Maulana, Johan Indra (2026) Klasifikasi Biji Kopi Jenis Robusta dan Arabika Menggunakan Metode Convolutional Neural Network (CNN) dengan MobileNetV2. Undergraduate thesis, Politeknik Negeri Jember.
![[img]](https://sipora.polije.ac.id/style/images/fileicons/text.png) |
Text (Abstract)
Abstract.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (228kB) |
|
Text (Bab 1 Pendahuluan)
Bab 1 Pendahuluan.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (240kB) |
|
Text (Daftar Pustaka)
Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (223kB) |
|
Text (Laporan Lengkap)
Laporan Lengkap.pdf - Submitted Version Restricted to Registered users only Download (4MB) | Request a copy |
Abstract
Indonesia, as an agrarian country, has coffee as one of its leading commodities, with two main types: Robusta and Arabica. Differences in the characteristics of these coffee types, along with variations in roasting levels (light, medium, and dark), often create challenges in visual identification, which is still performed manually. This study aims to implement and evaluate a Convolutional Neural Network (CNN) method using the MobileNetV2 model on a mobile-based system to classify Robusta and Arabica coffee beans at different roasting levels through visual images. The dataset consists of 2,100 images divided into six classes. The system is implemented in an Android-based application to facilitate real-time classification. The results show that the model achieves a test accuracy of 89.76%, with precision, recall, and F1-score values above 78% across all classes. In addition, the System Usability Scale (SUS) evaluation yields a score of 81.69, which is categorized as acceptable with grade A. These results indicate that the CNN-MobileNetV2 method is effective for coffee bean classification, although limitations related to lighting conditions in the dataset remain.
| Item Type: | Thesis (Undergraduate) | ||||||
|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||
| Uncontrolled Keywords: | Convolutional Neural Network (CNN), MobileNetV2, Klasifikasi Biji Kopi, Tingkat Roasting. | ||||||
| Subjects: | 410 - Rumpun Ilmu Teknik > 450 - Teknik Elektro dan Informatika > 458 - Teknik Informatika 410 - Rumpun Ilmu Teknik > 450 - Teknik Elektro dan Informatika > 462 - Teknologi Informasi |
||||||
| Divisions: | Jurusan Teknologi Informasi > Prodi D4 Teknik Informatika > Tugas Akhir | ||||||
| Depositing User: | Johan Indra Maulana | ||||||
| Date Deposited: | 25 May 2026 00:50 | ||||||
| Last Modified: | 25 May 2026 00:53 | ||||||
| URI: | https://sipora.polije.ac.id/id/eprint/56002 |
Actions (login required)
 |
View Item |
