Muhammad Haswan Alfarandy, . (2025) PENERAPAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN) DENGAN ARSITEKTUR VGG16 UNTUK IDENTIFIKASI JENIS REMPAH RIMPANG. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (234kB) |
|
Text
AWAL.pdf Download (803kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (290kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (768kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (401kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 5.pdf Download (272kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (250kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (157kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (11MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (848kB) |
Abstract
Indonesia is among the top five spice-producing countries in the world, offering significant potential to develop this commodity. Spices are plant products with distinct aromas and various benefits. One notable spice category in Indonesia is rhizome spices, known for their thick roots or tubers. However, the similar shapes and colors among various rhizome types often make them difficult to distinguish, especially for those unfamiliar with these spices. Therefore, this study aims to identify several types of rhizome spices, including turmeric, ginger, galangal, and kencur. The study utilizes a Convolutional Neural Network (CNN) algorithm with the VGG16 architecture to build a model capable of identifying these rhizome types. The dataset comprises primary data collected directly by the researcher using a smartphone camera, and secondary data obtained from the Kaggle platform. The data is divided into three scenarios involving both data types. Evaluation results show that Scenario 3 yields the best performance, achieving 99% accuracy, precision, recall, and F1-score, with a loss value of 4.69%. Scenario 3 uses a combination of primary and secondary data with a data split ratio of 80:10:10, and serves as the basis for developing the graphical user interface (GUI).
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No. Panggil: 2110511122] [Pembimbing 1: Ridwan Raafi’udin] [Pembimbing 2: Catur Nugrahaeni Puspita Dewi] [Penguji 1: Neny Rosmawarni] [Penguji 2: Kharisma Wiati Gusti] |
| Uncontrolled Keywords: | Spices, Rhizome spice, CNN, VGG16. |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | MUHAMMAD HASWAN ALFARANDY |
| Date Deposited: | 26 Aug 2025 03:36 |
| Last Modified: | 26 Aug 2025 03:36 |
| URI: | http://repository.upnvj.ac.id/id/eprint/37273 |
Actions (login required)
 |
View Item |