Penerapan Algoritma Extreme Learning Machine pada Aplikasi Deteksi Penyakit Diabetes

Alibasyah, Fahmi Nugroho (2022) Penerapan Algoritma Extreme Learning Machine pada Aplikasi Deteksi Penyakit Diabetes. Undergraduate thesis, UPN Veteran Jawa Timur.

[img]
Preview
Text (Cover)
18081010065-cover.pdf

Download (2MB) | Preview
[img]
Preview
Text (BAB I)
18081010065-bab1.pdf

Download (83kB) | Preview
[img]
Preview
Text (BAB II)
18081010065-bab2.pdf

Download (324kB) | Preview
[img] Text (BAB III)
18081010065-bab3.pdf
Restricted to Registered users only until 30 May 2024.

Download (340kB)
[img] Text (BAB IV)
18081010065-bab4.pdf
Restricted to Registered users only until 30 May 2024.

Download (322kB)
[img]
Preview
Text (BAB V)
18081010065-bab5.pdf

Download (11kB) | Preview
[img]
Preview
Text (Daftar Pustaka)
18081010065-daftarpustaka.pdf

Download (195kB) | Preview

Abstract

Diabetes Mellitus is a non-communicable disease caused by damage to the pancreas that causes reduced insulin. Increased levels of sugar in the blood or insulin resistance is the biggest health problem in the world today. In this study, the authors developed a Diabetes Mellitus detection application using medical record data. This system uses the Extreme Learning Machine (ELM) algorithm. ELM has one advantage, namely that the training process is faster when compared to other learning algorithms. This study uses a dataset from the Pima Indians Diabetes Database obtained through the open source website Kaggle. The number of datasets is 768 data, which will pass the pre-processing stage before entering the classification stage. System testing is carried out using two scenarios, namely the scenario of variations in the number of training data, and scenarios of variations in the number of nodes in the hidden layer. From the experimental results, the best accuracy is obtained in a scenario that uses 80% training data - 20% test data, and uses 75 nodes in the hidden layer. The average value of precision, recall, and F1-score obtained is 0.80 while the test accuracy is 80%.

Item Type: Thesis (Undergraduate)
Contributors:
ContributionContributorsNIDN/NIDKEmail
Thesis advisorVia, Yisti VitaNIDN0025048602yistivia.if@upnjatim.ac.id
Thesis advisorSaputra, Wahyu S JNIDN0725088601wahyu.s.j.saputra.if@upnjatim.ac.id
Subjects: Q Science > QA Mathematics > QA76 Computer software
Q Science > QA Mathematics > QA76.6 Computer Programming
Divisions: Faculty of Computer Science > Departemen of Informatics
Depositing User: Fahmi Nugroho Alibasyah
Date Deposited: 30 May 2022 07:09
Last Modified: 30 May 2022 07:09
URI: http://repository.upnjatim.ac.id/id/eprint/6336

Actions (login required)

View Item View Item