Handayanti, Ima (2025) CONVOLUTIONAL NEURAL NETWORK IN ORGANIC AND INORGANIC WASTE CLASSIFICATION. Tugas Akhir thesis, University of Technology Yogyakarta.
![[img]](http://eprints.uty.ac.id/style/images/fileicons/text.png) |
Text
5190411587_Ima Handayanti_Abstrak.pdf Download (15kB) |
Abstract
Household waste management in Indonesia continues to face numerous challenges, particularly in the separation of organic and inorganic waste. A lack of public awareness and understanding of the importance of waste sorting contributes to the low effectiveness of recycling efforts. This research aims to develop a simple web-based waste classification system using a Convolutional Neural Network (CNN) to assist in the automated sorting process. The dataset comprised 900 images of household waste, captured independently under varying lighting conditions and times of day. The CNN model was constructed using three Conv2D layers, MaxPooling, Flatten, and several Dense and Dropout layers. Evaluation results demonstrated that the CNN model could classify organic and inorganic waste with an accuracy of 85.56%, a precision of 95.71%, and a recall of 74.44%. The system was implemented in a simple web interface that allows users to upload images and receive classification results instantly. It is hoped that this system will serve as an educational tool to encourage the habit of sorting waste at its source. Keywords: Accuracy, Convolutional Neural Network, waste classification, waste sorting, inorganic waste, organic waste, web
| 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: | 13 Nov 2025 02:02 |
| Last Modified: | 13 Nov 2025 02:02 |
| URI: | http://eprints.uty.ac.id/id/eprint/19394 |
Actions (login required)
 |
View Item |
