Evaluation of Artificial Neural Network Model for Predicting Nitrogen Oxides (NOₓ) Concentration
Nitrogen Oxides (NOₓ) are air pollutants that require serious attention due to their potential negative impacts on human health, the environment, and the economy. This research is crucial to provide accurate predictive models of NOₓ concentration, which can serve as a foundation for decision-making...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | Indonesian |
| Published: |
Islamic University of Indragiri
2025-05-01
|
| Series: | Sistemasi: Jurnal Sistem Informasi |
| Subjects: | |
| Online Access: | https://sistemasi.ftik.unisi.ac.id/index.php/stmsi/article/view/4371 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Nitrogen Oxides (NOₓ) are air pollutants that require serious attention due to their potential negative impacts on human health, the environment, and the economy. This research is crucial to provide accurate predictive models of NOₓ concentration, which can serve as a foundation for decision-making and effective air pollution mitigation measures. The objective of this study is to evaluate several artificial neural network (ANN) models to determine the most effective model for accurately predicting NOₓ concentrations. One of the methods used for predicting air pollution data, such as NOₓ, is artificial neural networks (ANN). In this study, four ANN models were constructed and evaluated: Feed Forward Neural Network (FNN), Time Lagged Neural Network (TLNN), Seasonal Artificial Neural Network (SANN), and Long Short-Term Memory (LSTM). The models predict NOₓ concentration using data from the air quality dataset provided by the UCI Machine Learning Repository. Testing results indicate that the LSTM model performs best, achieving the lowest error value, characterized by 24 input nodes, three hidden nodes, one output node, and 300 training epochs. The RMSE values for LSTM, FNN, TLNN, and SANN are 57.3, 62.8, 64, and 89, respectively. |
|---|---|
| ISSN: | 2302-8149 2540-9719 |