KLASTERISASI VARIABEL INDIKATOR DIABETES MELLITUS DENGAN PENDEKATAN ALGORITMA FUZZY C-MEANS

Adiwidyatma, Afdhal Reshanda (2024) KLASTERISASI VARIABEL INDIKATOR DIABETES MELLITUS DENGAN PENDEKATAN ALGORITMA FUZZY C-MEANS. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text 20083010024.-cover.pdf Download (5MB)
	Text (bab 1) 20083010024.-bab1.pdf Download (36kB)
	Text (bab 2) 20083010024.-bab2.pdf Restricted to Repository staff only until 30 July 2026. Download (296kB)
	Text (bab 3) 20083010024.-bab3.pdf Restricted to Repository staff only until 30 July 2026. Download (39kB)
	Text (bab 4) 20083010024.-bab4.pdf Restricted to Repository staff only until 30 July 2026. Download (424kB)
	Text (bab 5) 20083010024.-bab5.pdf Download (12kB)
	Text (daftar pustaka) 20083010024.-daftarpustaka.pdf Download (87kB)
	Text (lampiran) 20083010024.-lampiran.pdf Restricted to Repository staff only until 30 July 2026. Download (322kB)

Abstract

This research focuses on the effectiveness of the Clustering algorithm, namely Fuzzy C-Means using the K-means algorithm as a supporting method, in analyzing indicator variables that cause Diabetes Mellitus. Diabetes mellitus is a chronic disease characterized by high levels of sugar (glucose) in the blood. Indonesia ranks 5th with the highest number of Diabetes Mellitus sufferers in the world. This research aims to understand the pattern of indicator variables that cause diabetes mellitus and test the effectiveness of the clustering algorithm used. The data analysis methods include data collection, data pre-processing, dividing the number of clusters, algorithm implementation, model adjustment, model training, model evaluation, and results analysis. The research results show that the Fuzzy C-Means algorithm gets a Coeffient of Fuzzyness score of 0.23 with a validation score of 0.40, while the supporting method used by the K-means algorithm gets a validation score of 0.32. These results indicate that the Fuzzy C-Means algorithm is superior in clustering indicator variables that cause diabetes mellitus. The results of which variables have the most influence on the values of clusters 0 and 1. Where cluster 0 is a cluster that shows which variables are more at risk of developing diabetes, while cluster 1 is a cluster whose values show which variables are far from the risk of causing diabetes mellitus.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Mas Diyasa, I Gede Susrama	NIDN0019067008	igsusrama.if@student.upnjatim.ac.id
Thesis advisor	Trimono, Trimono	NIDN0008099501	trimono.stat@student.upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Data Science

Depositing User:

Afdhal Reshanda Adiwidyatma

Date Deposited:

30 Jul 2024 06:43

Last Modified:

30 Jul 2024 06:43

URI:

https://repository.upnjatim.ac.id/id/eprint/28007