Hermawan, Aditya (2019) SPKU: SISTEM PREDIKSI KUALITAS UDARA (STUDI KASUS: DKI JAKARTA). Tugas Akhir thesis, University of Technology Yogyakarta.
|
Text
Naskah Publikasi 5150411392 Aditya Hermawan.pdf Download (749kB) | Preview |
Abstract
The Special Capital Region of Jakarta is the Capital City of the Republic of Indonesia, which has a growing population which is not balanced with the area. The level of motor vehicle density and the level of infrastructure development are also increasing with the presence of various vehicles and infrastructure development. This will result in higher levels of air pollution. Therefore, it needs the implementation of the support vector machine (SVM) method with a kernel radial basis function (RBF) to predict air quality in DKI Jakarta Province so that it can provide early warning to the government and the public regarding air quality. By using the RBF kernel SVM method, the prediction of air quality in DKI Jakarta was successfully carried out with a prediction accuracy rate on all DKI Jakarta data of 96.03%, prediction accuracy in Central Jakarta (DKI1) data of 93.97%, prediction accuracy in North Jakarta data (DKI2) amounted to 91.35%, prediction accuracy in South Jakarta data (DKI3) was 89.47%, prediction accuracy in East Jakarta data (DKI4) was 89.27%, and prediction accuracy in West Jakarta data was 87.29% (DKI5). This is influenced by the optimal parameter value settings that are cost value = 3, epsilon value = 0.001, sigma value = 0.03, maximum iteration value = 10, tolerance value = 0.0001 and many equal values = 10. Keywords: Prediction, Air Quality, DKI Jakarta, Support Vector Machine
| Item Type: | Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir) |
|---|---|
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Sains Dan Teknologi > S1 Informatika |
| Depositing User: | Kaprodi S1 Informatika UTY |
| Date Deposited: | 27 Oct 2019 15:02 |
| Last Modified: | 27 Oct 2019 15:02 |
| URI: | http://eprints.uty.ac.id/id/eprint/3552 |
Actions (login required)
 |
View Item |
