HALIM, RIDWAN (2025) THE APPLICATION OF MULTILAYER PERCEPTRON ALGORITHM FOR HONEY TYPE CLASSIFICATION BASED ON RGB COLOR. Tugas Akhir thesis, Informatics.
![[img]](http://eprints.uty.ac.id/style/images/fileicons/text.png) |
Text
5210411257_Ridwan Halim_Abstrak.pdf Download (62kB) |
Abstract
Technological advancements have significantly modernized the agricultural industry. Distinguishing honey types with nearly identical colors presents a considerable challenge. However, differentiating between acacia honey and forest honey based on color is one of the simplest approaches to ensure product authenticity and quality. This study aims to develop a honey color classification model using the Multilayer Perceptron (MLP) algorithm. Image data were collected from various angles under natural lighting conditions. A total of ninety experiments were conducted using different parameter combinations, including data imbalance handling methods, dense layer configurations, and training settings. The results indicate that the MLP model, when optimized with Adaptive Synthetic Sampling (ADASYN) to address data imbalance, achieved a validation accuracy of 87.50%. This level of accuracy demonstrates the model’s potential to support automation processes in the industry for reliable honey color classification. Keywords: Multilayer Perceptron, ADASYN, Acacia Honey, Forest Honey, Color Classification
| Item Type: | Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir) |
|---|---|
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Sains Dan Teknologi > S1 Informatika |
| Depositing User: | Kaprodi S1 Informatika UTY |
| Date Deposited: | 17 Jul 2025 02:05 |
| Last Modified: | 17 Jul 2025 02:05 |
| URI: | http://eprints.uty.ac.id/id/eprint/18197 |
Actions (login required)
 |
View Item |
