KLASIFIKASI RUMAH ADAT DI INDONESIA MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN)

Nida Zakia Aldina, . (2024) KLASIFIKASI RUMAH ADAT DI INDONESIA MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN). Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

	Text ABSTRAK.pdf Download (359kB)
	Text AWAL.pdf Download (1MB)
	Text BAB 1.pdf Restricted to Repository UPNVJ Only Download (433kB)
	Text BAB 2.pdf Restricted to Repository UPNVJ Only Download (867kB)
	Text BAB 3.pdf Restricted to Repository UPNVJ Only Download (1MB)
	Text BAB 4.pdf Restricted to Repository UPNVJ Only Download (4MB)
	Text BAB 5.pdf Download (417kB)
	Text DAFTAR PUSTAKA.pdf Download (389kB)
	Text RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (65kB)
	Text LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB)
	Text HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (1MB)
	Text ARTIKEL KI.pdf Restricted to Repository staff only Download (658kB)

Abstract

Indonesia is a country rich in diversity such as ethnicity and culture. Each region in Indonesia has its own characteristics, including traditional houses owned by each region in Indonesia. Traditional house buildings are included in the cultural heritage that needs to be preserved and maintained because they have important historical, scientific, and educational values. The many types of traditional houses in Indonesia make it difficult for people to identify types of traditional houses. Along with the development of technology, especially in the field of artificial intelligence, this can be utilized in helping preserve cultural heritage in Indonesia. Therefore, there is a need for technology that can classify or identify types of traditional houses. This research uses the Convolutional Neural Network (CNN) algorithm and uses two types of optimization functions, namely Adam and RMSprop as a comparison to build a model that can classify as many as 8 (eight) types of traditional houses. The results show that the CNN model built using 6 CNN layers consisting of convolutional layer, pooling layer, flatten, and fully connected layer produces a test accuracy of 96.07% with a loss of 0.1440 for the Adam optimizer, and a test accuracy of 95% with a loss of 0.1554 using the RMSprop optimizer. Based on these results, in classifying 8 types of traditional houses, the CNN model produces better accuracy using the Adam optimizer

Item Type:	Thesis (Skripsi)
Additional Information:	[No.Panggil :2010511143] [Pembimbing: WIdya Cholil] [Penguji 1: Ermatita] [Penguji 2: Erly Krisnanik]
Uncontrolled Keywords:	Classification, Traditional Houses, CNN, Adam, RMSprop
Subjects:	L Education > L Education (General) Q Science > Q Science (General) T Technology > T Technology (General)
Divisions:	Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User:	NIDA ZAKIA ALDINA
Date Deposited:	29 Aug 2024 03:05
Last Modified:	29 Aug 2024 03:05
URI:	http://repository.upnvj.ac.id/id/eprint/30817

Actions (login required)

View Item