings of the 2017 18th International Carpathian Control Conference (ICCC), Sinaia, Romania.10.1109/CarpathianCC.2017.7970365 ↗
22. Gil-Lebrero, S., Quiles Latorre, F., Ortiz, M., Sánche Ruiz, V., Gamiz, V., and Luna-Rodriguez, J.J. (2017). Honey Bee Colonies Remote Monitoring System. Sensors, 17.10.3390/s17010055 ↗
23. Rustia, D.J., Ngo, N., and Lin, T.T. (2016, January 23–25). An IoT-based information system for honeybee in and out activity with beehive environmental condition monitoring. Proceedings of the Conference on Bio-Mechatronics and Agricultural Machinery Engineering, Niigata, Japan.
24. Braga, A.R., Hassler, E.E., Gomes, D.G., Freitas, B.M., and Cazier, J.A. (2019, January 15–17). IoT for Development: Building a Classification Algorithm to Help Beekeepers Detect Honeybee Health Problems Early. Proceedings of the AMCIS 2019, Cancún, Mexico.
25. Kontogiannis, S. (2019). An Internet of Things-Based Low-Power Integrated Beekeeping Safety and Conditions Monitoring System. Inventions, 4.10.3390/inventions4030052 ↗
26. Web Monitoring of Bee Health for Researchers and Beekeepers Based on the Internet of Things10.1016/j.procs.2018.04.103 ↗
27. b+WSN: Smart beehive with preliminary decision tree analysis for agriculture and honey bee health monitoring10.1016/j.compag.2016.04.008 ↗
28. Meitalovs, J., Histjajevs, A., and Stalidzans, E. (2009, January 28–29). Automatic Microclimate Controlled Beehive Observation System. Proceedings of the 8th International Scientific Conference ‘Enginieering for Rural Development’, Jelgava, Latvia.
29. Balta, A., Dogan, S., ozmen koca, G., and Akbal, E. (2017, January 10–12). Software Modeling of Remote Controlled Beehive Design. Proceedings of the International Conference on Advances and Innovations in Engineering (ICAIE), Elazig, Turkey.
30. Fitzgerald, D.W., Murphy, F.E., Wright, W.M.D., Whelan, P.M., and Popovici, E.M. (2015, January 24–25). Design and development of a smart weighing scale for beehive monitoring. Proceedings of the 2015 26th Irish Signals and Systems Conference (ISSC), Pittsburgh, PA, USA.10.1109/ISSC.2015.7163763 ↗
31. Solution for automated bee colony weight monitoring
32. Machhamer, R., Altenhofer, J., Ueding, K., Czenkusch, L., Stolz, F., Harth, M., Mattern, M., Latif, A., Haab, S., and Herrmann, J. (2020, January 8–11). Visual Programmed IoT Beehive Monitoring for Decision Aid by Machine Learning based Anomaly Detection. Proceedings of the 2020 9th Mediterranean Conference on Embedded Computing (MECO), Budva, Montenegro.10.1109/MECO49872.2020.9134323 ↗
33. Szczurek, A., Maciejewska, M., Zajiczek, Z., Wilk, J., Wilde, J., and Siuda, M. (2020). The Effectiveness of Varroa destructor Infestation Classification Using an E-Nose Depending on the Time of Day. Sensors, 20.10.3390/s20092532 ↗
34. Szczurek, A., Maciejewska, M., Wilk, J., Wilde, J., and Siuda, M. (2019, January 26–27). Detection of Honeybee Disease: Varrosis using a Semiconductor Gas Sensor Array. Proceedings of the 8th International Conference on Sensor Networks, Prague, Cxech Republic.10.5220/0007575600580066 ↗
35. Application of continuous monitoring of honeybee colonies10.1007/s13592-014-0298-x ↗
36. Short communication.: Platform for bee-hives monitoring based on sound analysis. A perpetual warehouse for swarming daily activity10.5424/sjar/2009074-1109 ↗
37. Identification of the honey bee swarming process by analysing the time course of hive vibrations10.1016/j.compag.2011.01.004 ↗
38. Zgank, A. (2020). Bee Swarm Activity Acoustic Classification for an IoT-Based Farm Service. Sensors, 20.10.3390/s20010021 ↗
39. Remote Beehive Monitoring using Acoustic Signals
40. Van Goethem, S., Verwulgen, S., Goethijn, F., and Steckel, J. (2019, January 15–18). An IoT solution for measuring bee pollination efficacy. Proceedings of the 2019 IEEE 5th World Forum on Internet of Things (WF-IoT), Limerick, Ireland.10.1109/WF-IoT.2019.8767298 ↗
41. Campbell, J., Mummert, L., and Sukthankar, R. (2008, January 8–11). Video Monitoring of Honey Bee Colonies at the Hive Entrance. Proceedings of the Workshop Visual Observation and Analysis of Animal and Insect Behavior, Tampa, FL, USA.
42. An imaging system for monitoring the in-and-out activity of honey bees10.1016/j.compag.2012.08.006 ↗
43. Pollen Bearing Honey Bee Detection in Hive Entrance Video Recorded by Remote Embedded System for Pollination Monitoring10.5194/isprs-annals-III-7-51-2016 ↗
44. A computer vision system to monitor the infestation level of Varroa destructor in a honeybee colony10.1016/j.compag.2019.104898 ↗
45. Marstaller, J., Tausch, F., and Stock, S. (2019, January 23–25). DeepBees—Building and Scaling Convolutional Neuronal Nets For Fast and Large-Scale Visual Monitoring of Bee Hives. Proceedings of the International Conference on Computer Vision, Thessaloniki, Greece.10.1109/ICCVW.2019.00036 ↗
46. IndusBee 4.0—Integrated Intelligent Sensory Systems for Advanced Bee Hive Instrumentation and Hive Keepers’ Assistance Systems
47. A Jxta Based Asynchronous Peer-to-Peer Implementation of Genetic Programming10.4304/jsw.1.2.12-23 ↗
48. (2021, September 30). Google Coral Documentation. Available online: https://coral.ai/docs.
49. Zoph, B., and Le, Q.V. (2017, January 24–26). Neural Architecture Search with Reinforcement Learning. Proceedings of the ICLR 2017, Toulon, France.
50. A Multi-Temporal Context-aware System for Competences Management10.1007/s40593-015-0047-y ↗
51. ORACON: An adaptive model for context prediction
52. A risk prediction model for software project management based on similarity analysis of context histories10.1016/j.infsof.2020.106497 ↗
53. CHSPAM: A multi-domain model for sequential pattern discovery and monitoring in contexts histories10.1007/s10044-019-00829-9 ↗