DOI QR코드

DOI QR Code

미세먼지 위험 단계 예측을 위한 1-D CRNN 모델 설계

Design of a 1-D CRNN Model for Prediction of Fine Dust Risk Level

  • 이기혁 (한양대학교 전자공학과) ;
  • 황우성 (한양대학교 전기전자제어계측공학과) ;
  • 최명렬 (한양대학교 전자공학부)
  • Lee, Ki-Hyeok (Department of Electrical and Electronic Engineering, Hanyang University) ;
  • Hwang, Woo-Sung (Department of Electronic, Electrical, Control & Instrumentation Engineering, Hanyang University) ;
  • Choi, Myung-Ryul (Division of Electronics Engineering, Hanyang University)
  • 투고 : 2020.11.15
  • 심사 : 2021.02.20
  • 발행 : 2021.02.28

초록

최근 국내 미세먼지 발생의 증가에 따라 발생하는 인체에 유해한 영향을 줄이기 위하여, 미세먼지 수치를 예측하고 사전 조치를 취할 수 있도록 돕는 기술이 필요해지고 있다. 본 논문에서는 국내 미세먼지 위험 수준을 예측하기 위한 1D Convolutional to Recurrent Neural Network (1-D CRNN) 모델을 제안한다. 제안 된 모델은 딥러닝 신경망의 CNN과 RNN을 결합한 구조이며, 다른 종류의 데이터로 구성된 시계열 데이터 세트에서 데이터 예측을 수행 할 수 있다. 데이터 예측을 위해 국내·외 미세먼지, 풍향, 풍속 데이터를 사용한다. 제안된 모델은 약 76%(부분 최대 84%)의 정확도를 달성했으며, 일반 RNN 모델(53%)보다 정확한 예측 결과를 얻었을 수 있었다. 제안된 모델은 향후 여러 개의 시계열 데이터 세트를 고려해야 하는 데이터 예측 모델 학습 및 실험을 목표로 한다.

In order to reduce the harmful effects on the human body caused by the recent increase in the generation of fine dust in Korea, there is a need for technology to help predict the level of fine dust and take precautions. In this paper, we propose a 1D Convolutional-Recurrent Neural Network (1-D CRNN) model to predict the level of fine dust in Korea. The proposed model is a structure that combines the CNN and the RNN, and uses domestic and foreign fine dust, wind direction, and wind speed data for data prediction. The proposed model achieved an accuracy of about 76%(Partial up to 84%). The proposed model aims to data prediction model for time series data sets that need to consider various data in the future.

키워드

참고문헌

  1. H. S. Kim, Kim, D. S., Kim, H., & Yi, S. M. (2012). Relationship between mortality and fine particles during Asian dust, smog-Asian dust, and smog days in Korea. International journal of environmental health research, 22(6). 518-530. https://doi.org/10.1080/09603123.2012.667796
  2. Y. P. Kim. (2006). (Invited paper)Air Pollution in Seoul Caused by Aerosols KOSAE, 22(5), 535-553.
  3. Jeon, S., & Son, Y. S. (2018). Prediction of fine dust PM 10 using a deep neural network model. The Korean Journal of Applied Statistics, 31(2), 265-28 https://doi.org/10.5351/KJAS.2018.31.2.265
  4. Kim, H. S., Kim, D. S., Kim, H., & Yi, S. M. (2012). Relationship between mortality and fine particles during Asian dust, smog-Asian dust, and smog days in Korea. International journal of environmental health research, 22(6). 518-530. https://doi.org/10.1080/09603123.2012.667796
  5. Graves, A., & Schmidhuber, J. (2009). Offline handwriting recognition with multidimensional recurrent neural networks. In Advances in neural information processing systems, 545-552.
  6. LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324. https://doi.org/10.1109/5.726791
  7. Hinton, G. E., Osindero, S., & Teh, Y. W. (2006). A fast learning algorithm for deep belief nets. Neural computation, 18(7), 1527-1554. https://doi.org/10.1162/neco.2006.18.7.1527
  8. Montgomery, D. C., Peck, E. A., & Vining, G. G. (2012). Introduction to linear regression analysis (Vol. 821). Hoboken : John Wiley & Sons.
  9. T. Y. Kim. (2019). Python Deep Learning Keras with Blocks. Seoul : Digital books.
  10. Greff, K., Srivastava, R. K., Koutnik, J., Steunebrink, B. R., & Schmidhuber, J. (2016). LSTM: A search space odyssey. IEEE transactions on neural networks and learning systems, 28(10), 2222-2232. https://doi.org/10.1109/TNNLS.2016.2582924
  11. Christoffersen, P., & Jacobs, K. (2004). The importance of the loss function in option valuation. Journal of Financial Economics, 72(2), 291-318. https://doi.org/10.1016/j.jfineco.2003.02.001
  12. Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization.ar Xiv preprint arXiv, 1412.6980.
  13. S. A. Park, & H. J. Shin. (2017). Analysis of the Factors Influencing PM2.5 in Korea : Focusing on Seasonal Factors. Journal of Environmental Policy and Administration, 25(1), 227-248. https://doi.org/10.15301/jepa.2017.25.1.227
  14. Korea Meteological Office. (2019). Yellow dust observation. Korea Meteorological Agency, Weather Data Opening Portal. https://data.kma.go.kr/data/climate/selectDustRltmList.do?pgmNo=68
  15. young-0. Beijing Air Quality: pm2.5. monthly comparison. http://www.young-0.com/airquality/
  16. D. Y. Wi. (2017.11.2.) Fine dust prediction accuracy, actually only 50%. Electimes, No. 3345, p. 12.