Skripsi
PENGEMBANGAN SISTEM PENDETEKSI PENYAKIT TANAMAN PADA CITRA DAUN MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN) BERBASIS APLIKASI ANDROID
Detection of plant diseases through visual observation of leaves manually has several limitations and takes a long time. This research develops an Android application-based plant disease detection system that can identify plant diseases through leaf images using the Convolutional Neural Network (CNN) algorithm. The dataset used in this research comes from Kaggle Disease Classification, which consists of various images of plant leaves with healthy and diseased conditions. In the development process, several experiments were conducted with batch size variations (8, 16, 32, and 64) at epoch 50 to get the best performing model. The results showed that the model with a batch size of 64 produced the best performance with an accuracy value of 98.68%, precision of 98.76%, recall of 98.66%, and F1-score of 98.68%. The developed system successfully automates the process of plant disease identification through Android devices so that it can help farmers and agricultural practitioners in diagnosing plant problems more quickly and accurately. The implementation of this system is expected to provide practical solutions in early detection of plant diseases through leaf image observation.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2407006952 | T162776 | T1627762024 | Central Library (REFERENS) | Available but not for loan - Not for Loan |
No other version available