AN EVALUATION OF HEART DISEASE PREDICTION USING AN EXTREME GRADIENT BOOSTING ALGORITHM

CHANG, DAVIN (2023) AN EVALUATION OF HEART DISEASE PREDICTION USING AN EXTREME GRADIENT BOOSTING ALGORITHM. Other thesis, Universitas Katholik Soegijapranata Semarang.

[img] Text
19.K1.0005-DAVIN CHANG-COVER_a.pdf
Download (1MB)
[img] Text
19.K1.0005-DAVIN CHANG-BAB I_a.pdf
Download (230kB)
[img] Text
19.K1.0005-DAVIN CHANG-BAB II_a.pdf
Restricted to Registered users only
Download (241kB)
[img] Text
19.K1.0005-DAVIN CHANG-BAB III_a.pdf
Download (262kB)
[img] Text
19.K1.0005-DAVIN CHANG-BAB IV_a.pdf
Download (249kB)
[img] Text
19.K1.0005-DAVIN CHANG-BAB V_a.pdf
Download (571kB)
[img] Text
19.K1.0005-DAVIN CHANG-BAB VI_a.pdf
Download (226kB)
[img] Text
19.K1.0005-DAVIN CHANG-DAPUS_a.pdf
Download (325kB)
[img] Text
19.K1.0005-DAVIN CHANG-LAMP_a.pdf
Download (240kB)

Abstract

Heart disease has recorded the most death cause in the world. A lot of researchers are trying to find better and more reliable machine learning to diagnose heart disease. Accuracy and the speed of computation become the main concern when classifying heart disease at its early stages related to human life. This paper researched about Extreme Gradient Boosting (XGBoost) as an ensemble learning with boosting method to predict heart disease. The data will be preprocessed using handling missing value and removing outliers. The algorithm will be compared with 2 different datasets (with feature selection and without feature selection). The outcome of this research hopefully can present the performance result of the Extreme Gradient Boosting algorithm using tenfold cross-validation and performance measures (Precision, Recall, F1-score, ROC Area, and Accuracy) when using feature selection and without using feature selection.

Item Type: Thesis (Other)
Subjects: 000 Computer Science, Information and General Works > 004 Data processing & computer science
Divisions: Faculty of Computer Science > Department of Informatics Engineering
Depositing User: mr AM. Pudja Adjie Sudoso
Date Deposited: 05 Apr 2023 01:25
Last Modified: 05 Apr 2023 01:25
URI: http://repository.unika.ac.id/id/eprint/31406

Actions (login required)

View Item View Item
Unika Repository is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.