Application of Informer for time-series NO2 prediction

Sin Hye Yeon (신혜연); Minchul Kang (강민철); Joonsung Kang (강준성)

doi:10.9708/jksci.2023.28.07.011

Application of Informer for time-series NO2 prediction

Journal of The Korea Society of Computer and Information
Abbr : JKSCI
2023, 28(7), pp.11-18
DOI : 10.9708/jksci.2023.28.07.011
Publisher : The Korean Society Of Computer And Information
Research Area : Engineering > Computer Science
Received : June 8, 2023
Accepted : July 20, 2023
Published : July 31, 2023

Sin Hye Yeon ¹, Minchul Kang ², Joonsung Kang ³

¹덕성여자대학교
²차의과학대학교
³강릉원주대학교

Accredited

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.

KEYWORDS

Deep learning, Prediction, LSTM, BI-LSTM, Transformer, Informer

Citation status

* References for papers published after 2023 are currently being built.

[book] G. E. P. Box / 2008 / Time Series Analysis / Wiley Series in Probability and Statistics

[journal] 이창용 / 2017 / A Study on the Short-term Prediction of Power Consumption by using the ARIMA Model / Journal of The Korean Data Analysis Society / 한국자료분석학회 19(3) : 1349~1362

[journal] 한대철 / 2021 / A Study on the Traffic Volume Correction and Prediction Using SARIMA Algorithm / 한국ITS학회 논문지 / 한국ITS학회 20(6) : 1~13

[book] J. Korstanje / 2021 / Advanced Forecasting with Python / Springer : 125~131

[confproc] S. S. -Namini / 2018 / A Comparison of ARIMA and LSTM in Forecasting Time Series / 2018 17th IEEE International Conference on Machine Learning and Applications : 1~8

[confproc] P. T. Yamak / 2019 / 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 : 49~55

[journal] A. A. Yammahi / 2023 / Forecasting the concentration of NO2 using statistical and machine learning methods: A case study in the UAE / Heliyon 9(2) : 12584~

[journal] A. Heydari / 2021 / Air pollution forecasting application based on deep learning model and optimization algorithm / Clean Technologies and Environmental Policy

[journal] Jarmo Ilonen / 2003 / Differential evolution training algorithm for feed-forward neural networks / Neural Processing Letters / Springer Science and Business Media LLC 17(1) : 93~105

[journal] 김재호 / 2022 / Comparative analysis of performance of BI-LSTM and GRU algorithm for predicting the number of Covid-19 confirmed cases / 한국정보통신학회논문지 / 한국정보통신학회 26(2) : 187~192

[journal] Sepp Hochreiter / 1997 / Long Short-Term Memory / Neural Computation / MIT Press - Journals 9(8) : 1735~1780

[journal] 정종진 / 2020 / A Performance Analysis by Adjusting Learning Methods in Stock Price Prediction Model Using LSTM / 디지털융복합연구 / 한국디지털정책학회 18(11) : 259~266

[journal] B. Liu / 2021 / A Long Short-Term Memory Neural Network for Daily NO2 Concentration Forecasting / International Journal of Information Technology and Web Engineering (IJITWE) 16(4)

[journal] C-L. Wu / 2023 / A hybrid deep learning model for regional O3and NO2 concentrations prediction based on spatiotemporal dependencies in air quality monitoring network / Environmental Pollution 320 : 1~

[confproc] Suhartono / 2019 / A Hybrid TSR and LSTM for Forecasting NO2 and SO2 in Surabaya / Home Soft Computing in Data Science Conference paper

[journal] G. I. Drewil / 2022 / Air pollution prediction using LSTM deep learning and metaheuristics algorithms / Measurement : Sensors 24 : 100546~

[web] L. Nashold / 2020 / Using LSTM and SARIMA Models to Forecast Cluster CPU Usage / arXiv:2007.08092 / arXiv:2007.08092

[confproc] Preeti / 2019 / 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) : 1~7

[confproc] I. Verma / 2018 / Air Pollutant Severity Prediction Using Bi-Directional LSTM Network / 2018IEEE/WIC/ACM International Conference on Web Intelligence (WI)

[journal] 고상준 / 2018 / Electronic Demand Data Prediction using Bidirectional Long Short Term Memory Networks / 한국소프트웨어감정평가학회 논문지 / 한국소프트웨어감정평가학회 14(1) : 33~40

[confproc] S. H. M. Hickman / 2022 / Forecasting European Ozone Air Pollution With Transformers / Tackling Climate Change with Machine Learning:workshop at NeurIPS

[web] A. Zeng / 2022 / Are Transformers Effective for Time Series Forecasting? / arXiv:2205.13504v3

[web] H. Zhou / 2021 / Informer: Beyond Efficient Transformer for long Sequence Time-Series Forecasting / arXiv:2012.07436v3

[journal] H. Wei / 2023 / A novel approach to ultra-short-term wind power prediction based on feature engineering and Informer / Energy Reports 9 : 1236~1250

[journal] M. Kang / 2023 / 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)

[journal] T. Falatouri / 2022 / Predictive Analytics for Demand Forecasting – A Comparison of SARIMA and LSTM in Retail SCM / Procedia Computer Science 200 : 993~1003

KJCKorea
Journal Central

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

Application of Informer for time-series NO2 prediction

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

Application of Informer for time-series NO2 prediction

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (0)

REFERENCES (26) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.