Perbandingan efektivitas support vector machine dan random forest dalam identifikasi diabetes dan penyakit jantung

Hutama, Elbert (2024) Perbandingan efektivitas support vector machine dan random forest dalam identifikasi diabetes dan penyakit jantung. Bachelor thesis, Universitas Pelita Harapan.

[thumbnail of Title]
Preview
Text (Title)
Title.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (16kB) | Preview
[thumbnail of Abstract]
Preview
Text (Abstract)
Abstract.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (383kB) | Preview
[thumbnail of ToC]
Preview
Text (ToC)
ToC.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (625kB) | Preview
[thumbnail of Chapter 1]
Preview
Text (Chapter 1)
Chapter 1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (747kB) | Preview
[thumbnail of Chapter 2] Text (Chapter 2)
Chapter 2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (2MB)
[thumbnail of Chapter 3] Text (Chapter 3)
Chapter 3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)
[thumbnail of Chapter 4] Text (Chapter 4)
Chapter 4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (5MB)
[thumbnail of Chapter 5] Text (Chapter 5)
Chapter 5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (475kB)
[thumbnail of Bibliography]
Preview
Text (Bibliography)
Bibliography.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (530kB) | Preview
[thumbnail of Appendices] Text (Appendices)
Appendices.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)

Abstract

Penelitian ini bertujuan untuk membandingkan efektivitas algoritma Support Vector Machine (SVM) dan Random Forest (RF) dalam identifikasi penyakit diabetes dan jantung. Penyakit diabetes dan jantung merupakan dua penyakit kronis yang prevalensinya semakin meningkat dan memerlukan metode diagnosis yang cepat dan akurat untuk pengelolaan yang lebih baik. Dalam penelitian ini menggunakan dataset yang diperoleh dari Kaggle, yang terdiri dari data pasien dengan atribut-atribut relevan yang digunakan untuk diagnosis penyakit. Algoritma SVM dan RF diterapkan untuk membangun model prediksi, dan kinerja masing-masing model dievaluasi berdasarkan metrik akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa model Stack dan Random Forest (RF) memiliki tingkat keakuratan yang tinggi dan sama, yaitu 89,4% dalam mendeteksi penyakit diabetes. Di sisi lain, model Stack dan Support Vector Machine (SVM) memiliki tingkat keakuratan yang tinggi dan sama, yaitu 81,8% dalam mendeteksi penyakit jantung. Kedua hasil ini menunjukkan bahwa baik model Stack-RF maupun Stack-SVM efektif dalam mendeteksi penyakit diabetes dan jantung, meskipun dengan tingkat akurasi yang berbeda. Penelitian ini memberikan kontribusi dalam bidang data mining dan machine learning untuk aplikasi medis, khususnya dalam pengembangan alat diagnostik berbasis machine learning. Dengan demikian, hasil dari penelitian ini diharapkan dapat membantu dalam pengembangan sistem pendukung keputusan klinis yang lebih akurat dan efisien untuk deteksi dini penyakit diabetes dan jantung. / This study aims to compare the effectiveness of Support Vector Machine (SVM) and Random Forest (RF) algorithms in identifying diabetes and heart diseases. Diabetes and heart diseases are two chronic conditions with increasing prevalence, requiring rapid and accurate diagnostic methods for better management. In this research utilized a dataset obtained from Kaggle, comprising patient data with relevant attributes used for disease diagnosis. SVM and RF algorithms were employed to build predictive models, and the performance of each model was evaluated based on accuracy, precision, recall, and F1-score metrics. The results indicate that both the Stack-RF and RF models exhibit a high level of accuracy, at 89.4%, in detecting diabetes. Conversely, both the Stack- SVM and SVM models demonstrate a similar high accuracy rate of 81.8% in detecting heart disease. These findings suggest that both Stack-RF and Stack-SVM models are effective in detecting diabetes and heart diseases, albeit with differing accuracy levels. This study contributes to the field of data mining and machine learning for medical applications, particularly in the development of machine learning-based diagnostic tools. Thus, the findings of this research are expected to aid in the development of more accurate and efficient clinical decision support systems for early detection of diabetes and heart diseases.
Item Type: Thesis (Bachelor)
Creators:
Creators
NIM
Email
ORCID
Hutama, Elbert
NIM03081200053
elberthutama8@gmail.com
UNSPECIFIED
Contributors:
Contribution
Contributors
NIDN/NIDK
Email
Thesis advisor
Haryani, Calandra
NIDN0307079302
calandra.haryani@uph.edu
Uncontrolled Keywords: support vector machine, random forest, prediksi penyakit, diabetes, penyakit jantung, machine learning, data mining.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: University Subject > Current > Faculty/School - UPH Medan > School of Information Science and Technology > Information Systems
Current > Faculty/School - UPH Medan > School of Information Science and Technology > Information Systems
Depositing User: Elbert Hutama
Date Deposited: 09 Aug 2024 02:37
Last Modified: 09 Aug 2024 02:37
URI: http://repository.uph.edu/id/eprint/64760

Actions (login required)

View Item
View Item