KLASIFIKASI PENYAKIT DIABETES MELLITUS MENGGUNAKAN METODE SYNTHETIC MINORITY OVER-SAMPLING TECHNIQUE (SMOTE) RANDOM FOREST

Maulidiyyah, Nofa Auliyatul (2024) KLASIFIKASI PENYAKIT DIABETES MELLITUS MENGGUNAKAN METODE SYNTHETIC MINORITY OVER-SAMPLING TECHNIQUE (SMOTE) RANDOM FOREST. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (cover) 20083010029.-cover.pdf Download (517kB)
	Text (bab 1) 20083010029.-bab1.pdf Download (271kB)
	Text (bab 2) 20083010029.-bab2.pdf Restricted to Repository staff only until 30 July 2026. Download (423kB)
	Text (bab 3) 20083010029.-bab3.pdf Restricted to Repository staff only until 30 July 2026. Download (90kB)
	Text (bab 4) 20083010029.-bab4.pdf Restricted to Repository staff only until 30 July 2026. Download (1MB)
	Text (bab 5) 20083010029.-bab5.pdf Download (61kB)
	Text (daftar pustaka) 20083010029.-daftarpustaka.pdf Download (216kB)
	Text (lampiran) 20083010029.-lampiran.pdf Restricted to Repository staff only Download (129kB)

Abstract

Indonesia ranks fifth globally, with an estimated 19.47 million people suffering from diabetes in 2021, projected to rise to 23.32 million by 2030. Diabetes can be prevented by carrying out early detection and using a machine learning approach to predict the disease. However, predictions often become less accurate because the available data is not balanced in the class distribution. This research aims to address the problem of data imbalance and compare the performance of models in predicting diabetes. The methods used are the Synthetic Minority Oversampling Technique (SMOTE) method to overcome data imbalances, Random Forest to classify diabetes, and Confusion Matrix to calculate model performance evaluations. The research results show that the model trained with data that went through the SMOTE process showed higher accuracy, namely 98%, compared to the model without SMOTE, which produced an accuracy of 93%. Research shows that the use of SMOTE in the Random Forest model training process significantly reduces prediction errors and increases classification accuracy.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Trimono, Trimono	NIDN0008099501	trimono.stat@upnjatim.ac.id
Thesis advisor	Damaliana, Aviolla Terza	NIDN0002089402	aviolla.terza.sada@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Data Science

Depositing User:

Nofa Auliyatul Maulidiyyah

Date Deposited:

30 Jul 2024 06:31

Last Modified:

30 Jul 2024 06:31

URI:

https://repository.upnjatim.ac.id/id/eprint/28001