Maulana, Riza Nur (2026) RANCANG BANGUN APLIKASI DETEKSI PENYAKIT PADA DAUN KOPI MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK. S1 / D3 thesis, Universitas Kuningan.
ABSTRAK.pdf
Download (1MB)
BAB I.pdf
Download (101kB)
BAB II.pdf
Restricted to Repository staff only
Download (1MB) | Request a copy
BAB III.pdf
Restricted to Repository staff only
Download (2MB) | Request a copy
BAB IV.pdf
Restricted to Repository staff only
Download (2MB) | Request a copy
BAB V.pdf
Download (14kB)
DAFTAR PUSTAKA.pdf
Download (143kB)
LAMPIRAN.pdf
Restricted to Repository staff only
Download (7MB) | Request a copy
Abstract
Tanaman kopi merupakan salah satu komoditas perkebunan penting di Indonesia yang memiliki nilai ekonomi tinggi dan berperan dalam meningkatkan pendapatan petani. Namun, produktivitas tanaman kopi dapat menurun akibat serangan penyakit daun, seperti antraknosa, bercak daun, karat daun, dan embun jelaga. Proses identifikasi yang masih dilakukan secara visual oleh petani berpotensi menimbulkan kesalahan dan keterlambatan penanganan. Penelitian ini bertujuan untuk merancang dan membangun aplikasi deteksi penyakit daun kopi berbasis Android menggunakan algoritma Convolutional Neural Network (CNN) dengan arsitektur MobileNetV2. Metode pengembangan sistem yang digunakan adalah Rapid Application Development (RAD). Dataset yang digunakan berupa kombinasi data primer dan sekunder berjumlah 5.000 citra daun kopi yang terdiri atas kelas antraknosa, bercak daun, daun sehat, embun jelaga, dan karat daun. Tahapan penelitian meliputi preprocessing citra, pelatihan model, evaluasi menggunakan metrik accuracy, precision, recall, dan F1-score, serta implementasi model ke dalam aplikasi Android. Hasil pengujian menunjukkan bahwa model memperoleh nilai accuracy sebesar 99% pada 500 data uji. Pengujian User Acceptance Test (UAT) memperoleh nilai sebesar 90,07% dengan kategori sangat baik. Hasil penelitian menunjukkan bahwa aplikasi mampu mendeteksi penyakit daun kopi dengan akurat dan dapat diterima dengan baik oleh pengguna. Meskipun model menunjukkan performa yang tinggi, penelitian ini memiliki beberapa keterbatasan, di antaranya variasi kondisi pencahayaan saat pengambilan citra, perbedaan spesies atau varietas kopi yang diuji, serta potensi bias yang berasal dari penggunaan sebagian data sekunder.
Coffee plants are one of the most important agricultural commodities in Indonesia, with high economic value and a role in increasing farmers' income. However, coffee plant productivity can decrease due to leaf diseases, such as anthracnose, leaf spot, leaf rust, and sooty mold. The identification process, which is still carried out visually by farmers, is prone to errors and delays in treatment. This study aimed to design and develop an Android-based mobile application for detecting coffee leaf diseases using the Convolutional Neural Network (CNN) algorithm with MobileNetV2 architecture. The system development method used is Rapid Application Development (RAD). The The dataset used consists of 5,000 combined primary and secondary images of coffee leaves, divided into classes for anthracnose, leaf spot, healthy leaves, sooty mold, and leaf rust. The research stages include image preprocessing, model training, evaluation using the accuracy, precision, recall, and F1-score metrics, and model implementation in the Android application. The evaluation results show that the model achieved an accuracy score of 99% on 500 test images. The User Acceptance Test (UAT) produced a score of 90.07%, categorized as 'very good'. The results of the study show that the application can accurately detect coffee leaf diseases and is well-received by users. Although the model demonstrated high performance, this study has several limitations, including variations in lighting conditions during image acquisition, differences in the coffee species or varieties tested, and potential bias arising from the partial use of secondary data.
| Item Type: | Thesis (S1 / D3) |
|---|---|
| Uncontrolled Keywords: | Android, Convolutional Neural Network, MobileNetV2, Penyakit Daun Kopi, Coffee Leaf Disease |
| Subjects: | Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Ilmu Komputer > S1 Teknik Informatika |
| Depositing User: | S.Kom Riza Nur Maulana |
| Date Deposited: | 10 Aug 2026 06:38 |
| Last Modified: | 10 Aug 2026 06:38 |
| URI: | https://rama.uniku.ac.id/id/eprint/6295 |

