Penerapan Algoritma CNN-LSTM dengan Lagged Features untuk Prediksi Konsentrasi Zat Polutan Udara di Kota Yogyakarta

Salsabila, Afifa (2025) Penerapan Algoritma CNN-LSTM dengan Lagged Features untuk Prediksi Konsentrasi Zat Polutan Udara di Kota Yogyakarta. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 21081010130_cover.pdf Download (1MB)
	Text (Bab 1) 21081010130_bab1.pdf Download (242kB)
	Text (Bab 2) 21081010130_bab2.pdf Restricted to Repository staff only until 19 June 2027. Download (631kB)
	Text (Bab 3) 21081010130_bab3.pdf Restricted to Repository staff only until 19 June 2027. Download (889kB)
	Text (Bab 4) 21081010130_bab4.pdf Restricted to Repository staff only until 19 June 2027. Download (4MB)
	Text (Bab 5) 21081010130_bab5.pdf Download (220kB)
	Text (Daftar Pustaka) 21081010130_daftarpustaka.pdf Download (204kB)

Abstract

This study aims to evaluate the performance of the Convolutional Neural Network (CNN) - Long Short Term Memory (LSTM) algorithm in predicting air pollutant concentration levels. The research process includes data collection and cleaning, data preprocessing, the application of lagged feature techniques, the creation and training of the CNN-LSTM model, as well as model evaluation and testing. The data used consists of carbon monoxide (CO) concentration and daily meteorological data from Yogyakarta City. After processing, the data is used as input for the prediction model. The development of the CNN-LSTM model is tailored to the data conditions through a testing system. The results show that the best CNN-LSTM model was achieved with the following settings: a data split of 70% for training and 30% for testing; 3 CNN layers with 64 neurons per layer; 2 LSTM layers with 32 neurons per layer; an alpha value of 1.0 for Ridge Regression optimization; and a learning rate of 0.0005. With these settings, the evaluation metrics obtained were: MSE of 0.00039, MAE of 0.0152, RMSE of 0.0197, and MAPE of 6.88%.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Sari, Anggraini Puspita	0716088605	anggraini.puspita.if@upnjatim.ac.id
Thesis advisor	Junaidi, Achmad	0710117803	achmadjunaidi.if@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Afifa Salsabila

Date Deposited:

20 Jun 2025 01:25

Last Modified:

20 Jun 2025 01:25

URI:

https://repository.upnjatim.ac.id/id/eprint/38630