Deteksi Citra Deepfake Menggunakan Metode Hibrida Convolutional Neural Network dan Extreme Learning Machine

Sanjaya, Alvian Dwi (2024) Deteksi Citra Deepfake Menggunakan Metode Hibrida Convolutional Neural Network dan Extreme Learning Machine. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 20081010100.-Cover.pdf Download (1MB)
	Text (Bab 1) 20081010100.-Bab 1.pdf Download (135kB)
	Text (Bab 2) 20081010100.-Bab 2.pdf Restricted to Repository staff only until 30 October 2026. Download (730kB) \| Request a copy
	Text (Bab 3) 20081010100.-Bab 3.pdf Restricted to Repository staff only until 30 October 2026. Download (561kB) \| Request a copy
	Text (Bab 4) 20081010100.-Bab 4.pdf Restricted to Repository staff only until 30 October 2026. Download (922kB) \| Request a copy
	Text (Bab 5) 20081010100.-Bab 5.pdf Download (56kB)
	Text (Daftar Pustaka) 20081010100.-Daftar Pustaka.pdf Download (207kB)

Abstract

The use of Artificial Intelligence (AI) has seen a significant increase in recent years. One of the negative impacts of AI is the emergence of the term "Deepfake," which is used in a negative context. Deepfake involves the use of deep learning to manipulate or falsify someone's face in an image or video. Due to this issue, image detection is necessary. Deepfake image detection can be achieved using machine learning algorithms. Convolutional Neural Network (CNN) is one of the commonly used machine learning algorithms for image classification and is frequently utilized in research dealing with visual data. Besides CNN, image classification can also be performed using the Extreme Machine Learning (ELM) algorithm. ELM can classify images in less time compared to other algorithms. This research aims to detect deepfake images using a hybrid CNN-ELM method. In this research, ELM is used for the classification of features extracted by CNN. The average accuracy rate obtained in this research is 85.77%, which is higher than using only the CNN method, which achieved an accuracy rate of 82.27%. This demonstrates that using ELM in this hybrid method can improve the accuracy of the CNN method.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Anggraeny, Fetty Tri	NIDN0711028201	fettyanggraeny.if@upnjatim.ac.id
Thesis advisor	Mumpuni, Retno	NIDN0016078703	retnomumpuni.if@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Alvian Dwi Sanjaya

Date Deposited:

31 Oct 2024 05:16

Last Modified:

31 Oct 2024 05:16

URI:

https://repository.upnjatim.ac.id/id/eprint/31735