Identifikasi Jenis Ikan Cupang Berdasarkan Gambar Meggunakan Metode Convolutional Neural Network

Laksono, Surya Adi (2024) Identifikasi Jenis Ikan Cupang Berdasarkan Gambar Meggunakan Metode Convolutional Neural Network. Undergraduate thesis, UPN Veteran Jawa Timur.

[img] Text (COVER)
COVER.pdf

Download (4MB)
[img] Text (BAB 1)
BAB 1.pdf

Download (824kB)
[img] Text (BAB 2)
BAB 2.pdf
Restricted to Repository staff only until 30 April 2026.

Download (1MB)
[img] Text (BAB 3)
BAB 3.pdf
Restricted to Repository staff only until 30 April 2026.

Download (1MB)
[img] Text (BAB 4)
BAB 4.pdf
Restricted to Repository staff only until 30 April 2026.

Download (1MB)
[img] Text (BAB 5)
BAB 5.pdf

Download (821kB)
[img] Text (DAFTAR PUSTAKA)
DAFTAR PUSTAKA.pdf

Download (958kB)
[img] Text (LAMPIRAN)
LAMPIRAN.pdf
Restricted to Repository staff only until 30 April 2026.

Download (931kB)

Abstract

This research was motivated by the difficulties of ordinary people in determining the types of betta fish on the market. Because the type of betta fish has a big influence on the offspring produced during spawning. Likewise, for people who will take part in betta fish contests, the type is very influential in determining the category of fish type that will be entered. Therefore, a system for identifying betta fish types is needed so that ordinary people can identify the type of betta fish independently. This system uses the Convolutional Neural Network method, a deep learning algorithm that is usually used to classify images with the Keras Sequential architecture which has a number of parameters of up to 1,424,403 parameters. This method was chosen because it is widely used in datasets in the form of images, and the dataset used in this research is images of betta fish. The dataset used is 330 data consisting of three classes. The system designed and implemented in this research was able to achieve an average accuracy of 97.8% in testing with 10 epochs, 98.7% in testing with 15 epochs, and 99.7% in testing with 20 epochs.

Item Type: Thesis (Undergraduate)
Contributors:
ContributionContributorsNIDN/NIDKEmail
Thesis advisorRahmat, BasukiNIDN0023076907UNSPECIFIED
Thesis advisorNugroho, BudiNIDN0707098003UNSPECIFIED
Subjects: Q Science > QA Mathematics > QA76.6 Computer Programming
Divisions: Faculty of Computer Science > Departemen of Informatics
Depositing User: Surya Adi Laksono
Date Deposited: 30 Apr 2024 04:51
Last Modified: 30 Apr 2024 04:51
URI: https://repository.upnjatim.ac.id/id/eprint/22554

Actions (login required)

View Item View Item