IMPLEMENTASI CONVOLUTIONAL NEURAL NETWORK (CNN) DAN LONG SHORT-TERM MEMORY RECCURENT (LSTM) PADA PENGENALAN TOKOH WAYANG KULIT BERBASIS ANDROID

Kurnianto, Achmad Fajar (2024) IMPLEMENTASI CONVOLUTIONAL NEURAL NETWORK (CNN) DAN LONG SHORT-TERM MEMORY RECCURENT (LSTM) PADA PENGENALAN TOKOH WAYANG KULIT BERBASIS ANDROID. Undergraduate thesis, UNIVERSITAS PEMBANGUNAN NASIONAL "VETERAN" JAWA TIMUR.

	Text (Cover) 20081010235_Cover.pdf Download (1MB)
	Text (Bab 1) 20081010235_BAB I.pdf Download (36kB)
	Text (Bab 2) 20081010235_BAB II.pdf Restricted to Registered users only until 13 December 2026. Download (669kB) \| Request a copy
	Text (Bab 3) 20081010235_BAB III.pdf Restricted to Registered users only until 13 December 2026. Download (2MB) \| Request a copy
	Text (Bab 4) 20081010235_BAB IV.pdf Restricted to Registered users only until 13 December 2026. Download (1MB) \| Request a copy
	Text (Bab 5) 20081010235_BAB V.pdf Download (27kB)
	Text (Daftar Pustaka) 20081010235_Daftar Pustaka.pdf Download (102kB)

Abstract

Wayang Kulit is an Indonesian cultural heritage rich in art and character, playing an important role in shaping the identity of society, especially in Java and Bali. Sanggar Ngrekodoyo in Surabaya actively preserves this art through performances and training. However, with the development of technology, the interest of the younger generation in traditional arts has decreased. The author developed the Android application "wayangku" to support the preservation of Wayang Kulit. This application recognizes Wayang Kulit characters through photos and provides background stories using CNN and LSTM technology, improving recognition accuracy with visual features and temporal patterns. This study used 3600 images from 24 classes of Wayang Kulit. The test results showed that the CNN-LSTM model in "Wayangku" achieved 99% accuracy with convolutional layers (16, 32, 64, 128) and LSTM layers (128). This application has the potential to be an effective tool in preserving Wayang Kulit and introducing it to the younger generation.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Sari, Anggraini Puspita	NIDN0716088605	anggraini.puspita.if@upnjatim.ac.id
Thesis advisor	Junaidi, Achmad	NIDN0710117803	achmadjunaidi.if@upnjatim.ac.id

Subjects:

T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105 Computer Network

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Achmad Fajar Kurnianto

Date Deposited:

13 Dec 2024 07:18

Last Modified:

13 Dec 2024 07:18

URI:

https://repository.upnjatim.ac.id/id/eprint/33338