Riyadi, Karisma (2025) Penerapan model support vector regression dan random forest dalam memprediksi indeks kualitas udara (aqi) di Jakarta = Application of support vector regression and random forest methods in predicting pm2.5 concentration in Jakarta. Bachelor thesis, Universitas Pelita Harapan.
![Title [thumbnail of Title]](http://repository.uph.edu/style/images/fileicons/text.png)
Title.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (202kB)
![Abstract [thumbnail of Abstract]](http://repository.uph.edu/style/images/fileicons/text.png)
Abstract.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (602kB)
![TOC [thumbnail of TOC]](http://repository.uph.edu/style/images/fileicons/text.png)
TOC.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (2MB)
![Chapter 1 [thumbnail of Chapter 1]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter 1.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (662kB)
![Chapter 2 [thumbnail of Chapter 2]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter 2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (773kB)
![Chapter 3 [thumbnail of Chapter 3]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter 3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (810kB)
![Chapter 4 [thumbnail of Chapter 4]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter 4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (3MB)
![Chapter 5 [thumbnail of Chapter 5]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter 5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (653kB)
![Bibliography [thumbnail of Bibliography]](http://repository.uph.edu/style/images/fileicons/text.png)
Bibliography.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (648kB)
![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 (2MB)
Abstract
Polusi udara telah dianggap sebagai permasalahan lingkungan yang sangat
mengkhawatirkan di seluruh dunia. Prediksi mengenai indeks kualitas udara
memiliki peranan penting dalam memperingatkan manusia agar dapat
meningkatkan kesadaran dan mengendalikan tingkat polusi udara. Penelitian ini
bertujuan untuk melihat perbandingan kinerja model Support Vector Regression
dan Random Forest dalam memprediksi indeks kualitas udara. Data yang
digunakan merupakan data harian dengan rentang waktu yaitu 1 Januari 2018
hingga 31 Desember 2023. Data dibagi menjadi tiga periode yaitu periode 1
merupakan periode sebelum Pandemi COVID-19 (1 Januari 2018 - 31 Desember
2019), periode 2 merupakan periode sebelum Pandemi COVID-19 (1 Januari 2018 - 31 Desember 2019), dan periode 3 merupakan periode setelah Pandemi
COVID-19 (1 Januari 2023 - 31 Desember 2023). Model SVR dan RF digunakan
untuk memprediksi indeks kualitas udara di Jakarta. Kinerja model diukur
menggunakan evaluasi metrik Adjusted R Squared, MAE, dan MAPE. Hasil dari
pembentukkan model SVR dan RF menunjukkan bahwa kinerja dari kedua model
paling baik ketika diterapkan pada dataset periode 1. Model SVR memperoleh
nilai Adjusted R
—
—
—
Squared sebesar 96.638%, nilai MAE dan MAPE
masing-masing sebesar 4.09109 atau sama dengan sebesar 5.62806% dengan
menggunakan dua kombinasi variabel independen. Sedangkan, model RF
memperoleh nilai R Squared sebesar 95.486%, nilai MAE dan MAPE
masing-masing sebesar 4.47743 atau sama dengan 6.15757% dengan
menggunakan tujuh kombinasi variabel independen dalam memprediksi indeks
kualitas udara. Model Support Vector Regression memiliki kemampuan prediksi
yang lebih baik dibandingkan model Random Forest. / Air pollution has been recognized as a critical environmental issue worldwide.
Predicting the air quality index (AQI) plays a significant role in raising awareness
and controlling the levels of air pollution. This study aims to compare the
performance of the Support Vector Regression (SVR) and Random Forest (RF)
models in predicting the AQI. The data used consists of daily records from January
1, 2018, to December 31, 2023. The data is divided into three periods: Period 1
represents the period before the COVID-19 pandemic (January 1, 2018 -
December 31, 2019), Period 2 also represents the period before the COVID-19
pandemic (January 1, 2018 - December 31, 2019), and Period 3 represents the
period after the COVID-19 pandemic (January 1, 2023 - December 31, 2023). The
SVR and RF models were applied to predict the AQI in Jakarta. The model
performance was assessed using evaluation metrics such as Adjusted R-Squared,
MAE, and MAPE. The results of developing the SVR and RF models indicate that
the performance of both models was optimal when applied to dataset period 1. The
SVR model achieved an Adjusted R-Squared value of 96.368%, with MAE and
MAPE values of 4.09109 and 5.62806%, respectively, using two independent
variable combinations. In contrast, the RF model reached an R-Squared value of
95.486%, with MAE and MAPE values of 4.47743 and 6.15757%, respectively,
using seven independent variable combinations to predict the AQI. Support Vector
Regression (SVR) model demonstrates better predictive performance compared to
the Random Forest (RF) model.
Item Type: | Thesis (Bachelor) |
---|---|
Creators: | Creators NIM Email ORCID Riyadi, Karisma NIM01112200017 karisma9b2016@gmail.com UNSPECIFIED |
Contributors: | Contribution Contributors NIDN/NIDK Email Thesis advisor Ferdinand, Ferry Vincenttius NIDN0323059001 ferry.vincenttius@uph.edu Thesis advisor Laurence, Laurence NIDN0328077602 laurence.fti@uph.edu |
Uncontrolled Keywords: | polusi udara; support vector regression; random forest; indeks kualitas udara; kinerja model; air pollution; support vector regression; random forest; aqi; perfomance evaluation. |
Subjects: | Q Science > QA Mathematics |
Divisions: | University Subject > Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Mathematics Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Mathematics |
Depositing User: | Stefanus Tanjung |
Date Deposited: | 09 Aug 2025 06:18 |
Last Modified: | 09 Aug 2025 06:18 |
URI: | http://repository.uph.edu/id/eprint/70423 |