Acknowledgement
이 논문은 2021년도 정부(교육부)의 재원으로 한국연구재단의 지원을 받아 수행된 기초연구사업임(No. NRF-2019R1I1A3A01059038)
Proceedings of the Korean Institute of Information and Commucation Sciences Conference (한국정보통신학회:학술대회논문집)
- 2021.05a
- /
- Pages.280-282
- /
- 2021
Performance Comparison of PM10 Prediction Models Based on RNN and LSTM
RNN과 LSTM 기반의 PM10 예측 모델 성능 비교
- Jung, Yong-jin (Korea University of Technology and Education) ;
- Lee, Jong-sung (Korea University of Technology and Education) ;
- Oh, Chang-heon (Korea University of Technology and Education)
- Published : 2021.05.03
Abstract
A particular matter prediction model was designed using a deep learning algorithm to solve the problem of particular matter forecast with subjective judgment applied. RNN and LSTM were used among deep learning algorithms, and it was designed by applying optimal parameters by proceeding with hyperparametric navigation. The predicted performance of the two models was evaluated through RMSE and predicted accuracy. The performance assessment confirmed that there was no significant difference between the RMSE and accuracy, but there was a difference in the detailed forecast accuracy.
주관적 판단을 적용하여 예보되는 미세먼지 예보의 문제를 해결하기 위해 딥러닝 알고리즘을 이용하여 미세먼지 예측 모델을 설계하였다. 딥러닝 알고리즘 중 RNN과 LSTM을 이용하였으며, 하이퍼 파라미터 탐색을 통해 최적의 파라미터를 적용하여 설계하였다. RMSE와 예측 정확도를 통해 두 모델의 예측 성능을 평가하였다. 성능 평가 결과, RMSE와 전체 정확도에서 큰 차이는 없었으나 세부 예측 정확도의 차이가 있음을 확인하였다.