Smart beekeeping: Machine learning for healthy hive location analysis
| dc.contributor.author | Kupsch, Stephan | |
| dc.date.accessioned | 2026-08-10T02:16:18Z | |
| dc.date.available | 2026-08-10T02:16:18Z | |
| dc.date.issued | 2026 | |
| dc.description.abstract | This paper presents HaBEEtat WebApp, machine learning-driven application designed to enhance decision-making in apiculture by automating the identification of suitable hive locations. Utilizing drone-captured imagery and lightweight scripting through Tracking.js (a 7KB JavaScript computer vision library), the system analyzes environmental features such as sunlight exposure, vegetation density, and windbreaks to determine areas conducive to healthy hive development. The web-based platform embodies the principles of smart farming and precision agriculture by integrating image processing, artificial intelligence, and geospatial analysis for practical field applications. The performance and usability of HaBEEtat WebApp were evaluated using ISO/IEC 25010 software quality model, covering eight key quality attributes: functional suitability, performance efficiency, compatibility, usability, reliability, security, maintainability, and portability. Results revealed high acceptability, with median ratings ranging from 4.0 (Agree) to 5.0 (Strongly Agree) across most categories, demonstrating the web app's reliability, interoperability, and efficiency in real-world agricultural settings. Findings confirm that lightweight machine learning architectures can effectively support small-scale and remote beekeepers, providing a low-resource yet powerful decision-support tool. The study concludes that HaBEEtat WebApp contributes to sustainable apiculture practices, aligns with digital transformation initiatives in agriculture, and offers a replicable model for other smart farming applications. Future work recommends developing a mobile-integrated version for real-time drone-assisted operations and wider accessibility among local apiculturists. | |
| dc.identifier.citation | Kupsch, S. (2026). Smart beekeeping: Machine learning for healthy hive location analysis. In 2026 The 15th International Conference on Informatics, Environment, Energy and Applications (IEEA 2026) (pp. 47–52). Association for Computing Machinery. [https://doi.org/10.1145/3803833.3803841](https://doi.org/10.1145/3803833.3803841) | |
| dc.identifier.uri | https://lakasa.dmmmsu.edu.ph/handle/123456789/2298 | |
| dc.language.iso | en | |
| dc.publisher | Don Mariano Marcos Memorial State University – Mid La Union Campus | |
| dc.sdg | SDG 2 | |
| dc.title | Smart beekeeping: Machine learning for healthy hive location analysis | |
| dc.type | Article |