Klasifikasi Penyakit Infeksi Saluran Pernapasan Akut Menggunakan Xgboost dan Grey Wolf Optimizer

Agnesya, Putri Dwi (2025) Klasifikasi Penyakit Infeksi Saluran Pernapasan Akut Menggunakan Xgboost dan Grey Wolf Optimizer. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 21081010142-cover.pdf Download (2MB)
	Text (Bab 1) 21081010142-bab1.pdf Download (340kB)
	Text (Bab 2) 21081010142-bab2.pdf Restricted to Repository staff only until 5 December 2028. Download (765kB)
	Text (Bab 3) 21081010142-bab3.pdf Restricted to Repository staff only until 5 December 2028. Download (1MB)
	Text (Bab 4) 21081010142-bab4.pdf Restricted to Repository staff only until 5 December 2028. Download (6MB)
	Text (Bab 5) 21081010142-bab5.pdf Download (214kB)
	Text (Daftar pustaka) 21081010142-daftarpustaka.pdf Download (257kB)
	Text (Lampiran) 21081010142-lampiran.pdf Restricted to Repository staff only until 2028. Download (2MB)

Abstract

Acute Respiratory Infection (ARI) is one of the diseases with a high morbidity rate in Indonesia, therefore an accurate classification model is needed to support early detection and medical decision-making. This study integrates the Extreme Gradient Boosting (XGBoost) algorithm with the Grey Wolf Optimizer (GWO) as a hyperparameter optimization method for XGBoost. GWO is applied to optimize important parameters such as n_estimators, learning_rate, max_depth, subsample, colsample_bytree, and min_child_weight through exploration and exploitation mechanisms that mimic the hunting behavior of grey wolves. The experimental results show that the XGBoost model optimized using GWO is able to provide a significant performance improvement compared to the baseline model. The optimized model achieves an accuracy of 0.92, higher than the model with default parameters which only achieves an accuracy of 0.88, and also shows improvements in precision, recall, and F1-score metrics. The optimization process produces the best parameter configuration in the form of n_estimators = 183, learning_rate = 0.036471, max_depth = 4, subsample = 1, colsample_bytree = 0.661291, and min_child_weight = 1.124875. Overall, this study proves that the combination of XGBoost and GWO is an effective and potential approach to improving the quality of ARI classification systems.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Rahajoe, Rr. Ani Dijah	NIDN0012057301	anidijah.if@upnjatim.ac.id
Thesis advisor	Nurlaili, Afina Lina	NIDN0013129303	afina.lina.if@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Putri Dwi Agnesya

Date Deposited:

05 Dec 2025 08:33

Last Modified:

05 Dec 2025 08:57

URI:

https://repository.upnjatim.ac.id/id/eprint/48076