<![CDATA[Stingless bee honey (SBH) is a food product with a simple and fast production process. Honey production is highly dependent on the condition and ability of the bees. Each region in Indonesia has different botanical and environmental conditions, with different entomological characteristics of bee species based on their geographical origin. This honey classification model is part of the formation of Geographical Indications (GI) based on product characteristics. A generative model is used in the pre-processing stage to produce spectrum data with the best grouping (silhouette score > 0.6). The main process discussed in this article is the application of GI classification model of four types of stingless bee honey based on cultivation location. The results of the study with a 400x745 dataset and 4 classes (Lampung, Bogor, Sukabumi, and Rangkas Bitung) showed that the classification model produced an accuracy above 95% with a precision and recall above 0.99. The SBH GI classification application has been successfully built using the scrum methodology and is cloud-based. The application displays the classification results of origin, type (entomological), feed dominance (botanical) and dominant spectrum values. The application has also been tested for feasibility based on the User Acceptance Test with results above 90%.]]>
Copyrights © 2026
