KLASIFIKASI SAMPAH MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK (CNN)

TIAN, AGUS and Rini, Dian Palupi and Miraswan, Kanda Januar (2025) KLASIFIKASI SAMPAH MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK (CNN). Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021182126022_cover.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (129kB)
	Text RAMA_55201_09021182126022.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021182126022_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_55201_09021182126022_0023027804_0009019002_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (553kB)
	Text RAMA_55201_09021182126022_0023027804_0009019002_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (534kB) | Request a copy
	Text RAMA_55201_09021182126022_0023027804_0009019002_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (406kB) | Request a copy
	Text RAMA_55201_09021182126022_0023027804_0009019002_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (623kB) | Request a copy
	Text RAMA_55201_09021182126022_0023027804_0009019002_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (622kB) | Request a copy
	Text RAMA_55201_09021182126022_0023027804_0009019002_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (238kB) | Request a copy
	Text RAMA_55201_09021182126022_0023027804_0009019002_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (211kB) | Request a copy
	Text RAMA_55201_09021182126022_0023027804_0009019002_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (114kB) | Request a copy

Abstract

Effective waste management is a major challenge in maintaining environmental cleanliness and sustainability. One important step is waste separation, such as distinguishing between organic and inorganic waste. Organic waste, such as food scraps and dry leaves, can be processed into compost or environmentally friendly energy. Meanwhile, inorganic waste, such as plastic, glass, and metal, can be recycled into new products. Proper waste separation allows for more efficient waste processing and has a positive impact on the environment. This study proposes an automated waste classification system based on digital images using deep learning technology with Convolutional Neural Network (CNN) architecture. The three CNN models used are VGG-16, ResNet-50, and Xception. The dataset consists of two main classes: organic and inorganic waste. The study was conducted under 12 testing scenarios with variations in learning rate and batch size. Evaluation metrics include accuracy, precision, recall, and F1-score. The best result was achieved by the VGG-16 model with a learning rate of 1e-4 and batch size of 64, reaching 94.34% accuracy, 90.58% precision, 95.05% recall, and 92.76% F1-score.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	waste classification, deep learning, CNN, VGG-16, ResNet-50, Xception
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	AGUS TIAN
Date Deposited:	23 Jul 2025 08:12
Last Modified:	23 Jul 2025 08:12
URI:	http://repository.unsri.ac.id/id/eprint/180146

Actions (login required)

View Item