An Interval Type-2 Fuzzy LSTM Algorithm for Modeling Environmental Time-Series Prediction

Anthropogenic Pollution

دوره 6، شماره 2، اسفند 2022، صفحه 62-72   

نوع مقاله: ORIGINAL RESEARCH PAPER

شناسه دیجیتال (DOI): 10.22034/ap.2022.1963124.1133

نویسندگان

Aref Safari^{* 1}؛ Rahil Hosseini²

¹Department of Computer Engineering, Shahr-e-Qods Branch, Islamic Azad University

²Department of Computer Engineering, Shahr-e-Qods Branch, Islamic Azad University, Tehran, Iran

چکیده

The statistical attributes of the non-stationary problems such as air quality and other natural phenomena frequently changed. Type-2 fuzzy logic is a robust and capable model to cope with high-order uncertainties associated with non-stationary time-dependent features. This research's main objective is to present a novel Fuzzy Deep LSTM (IT2FLSTM) model to predict air quality for Tehran and Beijing in a short and long time series scale. The proposed model has been evaluated on a real dataset that contains the one-decade information about outdoor pollutants from April 2011 to November 2020 in Tehran and Beijing. The IT2FLSTM model was evaluated using a ROC curve analysis and validated using 10-fold cross-validation. The results confirm the IT2FLSTM model's superiority with an average area under the ROC curve (AUC) of 97 % and a 95% confidence interval of [95-98] %. The proposed IT2FLSTM model promises to predict complex problems to make strategic prevention decisions to save more lives.

کلیدواژه‌ها

Deep learning؛ Type-2 fuzzy logic؛ LSTM network؛ Air Pollution Prediction؛ Enviroment

مراجع

Loquercio, M. Segu, and D. Scaramuzza. (2020). A General Framework for Uncertainty Estimation in Deep Learning, IEEE robotics and automation letters.
2. Safari, R. Hosseini and M. Mazinani, “A Type-2 Fuzzy Time Series Model for Pattern Similarity Analysis: A Case Study on Air Quality Forecasting,” in IEEE Intelligent Systems, (2021).
3. Safari, R. Hosseini, M. Mazinani, “A novel deep interval type-2 fuzzy LSTM (DIT2FLSTM) model applied to COVID-19 pandemic time-series prediction”, Journal of Biomedical Informatics, Vol 123, (2021).
4. Biancofiore, F., Busilacchio, M., Verdecchia, M., Tomassetti, B., Aru o, E., Bianco, S., Di Tommaso, S., Colangeli, C., Rosatelli, G., Di Carlo, P. (2017). Recursive neural network model for analysis and forecast of PM10 and PM2.5. Atmos. Pollut. Res. 8, 652–659.
5. Li, C. Zhou, W. Peng, Y. Lv, and X. Luo. (2020). Accurate prediction of short-term photovoltaic power generation via a novel double input-rule-modules stacked deep fuzzy method, Energy, 11(7) 118700. https://doi.org/10.1016/j.energy.2020.118700
6. Confalonieri, U., et al. (2007) Human Health. In: Parry, M.L., Canziani, O.F., Palutikof, J.P., van der Linden, P.J. and Hanson, C.E., Eds., Climate Change 2007: Impacts, Adaptation and Vulnerability, Contribution of Working Group II to the Fourth Assessment Report of the Intergovernmental Panel on Climate Change, Cambridge, 391-431.
7. Wu and J. M. Mendel. (2019). Recommendations on designing practical interval type-2 fuzzy systems, Engineering Applications of Artificial Intelligence, 85 182–193. https://doi.org/10.1016/j. engappai.2019.06.012
8. Wu. (2013). approaches for reducing the computational cost of interval type-2 fuzzy logic systems Overview and comparisons, IEEE Transactions on Fuzzy Systems, 21(1) 80–99. doi: 10.1109/TFUZZ.2012.2201728.
9. Wu. (2012). On the Fundamental Differences Between Interval Type-2 and Type-1 Fuzzy Logic Controllers, IEEE Transactions on Fuzzy Systems, 20(5) 832-848 doi: 10.1109/TFUZZ.2012.2186818.
10. Gaxiola F., Melin P., Valdez F., Castro J.R. (2018). Ensemble Neural Network with Type-2 Fuzzy Weights Using Response Integration for Time Series Prediction. Studies in Fuzziness and Soft Computing, vol 361. https://doi.org/10.1007/978-3-319-75408-6_15
11. Ibarra-Berastegi, G., Elias, A.; Barona, A., Saenz, J., Ezcurra, A., de Argandoña, J.D. (2008). From diagnosis to prognosis for forecasting air pollution using neural networks: Air pollution monitoring in Bilbao. Environ. Model. Softw, 23, 622–637.
12. M. Mendel. (2013). on km algorithms for solving type-2 fuzzy set problems, IEEE Transactions on Fuzzy Systems, 21(3) 426–446. doi: 10.1109/ TFUZZ.2012.2227488.
13. J. M. Mendel, R. I. John, and F. Liu. (2006). Interval type-2 fuzzy logic systems made simple, IEEE Transactions on Fuzzy Systems, 14 (6) doi: 808–821. 10.1109/TFUZZ.2006.879986.
14. Safari A, Hosseini R, Mazinani M. Dynamic Type-2 Fuzzy Time Warping (DT2FTW): A Hybrid Model for Uncertain Time-Series Prediction. IJFIS 2021; 21:338 348.
15. K. Smagulova, O. Krestinskaya, and A. P, James. (2018). A memristor-based long short-term memory circuit. Analog Integr. Circuits Signal Process. 95(3) 467–472. doi: https://doi.org/10.1007/s10470-018- 1180-y
16. Li, C., Wang, Z. and Rao, M Long. (2019). shortterm memory networks in memristor crossbar arrays. Nat Mach Intell, 1(1) 49–57. https://doi.org/10.1038/ s42256-018-0001-4
17. Li, R., Chen, X. and Balezentis, T. (2020). Multistep least squares support vector machine modeling approach for forecasting short-term electricity demand with application. Neural Comput & Applic. 21(1) (2020) 1–20. https://doi.org/10.1007/s00521-020- 04996-3
18. Liang Guo, Naipeng Li, Feng Jia, Yaguo Lei, Jing Lin. (2017). A recurrent neural network-based health indicator for remaining useful life prediction of bearings, Neurocomputing, 24098-109 doi: https://doi. org/10.1016/j.neucom.2017.02.045.
19. Liu, H.; Li, Q.; Yu, D.; Gu, Y. (2019). Air Quality Index and Air Pollutant Concentration Prediction Based on Machine Learning Algorithms. Appl. Sci. 9, 4069.
20. Marlier, M.E., Jina, A.S., Kinney, P.L. (2016). Extreme Air Pollution in Global Megacities. Curr Clim Change Rep 2, 15–27. https://doi.org/10.1007/s40641-016- 0032-z
21. N. Anh, S. Suresh, M. Pratama, and N. Srikanth. (2019). Interval prediction of wave energy characteristics using meta-cognitive interval type-2 fuzzy inference system, Knowledge-Based Systems, 169 doi:28-38. https://doi.org/10.1016/j.knosys.2019.01.025.
22. P. C. de Lima Silva, H. J. Sadaei, R. Ballini, and F. G. Guimarães. (2020). Probabilistic Forecasting with Fuzzy Time Series, IEEE Transactions on Fuzzy Systems, 28(8) 1771-1784 doi: 10.1109/ TFUZZ.2019.2922152.
23. P. Pahlavani, H. Sheikhian and B. Bigdeli. (2017). Assessment of an air pollution monitoring network to generate urban air pollution maps using Shannon information index, fuzzy overlay, and Dempster- Shafer theory, A case study: Tehran, Iran, Atmospheric Environment, (167), 254-269, https://doi.org/10.1016/j. atmosenv.2017.08.039.
24. R. N. Almanza, R. J. Ramírez, G. Licea, J. R. Castro. (2020). Automated Ontology Extraction from Unstructured Texts using Deep Learning, Intuitionistic and Type-2 Fuzzy Logic Enhancements in Neural and Optimization Algorithms: Theory and Applications, Springer cham. 727-755. https://doi.org/10.1007/978- 3-030-35445-9
25. Safari, A., Hosseini, R., Mazinani, M. (2022). An Adaptive Intelligent Type-2 Fuzzy Logic Model to Manage Uncertainty of Short and Long Time-Series in Covid-19 Patterns Prediction: A Case Study on Iran. Computational Intelligence in Electrical Engineering.
26. Safari, A., Mazinani, M., Hosseini, R. (2017). A Novel Type-2 Adaptive Neuro-Fuzzy Inference System Classifier for Modelling Uncertainty in Prediction of Air Pollution Disaster (RESEARCH NOTE). International Journal of Engineering, 30(11), 1746- 1751.
27. V. Georgescu. (2014). Joint propagation of ontological and epistemic uncertainty across risk assessment and fuzzy time series models, Computer Science and Information Systems. 11(2) doi: https://doi. org/10.2298/CSIS121215048G
28. V. Sumati and C. Patvardhan. (2018). Interval Type- 2 Mutual Subsethood Fuzzy Neural Inference System (IT2MSFuNIS), IEEE Transactions on Fuzzy Systems, 26(1)
29. W. Chen and Y. Zou. (2020). Group decision making under generalized fuzzy soft sets and limited cognition of decision makers, Engineering Applications of Artificial Intelligence, 87 103344. Doi: https://doi. org/10.1016/j.engappai.2019.103344.
30. Xiaoyang Liu, Zhigang Zeng, Donald C. Wunsch. (2020). Memristor-based LSTM network with in situ training and its applications, Neural Networks, 131, 300-311. https://doi.org/10.1016/j.neunet.2020.07.035
31. Y. Lin, J. Chang, N. R. Pal and C. Lin. (2013). A Mutually Recurrent Interval Type-2 Neural Fuzzy System (MRIT2NFS) With Self-Evolving Structure and Parameters, IEEE Transactions on Fuzzy Systems. 21(3) 492-509, 10.1109/TFUZZ.2013.2255613.
32. Sekhavati E, Jalilzadeh Yengejeh R, (2021) Assessment Optimization of Safety and Health Risks Using Fuzzy TOPSIS Technique (Case Study: Construction Sites in the South of Iran). Journal of Environmental Health and Sustainable Development, 6(4): 1494-1506.
33. Sekhavati E, Jalilzadeh R, (2022) Optimizing the Risk of Building Environments Using Multi-Criteria Decision Making. Anthropogenic Pollution, 6(1):1-7.
34. Hoseini LK, Yengejeh RJ, Rouzbehani MM, Sabzalipour S, (2022) Health risk assessment of volatile organic compounds (VOCs) in a refinery in the southwest of Iran using SQRA method. Frontiers in Public Health, 10:978354
35. Khajeh Hoseini L, Jalilzadeh Yengejeh R, Mahmoudie A, Mohammadi Rouzbehani M, Sabz Alipour S, (2021) Prioritization of Effective Strategic Parameters in the Removal of VOCs from the ROP System by Using AHP: A Case Study of Abadan Oil Refinery. Journal of Health Sciences & Surveillance System, 9(3):199-205.
36. Guo, H., Gu, W., Khayatnezhad, M. & Ghadimi, N. 2022. Parameter extraction of the SOFC mathematical model based on fractional order version of dragonfly algorithm. International Journal of Hydrogen Energy, 47, 24059-24068.
37. Lin, H. 2022. Levafix blue color’s visible light degradation utilizing Fenton and photo-Fenton procedures. Water and Environmental Sustainability, 2, 1-8.
38. Mobar, S. & Bhatnagar, P. 2022. ling women by Safari A. & Hosseini H. 72 Anthropogenic Pollut J. Vol 6 (2), 2022: 62-72 Greenhouse plan as illustrated in the Post-Feminist Tamil Film 36 Vayadhinile. Water and Environmental Sustainability, 2, 9-12.
39. Zhang, J., Khayatnezhad, M. & Ghadimi, N. 2022. Optimal model evaluation of the proton-exchange membrane fuel cells based on deep learning and modified African Vulture Optimization Algorithm. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 44, 287-305.