Optimizing Long Short-Term Memory Network Parameter with Artificial Bee Colony Algorithm for PM2.5 Prediction

Optimizing Long Short-Term Memory Network Parameter with Artificial Bee Colony Algorithm for PM2.5 Prediction
  IJETT-book-cover           
  
© 2023 by IJETT Journal
Volume-71 Issue-2
Year of Publication : 2023
Author : Thanpitcha Atiwanwong, Adirek Jantakun, Adisak Sangsongfa
DOI : 10.14445/22315381/IJETT-V71I2P234

How to Cite?

Thanpitcha Atiwanwong, Adirek Jantakun, Adisak Sangsongfa, "Optimizing Long Short-Term Memory Network Parameter with Artificial Bee Colony Algorithm for PM2.5 Prediction," International Journal of Engineering Trends and Technology, vol. 71, no. 2, pp. 323-333, 2023. Crossref, https://doi.org/10.14445/22315381/IJETT-V71I2P234

Abstract
The problem caused by the PM2.5 value exceeding the standard causes an impact on the population, whether in terms of health, economics, and social aspects, not only in Thailand but all over the world. To solve the problem of PM2.5 occurrence well, it is necessary to be able to predict PM2.5 occurrence effectively. Therefore, this research presents the prediction of PM2.5 occurrence using the Long Short Term Memory neural network. Parameter optimization with the Artificial Bee Colony algorithm, the experimental results obtained an average accuracy of 98%, an average error (MSE) of 0.00267, and an overall parameter value of 6,476 params. The experimental results were compared with the Long Short Term Memory neural network that used experts to determine the parameters. The results showed that the average accuracy was 96%, the average error (MSE) was 0.00651, and the total number of parameters was 21,025 params.

Keywords
Artificial Neural Network, Long Short Term Memory, Artificial Bee Colony Algorithm, PM2.5

References
[1] T. Airveda, What Is Pm2.5 and Why Is It Important?, Airveda, 2017. [Online]. Available: https://www.airveda.com/blog/what-is-pm2- 5-and-why-is-it-important
[2] Ambient Air Pollution, World Health Organization: Health Impact, Institute for Health and Evaluation, University of Washington, 2020.
[3] Yanlin Qi et al., “A Hybrid Model for Spatiotemporal Forecasting of PM2.5 Based on Graph Convolutional Neural Network and Long Short-Term Memory,” Science of the Total Environment, vol. 664, pp. 1-10, 2019. Crossref, https://doi.org/10.1016/j.scitotenv.2019.01.333
[4] Dewan Seng et al., “Spatiotemporal Prediction of Air Quality Based on LSTM Neural Network,” Alexandria Engineering Journal, vol. 60, no. 2, 2020. Crossref, http://dx.doi.org/10.1016/j.aej.2020.12.009
[5] Thanpitcha Atiwanwong, and Saweth Hongprasit, “A Low-Power Real-Time Pollution Monitoring System Using ESP LoRa,” Mahasarakham International Journal of Engineering Technology, vol. 6, no. 1, pp. 36–40, 2020. Crossref, https://doi.org/10.14456/mijet.2020.8
[6] Syed Ahsin Ali Shah et al., “A Hybrid Model for Forecasting of Particulate Matter Concentrations Based on Multiscale Characterizations and Machine Learning Techniques,” Mathematical Biosciences and Engineering, vol. 18, no. 3, pp. 1192–2009. Crossref, https://doi.org/10.3934/mbe.2021104
[7] Rayner, and David Christopher Ferguson, “Optimization for Heuristic Search,” Thesis ERA, 2014, Crossref, https://doi.org/10.7939/R39W91
[8] Vincent Kenny, Matthew Nathal, and Spencer Saldana, Heuristic Algorithms, Optimization, 2014, [Online]. Available:
https://optimization.mccormick.northwestern.edu/index.php/heuristic/algorithms
[9] Feng Jiang et al., “Atmospheric PM2.5 Prediction Using Deepar Optimized by Sparrow Search Algorithm with Opposition-Based and Fitness-Based Learning,” Atmosphere, vol. 12, no. 7, pp. 1–18, 2021. Crossref, https://doi.org/10.3390/atmos12070894
[10] Jie Heng, and Min Li, “Prediction of PM 2.5 Concentration Based on BP Neural Network Optimized By Bee Colony Algorithm,” MATEC Web of Conferences, vol. 355, p. 03025, 2022. Crossref, https://doi.org/10.1051/matecconf/202235503025
[11] Sang Won Choi, and Brian H. S. Kim, “Applying PCA to Deep Learning Forecasting Model for Predicting PM2.5,” Sustainability, vol. 13, no. 7, pp. 1–30, 2021. Crossref, https://doi.org/10.3390/su13073726
[12] Qiang Wang et al., “PM2.5 Prediction Model Based on ABC-BP,” 2019 International Conference on Communications, Information System and Computer Engineering (CISCE), pp. 140–143, 2019. Crossref, https://doi.org/10.1109/CISCE.2019.00039
[13] X.-S. Yang, Nature-Inspired Optimization Algorithms, 2014, [Online]. Available: https://www.sciencedirect.com/science/article/pii/b9780124167438000166
[14] B. S. Chaudhari, and M. Zennaro, LPWAN Technologies for IoT and M2M Applications, Academic Press, pp. 1-3, 2020, [Online]. Available:
https://www.sciencedirect.com/science/article/pii/b978012818880400020x
[15] Health and Envitech, Air Quality Problems from PM2.5 in Thailand, Air Quality Problems from PM2.5, 2022, [Online]. Available: https://www.https://healthenvi.com/
[16] Sepp Hochreiter, and Jürgen Schmidhuber, “Long Short Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.
Crossref, https://doi.org/10.1162/neco.1997.9.8.1735
[17] M. Dhanalakshmi, and V. Radha, "Discretized Linear Regression and Multiclass Support Vector Based Air Pollution Forecasting Technique," International Journal of Engineering Trends and Technology, vol. 70, no. 11, pp. 315-323, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I11P234
[18] S. Neelima et al., “A Comprehensive Survey on Variants in Artificial Bee Colony (ABC),” International Journal of Computer Science and Information Technologies, vol. 7, no. 4, pp. 1684-1689, 2016.
[19] Palak, Preeti Gulia, and Nasib Singh Gill, “Optimized Test Case Selection Using Scout-Less Hybrid Artificial Bee Colony Approach and Crossover Operator,” International Journal of Engineering Trends and Technology, vol. 69, no. 3, pp. 39-45, 2021. Crossref, 10.14445/22315381/IJETT-V69I3P208
[20] Karaboga, Dervis, and Celal Ozturk, “A Novel Clustering Approach: Artificial Bee Colony (ABC) Algorithm,” Applied Soft Computing vol. 11, pp. 652–657, 2011.
[21] U. Taetragool, “Adaptive Hyperparameter Using Artificial Bee Colony Algorithms,” Big Data Experience Center, 2021. [Online]. Available: http://bigdataexperience.org/hyper-parameter-with-bee-colony/
[22] R. K. Punitha Stephan, Thompson Stephan, and A. Abraham, “A Hybrid Artificial Bee Co Algorithm for Improved Breast Cancer Diagnosis,” Neural Computing and Applications, vol. 33, no. 2, pp. 13667–13691, 2021. Crossref, https://doi.org/10.1007/s00521-021- 05997-6
[23] Junfu Xi et al., “Bp-Svm Air Quality Combina Gression,” International Journal of Earth Sciences and Engineering, vol. 9, no. 3, pp. 1194–1199, 2016.
[24] P. K. Raghavendra Kumar, and Y. Kumar, “Integrating Big Data Driven Sentiments Polarity and ABC-Optimized LSTM for Time Series Forecasting,” Multimedia Tools and Applications, vol. 81, pp. 34595–34614, 2021. Crossref, https://doi.org/10.1007/s11042-021-11029- 1
[25] J. Heng, and M. Li, “PM2.5 Prediction Based on Bp Neural Network Optimized By Bee Colony Algorithm,” ICPM2021, vol. 30250, pp. 1–8, 2022.
[26] Chen Zhang and et al., “PM2.5 Prediction Base on Multifractal Dimension and Artificial Bee Colony Algorithm,” Journal of Physics Conference Series, vol. 1237, no. 2, pp. 1–8, 2019. Crossref, https://doi.org/10.1088/1742-6596/1237/2/022085
[27] Qiang Wang et al., “PM2.5 Prediction Model Based on ABC-BP,” 2019 International Conference on Communications, Information System and Computer Engineering (CISCE), pp. 141–143, 2019. Crossref, https://doi.org/10.1109/CISCE.2019.00039
[28] Md. Mostafizer Rahman et al., “A Bidirectional LSTM Language Model for Code Evaluation and Repair,” Symmetry, vol. 13, no. 247, pp.1–15, 2021. Crossref, https://doi.org/10.3390/sym13020247