Tjoa, Jason (2025) Prediksi kasus mingguan mpox di Republik Demokratik Kongo (RDK) dengan metode decision tree regression (dtr). Bachelor thesis, Universitas Pelita Harapan.
![Title [thumbnail of Title]](http://repository.uph.edu/style/images/fileicons/text.png)
Title.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (203kB)
![Abstract [thumbnail of Abstract]](http://repository.uph.edu/style/images/fileicons/text.png)
Abstract.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (309kB)
![ToC [thumbnail of ToC]](http://repository.uph.edu/style/images/fileicons/text.png)
ToC.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (292kB)
![Chapter1 [thumbnail of Chapter1]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (317kB)
![Chapter2 [thumbnail of Chapter2]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (886kB)
![Chapter3 [thumbnail of Chapter3]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (913kB)
![Chapter4 [thumbnail of Chapter4]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (493kB)
![Chapter5 [thumbnail of Chapter5]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (272kB)
![Bibliography [thumbnail of Bibliography]](http://repository.uph.edu/style/images/fileicons/text.png)
Bibliography.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (280kB)
![Appendices [thumbnail of Appendices]](http://repository.uph.edu/style/images/fileicons/text.png)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (3MB)
Abstract
Saat ini, kasus pasien yang menderita penyakit mpox terus meningkat secara signifikan, dengan tercatatnya mendekati 20.000 kasus dari awal tahun 2024 hingga bulan Agustus, yang menyebabkan 630 orang meninggal dunia di Republik Demokratik Kongo (RDK). Hal ini disebabkan oleh pola kemunculan kasus yang tidak menentu, membuat otoritas kesehatan kesulitan dalam mempersiapkan obat serta infrastruktur kesehatan dengan baik. Ketidakpastian ini juga mengakibatkan distribusi sumber daya yang tidak efisien dan ketimpangan layanan kesehatan antar daerah, sehingga menghambat respons yang cepat dan efektif terhadap lonjakan kasus. Berdasarkan permasalahan tersebut, dikembangkan model machine learning dengan metode Decision Tree Regression (DTR) untuk memprediksi kemunculan kasus mingguan mpox, guna membantu mengurangi lonjakan kasus yang berisiko menyebabkan kematian. Data yang digunakan merupakan data sekunder yang diperoleh dari situs Our World in Data, khususnya data dari tanggal 01 Mei 2022 sampai 10 November 2024. Penelitian ini menggunakan beberapa nilai max depth dan pembagian data training serta data testing untuk mencari kombinasi terbaik. Hasil penelitian menunjukkan bahwa kombinasi nilai max depth = 5 dan pembagian data 80% training serta 20% testing menghasilkan akurasi paling optimal dengan nilai R2 97,496% untuk training dan 97,977% untuk testing, menunjukkan performa model yang stabil dan akurat. / Currently, the number of patients suffering from mpox is increasing significantly, with nearly 20.000 cases recorded from the beginning of 2024 to August, resulting in 630 deaths in the Democratic Republic of the Congo (DRC). This is due to the unpredictable emergence patterns of cases, making it difficult for health authorities to adequately prepare medications and healthcare infrastructure. This uncertainty has also led to inefficient distribution of resources and healthcare disparities between regions, hindering a rapid and effective response to the surge in cases. To address this, a Decision Tree Regression (DTR) machine learning model was developed to predict the weekly emergence of cases, aiming to help reduce surges that risk causing fatalities. The model used secondary data from the Our World in Data website, specifically from May 1, 2022, to November 10, 2024. This study tested various max depth values and data training/testing splits to find the best combination. The combination of a max depth value of 5 and an 80% training, 20% testing data split produced the most optimal accuracy, with an R2 value of 97.496% for training and 97.977% for testing, demonstrating a stable and accurate model performance.
Item Type: | Thesis (Bachelor) |
---|---|
Creators: | Creators NIM Email ORCID Tjoa, Jason NIM03082210003 tjoajason2003@gmail.com UNSPECIFIED |
Contributors: | Contribution Contributors NIDN/NIDK Email Thesis advisor Ferawaty, Ferawaty NIDN0127047701 ferawaty.fik@uph.edu |
Uncontrolled Keywords: | Data Testing; Data Training; Decision Tree Regression; Max Depth; Mpox |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
Divisions: | University Subject > Current > Faculty/School - UPH Medan > School of Information Science and Technology > Informatics Current > Faculty/School - UPH Medan > School of Information Science and Technology > Informatics |
Depositing User: | Jason Tjoa |
Date Deposited: | 21 Jul 2025 07:51 |
Last Modified: | 21 Jul 2025 07:51 |
URI: | http://repository.uph.edu/id/eprint/69840 |