IMPLEMENTASI ALGORITMA LONG SHORT-TERM MEMORY UNTUK MEMPREDIKSI KUALITAS UDARA DI DKI JAKARTA

PUTRA, AGUNG NURPRASETYA (2024) IMPLEMENTASI ALGORITMA LONG SHORT-TERM MEMORY UNTUK MEMPREDIKSI KUALITAS UDARA DI DKI JAKARTA. S1 thesis, Universitas Mercu Buana Jakarta.

Preview	Text (HAL COVER) 01 COVER.pdf Download (395kB) | Preview
Preview	Text (ABSTRAK) 02 ABSTRAK.pdf Download (27kB) | Preview
	Text (BAB I) 03 BAB 1.pdf Restricted to Registered users only Download (110kB)
	Text (BAB II) 04 BAB 2.pdf Restricted to Registered users only Download (209kB)
	Text (BAB III) 05 BAB 3.pdf Restricted to Registered users only Download (32kB)
	Text (BAB IV) 06 BAB 4.pdf Restricted to Registered users only Download (526kB)
	Text (BAB V) 07 BAB 5.pdf Restricted to Registered users only Download (31kB)
	Text (DAFTAR PUSTAKA) 08 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (132kB)
	Text (LAMPIRAN) 09 LAMPIRAN.pdf Restricted to Registered users only Download (266kB)

Abstract

Air quality is a major problem in big cities like DKI Jakarta. This research applies the Long Short-Term Memory (LSTM) algorithm to predict air quality by considering parameters such as date, station, PM10, PM2.5, SO2, CO, O3, NO2, max, critical, and category. The dataset consists of 2504 data from January 2017 to November 2023. The LSTM model performance evaluation uses Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Squared Error (RMSE) metrics. The results showed that the LSTM model has good prediction accuracy. MAE for PM10 was 6.98, PM2.5 was 10.29, SO2 was 3.18, CO was 1.99, O3 was 5.56, and NO2 was 4.79. MAPE for PM10 was 18.11%, PM2.5 was 17.33%, SO2 was 8.99%, CO was 19.81%, O3 was 21.02%, and NO2 was 16.12%. The RMSE for PM10 was 9.58, PM2.5 was 12.88, SO2 was 5.17, CO was 2.92, O3 was 7.46, and NO2 was 6.30. This research proves that the LSTM algorithm is effective for monitoring and predicting air quality, although some pollutants require improved prediction accuracy. Keywords: Air Quality, Long Short-Term Memory (LSTM), Prediction, DKI Jakarta, Deep Learning Kualitas udara merupakan masalah utama di kota besar seperti DKI Jakarta. Penelitian ini menerapkan algoritma Long Short-Term Memory (LSTM) untuk memprediksi kualitas udara dengan mempertimbangkan parameter seperti tanggal, stasiun, PM10, PM2.5, SO2, CO, O3, NO2, max, critical, dan kategori. Dataset terdiri dari 2504 data dari Januari 2017 hingga November 2023. Evaluasi kinerja model LSTM menggunakan metrik Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), dan Root Mean Squared Error (RMSE). Hasil penelitian menunjukkan bahwa model LSTM memiliki akurasi prediksi yang baik. MAE untuk PM10 sebesar 6.98, PM2.5 sebesar 10.29, SO2 sebesar 3.18, CO sebesar 1.99, O3 sebesar 5.56, dan NO2 sebesar 4.79. MAPE untuk PM10 sebesar 18.11%, PM2.5 sebesar 17.33%, SO2 sebesar 8.99%, CO sebesar 19.81%, O3 sebesar 21.02%, dan NO2 sebesar 16.12%. RMSE untuk PM10 sebesar 9.58, PM2.5 sebesar 12.88, SO2 sebesar 5.17, CO sebesar 2.92, O3 sebesar 7.46, dan NO2 sebesar 6.30. Penelitian ini membuktikan bahwa algoritma LSTM efektif untuk memantau dan memprediksi kualitas udara, meskipun beberapa polutan memerlukan peningkatan akurasi prediksi. Kata Kunci: Kualitas Udara, Long Short-Term Memory (LSTM), Prediksi, DKI Jakarta, Deep Learning

Item Type:	Thesis (S1)
Call Number CD:	FIK/INFO. 24 151
Call Number:	SIK/15/24/110
NIM/NIDN Creators:	41520010088
Uncontrolled Keywords:	Kualitas Udara, Long Short-Term Memory (LSTM), Prediksi, DKI Jakarta, Deep Learning
Subjects:	000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 005 Computer Programmming, Programs, Data/Pemprograman Komputer, Program, Data > 005.4 System Programming and Programs/Sistem Pemrograman dan Program > 005.43 Operating System/Sistem Operasi > 005.435 Memory Management Programs/Program Manajemen Memori 500 Natural Science and Mathematics/Ilmu-ilmu Alam dan Matematika > 510 Mathematics/Matematika > 518 Numerical Analysis/Analisis Numerik, Analisa Numerik > 518.1 Algorithms/Algoritma
Divisions:	Fakultas Ilmu Komputer > Informatika
Depositing User:	khalimah
Date Deposited:	14 Aug 2024 02:50
Last Modified:	14 Aug 2024 02:50
URI:	http://repository.mercubuana.ac.id/id/eprint/90217

Actions (login required)

View Item