Affandra Fahrezi, . (2025) IMPLEMENTASI CONVOLUTIONAL NEURAL NETWORK PADA APLIKASI ANDROID UNTUK KLASIFIKASI PENYAKIT BUAH JAMBU BIJI MENGGUNAKAN ARSITEKTUR VGG16. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![]() |
Text
ABSTRAK.pdf Download (432kB) |
![]() |
Text
AWAL.pdf Download (2MB) |
![]() |
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (1MB) |
![]() |
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (9MB) |
![]() |
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (1MB) |
![]() |
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (12MB) |
![]() |
Text
BAB 5.pdf Download (645kB) |
![]() |
Text
DAFTAR PUSTAKA.pdf Download (2MB) |
![]() |
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (117kB) |
![]() |
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (2MB) |
![]() |
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (18MB) |
![]() |
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (558kB) |
Abstract
Guava fruit production often declines due to diseases that are difficult for farmers to recognize early. A lack of knowledge about the visual symptoms of these diseases results in slow and inaccurate identification, hindering effective control efforts. This study aims to develop a disease detection system for guava fruit using a Convolutional Neural Network (CNN) based on the VGG16 architecture, implemented in an Android application. The CNN model is designed to classify four fruit conditions: Healthy, Phytophthora, Scab, and Styler End Rot. The dataset used has undergone preprocessing steps including resizing, data splitting, augmentation, and normalization. The best performing model was obtained using a learning rate of 0.001, the SGD optimizer, and a dropout rate of 0.5. Evaluation results show an accuracy of 90.70%, precision of 90.87%, recall of 90.68%, and an F1-score of 90.68%. The model is deployed using Google Cloud Run and stored in Google Cloud Storage. The developed Android application provides features such as login, image classification, and prediction history. Testing using the Blackbox Testing method indicates that all features function according to the designed specifications.
Item Type: | Thesis (Skripsi) |
---|---|
Additional Information: | [No.Panggil: 2110511001] [Pembimbing 1: Widya Cholil] [Pembimbing 2: Radinal Setyadinsa] [Penguji 1: Ridwan Raafi'udin] [Penguji 2: Nurul Afifah Arifuddin] |
Uncontrolled Keywords: | Android application, Convolutional Neural Network (CNN), guava, image classification, 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: | AFFANDRA FAHREZI |
Date Deposited: | 24 Jul 2025 04:31 |
Last Modified: | 24 Jul 2025 04:31 |
URI: | http://repository.upnvj.ac.id/id/eprint/37256 |
Actions (login required)
![]() |
View Item |