FAUZI, RAYHAN DZIKRI (2025) TOMATO RIPENESS PREDICTION SYSTEM USING CONVOLUTIONAL NEURAL NETWORK METHOD. Tugas Akhir thesis, Informatics.
![[img]](http://eprints.uty.ac.id/style/images/fileicons/text.png) |
Text
5210411281_Rayhan Dzikri Fauzi_Abstrak.pdf Download (72kB) |
Abstract
Manual determination of tomato ripeness remains inefficient due to its subjectivity, labor-intensive nature, and susceptibility to inconsistency. Therefore, this study employs the Convolutional Neural Network (CNN) method to automate the assessment of tomato ripeness. The VGG16 model is compared with a Vanilla CNN in predicting ripeness. As a result, VGG16 achieves an accuracy of 98.41% on the training data and 99.38% on the validation data, while the Vanilla CNN exhibits signs of overfitting. To address this overfitting, techniques such as regularization, dropout, and hyperparameter fine-tuning are necessary. This study demonstrates that VGG16 outperforms Vanilla CNN in predicting tomato ripeness, yielding more stable and accurate results. However, further optimization is required to enhance the model’s performance under varying lighting conditions and tomato shape variations. With the appropriate methodologies, CNN-based technology can serve as an effective solution to improve the efficiency and accuracy of tomato ripeness classification in the agricultural and food processing industries. Keywords: Prediction accuracy, Convolutional Neural Network (CNN), Tomato fruit ripeness, Overfitting, Digital image processing, VGG16, Vanilla CNN
| 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: | 07 May 2025 03:21 |
| Last Modified: | 07 May 2025 03:21 |
| URI: | http://eprints.uty.ac.id/id/eprint/17887 |
Actions (login required)
 |
View Item |
