PERBANDINGAN ALGORITMA SUPPORT VECTOR MACHINE (SVM) DAN RANDOM FOREST CLASSIFIER PADA KLASIFIKASI PENYAKIT INFEKSI SALURAN PERNAPASAN AKUT (ISPA)

Dhea Syahira Julianti, . (2024) PERBANDINGAN ALGORITMA SUPPORT VECTOR MACHINE (SVM) DAN RANDOM FOREST CLASSIFIER PADA KLASIFIKASI PENYAKIT INFEKSI SALURAN PERNAPASAN AKUT (ISPA). Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (2MB)
[img] Text
AWAL.pdf
Download (3MB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only
Download (2MB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (3MB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (3MB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (3MB)
[img] Text
BAB 5.pdf
Download (2MB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (2MB)
[img] Text
Riwayat Hidup.pdf
Restricted to Repository UPNVJ Only
Download (103kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (4MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (18MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (1MB)

Abstract

The Ministry of Health of the Republic of Indonesia has noted an increase in Acute Respiratory Infection (ARI) cases in the Jabodetabek area, averaging 200 thousand cases per month. High air pollution in the Jakarta Capital Region has a significant impact on respiratory health, with ARI being one of the diseases associated with air pollution. This research aims to develop and compare ARI classification models using Support Vector Machine (SVM) and Random Forest Classifier algorithms. The data used was obtained from the Matraman Sub-district Community Health Center during the period 2021-2023, focusing on two types of ARI: nasopharyngitis and pharyngitis. The model was developed using various scenarios, including using default parameters (without hyperparameter tuning) and with hyperparameter tuning, employing resampling techniques such as undersampling and oversampling, reducing the size of the data sample, and utilizing both training and testing data splits. The research results indicate that both SVM and Random Forest models achieve high accuracy across various experimental scenarios. In the data split of 90% for training and 10% for testing, the SVM algorithm achieved the highest accuracy of 98% in experiment with a sample size of 500 data, and the Random Forest algorithm achieved 96.4% in experiments with 2500 data, even though the accuracy was the same as SVM. However, despite parameter tuning, there was no significant increase in accuracy compared to using default parameters or without hyperparameter tuning. Resampling techniques helped balance the classes, but precision for the pharyngitis class remained low, indicating the need for further adjustments to improve classification performance on minority classes. This study provides insights into the performance of SVM and Random Forest in ARI classification and serves as a reference for further research on the same topic.

Item Type: Thesis (Skripsi)
Additional Information: [No. Panggil: 2010511075] [Pembimbing 1: Bayu Hananto] [Pembimbing 2: Ika Nurlaili Isnainiyah] [Penguji 1: Ridwan Raafi'udin] [Penguji 2: Neny Rosmawarni]
Uncontrolled Keywords: ISPA, Support Vector Machine, Random Forest Classifier, Hyperparameter tuning
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: DHEA SYAHIRA JULIANTI
Date Deposited: 30 Jul 2024 09:13
Last Modified: 05 Sep 2024 04:20
URI: http://repository.upnvj.ac.id/id/eprint/31723

Actions (login required)

View Item View Item