ANALISIS PERFORMANSI METODE CONVOLUTIONAL NEURAL NETWORK (CNN) DAN SUPPORT VECTOR MACHINE (SVM) DALAM MENDETEKSI KEASLIAN DAN NOMINAL CITRA UANG KERTAS RUPIAH

Jonathan Andrew Pandapotan Simarmata, . (2023) ANALISIS PERFORMANSI METODE CONVOLUTIONAL NEURAL NETWORK (CNN) DAN SUPPORT VECTOR MACHINE (SVM) DALAM MENDETEKSI KEASLIAN DAN NOMINAL CITRA UANG KERTAS RUPIAH. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (163kB)
[img] Text
AWAL.pdf
Download (1MB)
[img] Text
BAB 1.pdf
Download (285kB)
[img] Text
BAB 2.pdf
Download (512kB)
[img] Text
BAB 3.pdf
Download (247kB)
[img] Text
BAB 4.pdf
Download (1MB)
[img] Text
BAB 5.pdf
Download (205kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (196kB)
[img] Text
RIWAYAT HIDUP.pdf
Download (99kB)
[img] Text
LAMPIRAN.pdf
Download (3MB)
[img] Text
HASIL PLAGIARISME.pdf
Download (8MB)
[img] Text
ARTIKEL KI.pdf
Download (579kB)

Abstract

The difficulty of distinguishing real money from fake money requires people to increase their caution about the authenticity of the money they own. Most manual verification of the authenticity of money is said to be less effective and efficient because it takes a huge amount of time and energy, which is wasted. As a result, the authenticity of the detection system for rupiah banknotes needs to be established, and this system can also be used in devices or cash transaction machines for further implementation. Convolutional Neural Network (CNN) and Support Vector Machine (SVM) are deep learning and machine learning algorithms that are often used in solving problems of image classification and object detection. This study will carry out the process of classification on the image of the rupiah with the use of the collection of data on the image of the rupiah to classify the six classes of image rupiah that are 20,000 Genuine, 20,000 Counterfeit, 50,000 Genuine, 50,000 Counterfeit, 100,000 genuine, and 100,000 Counterfeit using the methods of CNN and SVM. The CNN method can classify images with an accuracy of 98.33%, while the SVM method can conduct classifications with a precision of 96.67%.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil : 1910314017] [Pembimbing : Achmad Zuchriadi P.] [Penguji 1 : Henry B. H. Sitorus] [Penguji 2 : Fajar Rahayu I.]
Uncontrolled Keywords: Rupiah Banknotes, Image Classification, Convolutional Neural Network (CNN), Support Vector Machine (SVM), Deep Learning, Machine Learning
Subjects: H Social Sciences > HA Statistics
H Social Sciences > HJ Public Finance
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
Divisions: Fakultas Teknik > Program Studi Teknik Elektro (S1)
Depositing User: Jonathan Andrew Pandapotan Simarmata
Date Deposited: 21 Jul 2023 04:35
Last Modified: 21 Jul 2023 04:35
URI: http://repository.upnvj.ac.id/id/eprint/25524

Actions (login required)

View Item View Item