ARYADI, IRFAN (2025) PALM FRUIT RIPENESS CLASSIFICATION USING RESNET50 ARCHITECTURE. Tugas Akhir thesis, Informatics.
![[img]](http://eprints.uty.ac.id/style/images/fileicons/text.png) |
Text
5210411264_Irfan Aryadi_Abstrak.pdf Download (66kB) |
Abstract
Oil palm (Elaeis guineensis Jacq) is a key commodity in national economic development. However, manual determination of fruit ripeness is often inaccurate and inconsistent. This study develops a classification system for palm fruit ripeness using the ResNet50 architecture based on Convolutional Neural Networks (CNN). The dataset, comprising two classes—ripe and unripe—was collected directly from the field. Image augmentation was applied to increase data variation for training. Transfer learning was implemented by using pretrained ResNet50 weights from ImageNet, with additional layers including GlobalAveragePooling2D, Dropout, and Dense. The model was trained for 20 epochs using the Adam optimizer and binary crossentropy loss function, and evaluated using a confusion matrix. Training results showed a validation accuracy of 99.67% and a validation loss of 0.0093. Testing on unseen and new data achieved 100% accuracy, with precision, recall, and F1-score all reaching 1.00 for both classes. These results demonstrate the high performance and consistency of ResNet50 in automating the classification of palm fruit ripeness. Keywords: Palm Oil Classification, Ripeness Detection, CNN, ResNet50, Transfer Learning.
| Item Type: | Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir) |
|---|---|
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Sains Dan Teknologi > S1 Informatika |
| Depositing User: | Kaprodi S1 Informatika UTY |
| Date Deposited: | 17 Jul 2025 01:56 |
| Last Modified: | 17 Jul 2025 01:56 |
| URI: | http://eprints.uty.ac.id/id/eprint/18194 |
Actions (login required)
 |
View Item |
