Comparative Analysis of PM10 Prediction Performance between Neural Network Models

• Published in: Journal of Information and Communication Convergence Engineering, 19(4) Vol. 19; no. 4; pp. 241 - 247
• Main Authors: Yong-Jin Jung, Chang-Heon Oh
• Format: Journal Article
• Language: English
• Published: 한국정보통신학회JICCE 2021; 한국정보통신학회
• Subjects: 전자/정보통신공학; Long short-term memory; Deep neural network; Neural network; Recurrent neural network; Particulate matter
• ISSN: 2234-8255; 2234-8883
• DOI: 10.6109/jicce.2021.19.4.241

Particulate matter has emerged as a serious global problem, necessitating highly reliable information on the matter. Therefore,various algorithms have been used in studies to predict particulate matter. In this study, we compared the prediction performanceof neural network models that have been actively studied for particulate matter prediction. Among the neural networkalgorithms, a deep neural network (DNN), a recurrent neural network, and long short-term memory were used to design theoptimal prediction model using a hyper-parameter search. In the comparative analysis of the prediction performance of eachmodel, the DNN model showed a lower root mean square error (RMSE) than the other algorithms in the performance comparisonusing the RMSE and the level of accuracy as metrics for evaluation. The stability of the recurrent neural network was slightlylower than that of the other algorithms, although the accuracy was higher. KCI Citation Count: 0