Klasifikasi Curah Hujan Harian Menggunakan Metode K-Nearest Neighbor Dengan Optimasi Algoritma Genetika

Ramadhan, Muhammad Alviriza (2024) Klasifikasi Curah Hujan Harian Menggunakan Metode K-Nearest Neighbor Dengan Optimasi Algoritma Genetika. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (COVER) 20081010143-Cover.pdf Download (695kB)
	Text (BAB I) 20081010143-bab1.pdf Download (88kB)
	Text (BAB II) 20081010143-bab2.pdf Restricted to Repository staff only until 4 June 2026. Download (184kB)
	Text (BAB III) 20081010143-bab3.pdf Restricted to Repository staff only until 4 June 2026. Download (318kB)
	Text (BAB IV) 20081010143-bab4.pdf Restricted to Repository staff only until 4 June 2026. Download (630kB)
	Text (BAB V) 20081010143-bab5.pdf Download (11kB)
	Text (DAFTAR PUSTAKA) 20081010143-daftarpustaka.pdf Download (132kB)

Abstract

Weather is a condition of the atmosphere observed over a relatively short or brief period within a limited territory. The advancement of technology today significantly aids humanity, particularly in weather observation such as the classification of daily rainfall. One of the methods utilized is the K-NN method along with genetic algorithms. Weather and climate changes can be influenced by many factors such as temperature, humidity, air pressure, wind speed, wind direction at maximum speed, duration of sunlight, and rainfall. Therefore, this study conducted a "Classification of daily rainfall using the KNN method with genetic algorithm optimization," with the expected output being the accuracy level of the applied methods. The results of this research indicate that datasets trained and tested using a data training and data testing ratio of 60:40 tend to yield higher accuracy levels. The K-Nearest Neighbor method with genetic algorithm optimization, executed using a parameter of 50 generations, tends to produce higher accuracy levels. Additionally, the K-Nearest Neighbor method with genetic algorithm optimization, executed using a crossover probability parameter of 0.5 when combined with a parameter of 50 generations, yields greater accuracy compared to using a crossover probability parameter of 0.75 combined with the same number of generations.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Anggraeny, Fetty Tri	NIDN0711028201	fettyanggraeny.if@upnjatim.ac.id
Thesis advisor	Putra, Chrystia Aji	NIDN0008108605	ajiputra@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Muhammad Alviriza Ramadhan

Date Deposited:

04 Jun 2024 05:40

Last Modified:

04 Jun 2024 05:40

URI:

https://repository.upnjatim.ac.id/id/eprint/24100