Application of Informer for time-series NO2 prediction
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this paper, we evaluate deep learning time series forecasting models. Recent studies show that those models perform better than the traditional prediction model such as ARIMA. Among them, recurrent neural networks to store previous information in the hidden layer are one of the prediction models. In order to solve the gradient vanishing problem in the network, LSTM is used with small memory inside the recurrent neural network along with BI-LSTM in which the hidden layer is added in the reverse direction of the data flow. In this paper, we compared the performance of Informer by comparing with other models (LSTM, BI-LSTM, and Transformer) for real Nitrogen dioxide (NO2) data. In order to evaluate the accuracy of each method, mean square root error and mean absolute error between the real value and the predicted value were obtained . Consequently, Informer has improved prediction accuracy compared with other methods.
Abstract
In this paper, we evaluate deep learning time series forecasting models. Recent studies show that those models perform better than the traditional prediction model such as ARIMA. Among them, recurrent neural networks to store previous information in the hidden layer are one of the prediction models. In order to solve the gradient vanishing problem in the network, LSTM is used with small memory inside the recurrent neural network along with BI-LSTM in which the hidden layer is added in the reverse direction of the data flow. In this paper, we compared the performance of Informer by comparing with other models (LSTM, BI-LSTM, and Transformer) for real Nitrogen dioxide (NO2) data. In order to evaluate the accuracy of each method, mean square root error and mean absolute error between the real value and the predicted value were obtained . Consequently, Informer has improved prediction accuracy compared with other methods.
참고문헌 (26)
- G. E. P. Box, "Time Series Analysis" (2008), Wiley Series in Probability and Statistics
- 이창용, "ARIMA 모형을 사용한 전력 소모량의 단기 예측에 관한 연구", Journal of The Korean Data Analysis Society, 19(3), pp.1349~1362 (2017), 한국자료분석학회[DOI]
- 한대철, "SARIMA 알고리즘을 이용한 교통량 보정 및 예측", 한국ITS학회 논문지, 20(6), pp.1~13 (2021), 한국ITS학회[DOI]
- J. Korstanje, "Advanced Forecasting with Python", pp.125~131 (2021), Springer
- S. S. -Namini, "A Comparison of ARIMA and LSTM in Forecasting Time Series", 2018 17th IEEE International Conference on Machine Learning and Applications, pp.1~8 (2018)
- P. T. Yamak, "A Comparison between ARIMA, LSTM, and GRU for Time Series Forecasting", ACAI 2019 : Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence, pp.49~55 (2019)
- A. A. Yammahi, "Forecasting the concentration of NO2 using statistical and machine learning methods: A case study in the UAE", Heliyon, 9(2), pp.12584~ (2023)
- A. Heydari, "Air pollution forecasting application based on deep learning model and optimization algorithm", Clean Technologies and Environmental Policy (2021)
- Jarmo Ilonen, "Differential evolution training algorithm for feed-forward neural networks", Neural Processing Letters, 17(1), pp.93~105 (2003), Springer Science and Business Media LLC[DOI]
- 김재호, "코로나 확진자 수 예측을 위한 BI-LSTM과 GRU 알고리즘의 성능 비교 분석", 한국정보통신학회논문지, 26(2), pp.187~192 (2022), 한국정보통신학회[DOI]
- Sepp Hochreiter, "Long Short-Term Memory", Neural Computation, 9(8), pp.1735~1780 (1997), MIT Press - Journals[DOI]
- 정종진, "LSTM을 이용한 주가예측 모델의 학습방법에 따른 성능분석", 디지털융복합연구, 18(11), pp.259~266 (2020), 한국디지털정책학회[DOI]
- B. Liu, "A Long Short-Term Memory Neural Network for Daily NO2 Concentration Forecasting", International Journal of Information Technology and Web Engineering (IJITWE), 16(4) (2021)
- C-L. Wu, "A hybrid deep learning model for regional O3and NO2 concentrations prediction based on spatiotemporal dependencies in air quality monitoring network", Environmental Pollution, 320, pp.1~ (2023)
- Suhartono, "A Hybrid TSR and LSTM for Forecasting NO2 and SO2 in Surabaya", Home Soft Computing in Data Science Conference paper (2019)
- G. I. Drewil, "Air pollution prediction using LSTM deep learning and metaheuristics algorithms", Measurement : Sensors, 24, pp.100546~ (2022)
- Preeti, "Financial and Non-Stationary Time Series Forecasting using LSTM Recurrent Neural Network for Short and Long Horizon", International Conference on Computing and Networking Technology (ICCNT), pp.1~7 (2019)
- I. Verma, "Air Pollutant Severity Prediction Using Bi-Directional LSTM Network", 2018IEEE, ACM International Conference on Web Intelligence (WI), pp.2018[DOI]
- 고상준, "양방향 LSTM을 활용한 전력수요 데이터 예측 기법 연구", 한국소프트웨어감정평가학회 논문지, 14(1), pp.33~40 (2018), 한국소프트웨어감정평가학회
- S. H. M. Hickman, "Forecasting European Ozone Air Pollution With Transformers", Tackling Climate Change with Machine Learning:workshop at NeurIPS (2022)
- H. Wei, "A novel approach to ultra-short-term wind power prediction based on feature engineering and Informer", Energy Reports, 9, pp.1236~1250 (2023)
- M. Kang, "The prediction model of Ultraviolet-B using Deep learning model (Bidirectional LSTM) in comparison with LSTM and SARIMA", Journal of The Korea Society of Computer and Information (JKSCI) (2023)
- T. Falatouri, "Predictive Analytics for Demand Forecasting – A Comparison of SARIMA and LSTM in Retail SCM", Procedia Computer Science, 200, pp.993~1003 (2022)