Rifai, Muhammad Rinal (2026) KLASIFIKASI JENIS-JENIS POHON BERINGIN MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN) (Studi Kasus: Kios Bunga Rabiku Florist). S1 / D3 thesis, Universitas Kuningan.
ABSTRAK.pdf
Download (747kB)
BAB I.pdf
Download (627kB)
BAB II.pdf
Restricted to Repository staff only
Download (1MB) | Request a copy
BAB III.pdf
Restricted to Repository staff only
Download (1MB) | Request a copy
BAB IV.pdf
Restricted to Repository staff only
Download (1MB) | Request a copy
BAB V.pdf
Download (240kB)
DAFTAR PUSTAKA.pdf
Download (261kB)
LAMPIRAN.pdf
Restricted to Repository staff only
Download (1MB) | Request a copy
Abstract
Pohon beringin memiliki beragam jenis dengan karakteristik fisik yang saling menyerupai sehingga menyulitkan proses identifikasi secara visual. Penelitian ini bertujuan mengembangkan sistem klasifikasi jenis pohon beringin berbasis citra menggunakan algoritma Convolutional Neural Network (CNN) dengan pendekatan transfer learning MobileNetV2. Dataset yang digunakan terdiri dari 5.000 citra daun yang terbagi ke dalam lima kelas, yaitu Beringin Dollar, Beringin Jepang, Beringin Kimeng, Beringin Korea Bulat, dan Beringin Korea Oval. Tahapan penelitian meliputi preprocessing data, perancangan arsitektur CNN, pelatihan model, serta evaluasi performa menggunakan metrik akurasi, presisi, recall, dan F1-score. Hasil pengujian menunjukkan bahwa model mencapai akurasi sebesar 99,0% pada data uji dengan nilai rata-rata presisi, recall, dan F1-score sebesar 99,0%, yang menandakan performa klasifikasi sangat baik meskipun terdapat kemiripan karakteristik antar kelas. Model yang telah dilatih kemudian diimplementasikan dalam aplikasi Android untuk memudahkan proses identifikasi jenis pohon beringin secara cepat dan akurat. Sistem ini diharapkan dapat membantu masyarakat dan pelaku usaha tanaman hias serta mendukung digitalisasi pengetahuan tanaman di Indonesia.
Banyan tree has various species with similar physical characteristics, making visual identification difficult. This research aims to develop a banyan tree species classification system based on images using the Convolutional Neural Network (CNN) algorithm with a MobileNetV2 transfer learning approach. The dataset used consists of 1,000 images of banyan trees taken from various locations in Indonesia. This research aims to develop a banyan tree classification system based on images using the Convolutional Neural Network (CNN) algorithm with a MobileNetV2 transfer learning approach. The dataset used consists of 5,000 leaf images divided into five classes, namely Dollar Banyan, Japanese Banyan, Kimeng Banyan, Round Korean Banyan, and Korean Oval Banyan Oval Banyan. The research stages include data preprocessing, CNN architecture design, model training, and performance evaluation using accuracy, precision, recall, and F1-score metrics. The test results shows that the model achieved an accuracy of 99.0% on the test data with an average precision, recall, and F1-score of 99.0%, which indicates excellent classification performance despite the similarity of characteristics between classes. The trained model is then implemented in an Android application to facilitate the process of identifying fig tree species quickly and accurately. This system is expected to assist the community, ornamental plant businesses and to support the digitalization of plant knowledge in Indonesia.
| Item Type: | Thesis (S1 / D3) |
|---|---|
| Uncontrolled Keywords: | Klasifikasi Citra, Pohon Beringin, Aplikasi Android, Convolutional Neural Network, MobileNetV2, Image Classification, Banyan Tree, Android Application. |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > S1 Teknik Informatika |
| Depositing User: | S.Kom Muhammad Rinal Rifai |
| Date Deposited: | 28 Sep 2026 07:37 |
| Last Modified: | 28 Sep 2026 07:37 |
| URI: | https://rama.uniku.ac.id/id/eprint/6752 |

