Implementing ANFIS with Three-Layer Architecture for Time Series

Abstract

The complex time addiction and randomness of multivariate time series make it nec-essary to apply time series analysis to these variables. So, it is important to produce methods that can be used appropriately for time series system identification. Time series are generally handled as a single-layer architecture consisting of only the observed data processing layer. In this study, a hybrid method has three-layer adapted and evaluated using an adaptive neuro-fuzzy inference system (ANFIS). The main motivation of this study is to learn the errors produced by ANFIS method and to use them as new in-formation. For this purpose, proposed method was evaluated using real-time serial data sets obtained from different fields. Due to the three-layer architecture, the errors caused by the results produced by ANFIS are reused. As a result, the method of learning from errors has been realized and better results have been produced com-pared to traditional single-layer architecture.

Keywords

• : Time series
• ANIFS
• neuro-fuzzy
• eurostat
• streamflow

Zaman Serileri için Üç-Katmanlı Mimari ile ANFIS'in Uygulanması

Abstract

Çok değişkenli zaman serilerinin karmaşık zaman bağımlılığı ve rastgeleliği, bu değiş-kenlere zaman serisi analizinin uygulanmasını gerekli kılar. Bu nedenle, zaman serisi sistemi tanımlaması için uygun şekilde kullanılabilecek yöntemler üretmek önemlidir. Zaman serileri genellikle yalnızca gözlenen veri işleme katmanından oluşan tek kat-manlı bir mimari olarak ele alınır. Bu çalışmada, üç katmanlı bir hibrit yöntem uyar-lanmış ve adaptif ağ tabanlı bulanık mantık çıkarım sistemi (ANFIS) kullanılarak değerlendirilmiştir. Bu çalışmanın temel motivasyonu, ANFIS yöntemi tarafından üre-tilen hataları öğrenmek ve bunları yeni bilgi olarak kullanmaktır. Bu amaçla, önerilen yöntem farklı alanlardan elde edilen gerçek zamanlı seri veri kümeleri kullanılarak değerlendirilmiştir. Üç katmanlı mimari nedeniyle, ANFIS tarafından üretilen sonuçların neden olduğu hatalar yeniden kullanılmaktadır. Sonuç olarak, hatalardan öğrenme yöntemi gerçekleştirilmiş ve geleneksel tek katmanlı mimariye kıyasla daha iyi sonuçlar üretilmiştir.

Keywords

• Zaman Serileri
• ANFIS
• sinirsel-bulanık
• eurostat
• nehir akış

References

1. F. Petropoulos et al., “Forecasting: theory and practice,” International Journal of Fore-casting, vol. 38, no. 3, pp. 705–871, 2022.
2. Y. Xiao, J. J. Liu, Y. Hu, Y. Wang, K. K. Lai, and S. Wang, “A neuro-fuzzy combination model based on singular spectrum analysis for air transport demand forecasting,” Journal of Air Transport Management, vol. 39, pp. 1–11, 2014.
3. S. Kim and D. H. Shin, “Forecasting short-term air passenger demand using big data from search engine queries,” Automation in Construction, vol. 70, pp. 98–108, 2016.
4. F. Perla, R. Richman, S. Scognamiglio, and M. V. Wüthrich, “Time-series forecasting of mortality rates using deep learning,” Scandinavian Actuarial Journal, no. 7, pp. 572–598, 2021.
5. Y. Si et al., “Revealing the water-energy-food nexus in the Upper Yellow River Basin through multi-objective optimization for reservoir system,” Science of The Total Environment, vol. 682, pp. 1–18, 2019.
6. X. Lei et al., “Stochastic optimal operation of reservoirs based on copula functions,” Journal of Hydrology, vol. 557, pp. 265–275, 2018.
7. X. Zeng, T. Hu, X. Cai, Y. Zhou, and X. Wang, “Improved dynamic programming for parallel reservoir system operation optimization,” Advances in Water Resources, vol. 131, 103373, 2019.
8. J. Zhao, Z. Wang, D. Wang et al., “Evaluation of economic and hydrologic impacts of unified water flow regulation in the yellow river basin,” Water Resource Management, vol. 23, pp. 1387–1401, 2009.

9. D. Yin, M. L. Roderick, G. Leech, F. Sun, and Y. Huang, “The contribution of reduction in evaporative cooling to higher surface air temperatures during drought,” Geophysical Research Letters, vol. 41, no. 22, pp. 7891–7897, 2014.
10. R. Hui, J. Herman, J. Lund, and K. Madani, “Adaptive water infrastructure planning for nonstationary hydrology,” Advances in Water Resources, vol. 118, pp. 83–94, 2018.
11. J. Asha, S. S. Kumar, and S. Rishidas, “Forecasting performance comparison of daily maximum temperature using ARMA based methods,” Journal of Physics: Conference Series, vol. 1921, no. 1, 012041, 2021.
12. V. Coban, E. Guler, T. Kilic, and S. Y. Kandemir, “Precipitation forecasting in Marmara region of Turkey,” Arabian Journal of Geosciences, vol. 14, no. 2, 86, 2021.
13. S. Saha, A. Haque, and G. Sidebottom, “An empirical study on internet traffic prediction using statistical rolling model,” in 2022 International Wireless Communications and Mobile Computing Conference (IWCMC), Dubrovnik, Croatia, 2022, pp. 1058–1063.
14. M. Achite et al., “Forecasting of SPI and SRI using multiplicative ARIMA under climate variability in a Mediterranean region: Wadi Ouahrane Basin, Algeria,” Climate, vol. 10, no. 3, 2022.
15. S. Kim, P.-Y. Lee, M. Lee, J. Kim, and W. Na, “Improved state-of-health prediction based on auto-regressive integrated moving average with exogenous variables model in overcoming battery degradation-dependent internal parameter variation,” Journal of Energy Storage, vol. 46, 103888, 2022.
16. F. Serin, Y. Alisan, and A. Kece, “Hybrid time series forecasting methods for travel time prediction,” Physica A: Statistical Mechanics and its Applications, vol. 579, 126134, 2021.
17. G. Nergiz and F. Serin, “Forecasting lip landmark movements using time series models,” Journal of Information Analytics, vol. 1, no. 1, 2025.
18. N. K. Ahmed, A. F. Atiya, N. E. Gayar, and H. El-Shishiny, “An empirical comparison of machine learning models for time series forecasting,” Econometric Reviews, vol. 29, no. 5–6, pp. 594–621, 2010.
19. A. R. S. Parmezan, V. M. A. Souza, and G. E. A. P. A. Batista, “Evaluation of statistical and machine learning models for time series prediction,” Information Sciences, vol. 484, pp. 302–337, 2019.
20. D. Makala and Z. Li, “Prediction of gold price with ARIMA and SVM,” Journal of Physics: Conference Series, vol. 1767, no. 1, 012022, 2021.
21. M. Shad, Y. D. Sharma, and A. Singh, “Forecasting of monthly relative humidity in Delhi, India, using SARIMA and ANN models,” Modeling Earth Systems and Environment, 2022.
22. M. Elsaraiti and A. Merabet, “A comparative analysis of the ARIMA and LSTM predictive models and their effectiveness for predicting wind speed,” Energies, vol. 14, no. 20, 2021.
23. S. Park, J.-Y. Lee, and S. Kim, “Wind power forecasting based on time series and machine learning models,” The Korean Journal of Applied Statistics, vol. 34, no. 5, pp. 723–734, 2021.
24. M. Farsi et al., “Parallel genetic algorithms for optimizing the SARIMA model for better forecasting of the NCDC weather data,” Alexandria Engineering Journal, vol. 60, no. 1, pp. 1299–1316, 2021.
25. C. Chang, W. Y. Wang, W. C. Peng, and T. F. Chen, “Llm4ts: Aligning pre-trained LLMs as data-efficient time-series forecasters,” ACM Transactions on Intelligent Systems and Tech-nology, vol. 16, no. 3, pp. 1–20, 2025.
26. W. Xue et al., “CARD: Channel aligned robust blend transformer for time series forecasting,” arXiv, arXiv:2305.12095, 2023. [Online]. Available: https://arxiv.org/abs/2305.12095
27. H. Klopries and A. Schwung, “ITF-GAN: Synthetic time series dataset generation and ma-nipulation by interpretable features,” Knowledge-Based Systems, vol. 283, 111131, 2024.
28. Q. Zhao et al., “Temporal characteristics of attentional disengagement from emotional facial cues in depression,” Neurophysiologie Clinique, vol. 49, no. 3, pp. 235–242, 2019.
29. R. Bochare, A. Jain, and R. Shrivastava, “Exploring ANFIS hybrid optimization for im-proved rainfall-runoff predictions: insights from Banjar River Catchment, India,” Environ-ment, Development and Sustainability, pp. 1–17, 2025.
30. C. Sun et al., “The CEEMD-LSTM-ARIMA model and its application in time series predic-tion,” Journal of Physics: Conference Series, vol. 2179, no. 1, 012012, 2022.
31. J.-S. R. Jang, “ANFIS: adaptive-network-based fuzzy inference system,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 23, no. 3, pp. 665–685, 1993.
32. A. A. Chowdhury, K. T. Hasan, and K. K. S. Hoque, “Analysis and prediction of COVID-19 pandemic in Bangladesh by using ANFIS and LSTM network,” Cognitive Computation, vol. 13, pp. 761–770, 2021.
33. M. A. Shoorehdeli, M. Teshnehlab, A. K. Sedigh, and M. A. Khanesar, “Identification using ANFIS with intelligent hybrid stable learning algorithm approaches and stability analysis of training methods,” Applied Soft Computing, vol. 9, no. 2, pp. 833–850, 2009.
34. S. Saif, P. Das, and S. Biswas, “A hybrid model based on mBA-ANFIS for COVID-19 confirmed cases prediction and forecast,” Journal of the Institution of Engineers (India): Series B, vol. 102, no. 5, pp. 973–980, 2021.
35. M. A. A. Al-qaness, A. A. Ewees, H. Fan, and M. Abd El Aziz, “Optimization method for forecasting confirmed cases of COVID-19 in China,” Journal of Clinical Medicine, vol. 9, no. 3, 2020.
36. F. Serin, Y. Alisan, and M. Erturkler, “Predicting bus travel time using machine learning methods with three-layer architecture,” Measurement, vol. 198, 111403, 2022.
37. B. Haznedar, “Training adaptive neuro-fuzzy inference system (ANFIS) using simulated annealing algorithm,” Ph.D. dissertation, Inst. of Science, Erciyes Univ., Kayseri, Turkey, 2017.
38. Eurostat, “Who we are,” European Commission. [Online]. Available: https://ec.europa.eu/eurostat/web/main/about/who-we-are. [Accessed: 5 May 2022].
39. B. Haznedar and A. Kalınlı, “Detection of the relationship between thrombophilia disease with genetic disorders by ANFIS,” Sakarya University Journal of Science, vol. 20, no. 1, pp. 13–21, 2016.
40. K. N. Nabi, M. T. Tahmid, A. Rafi, M. E. Kader, and M. A. Haider, “Forecasting COVID-19 cases: A comparative analysis between recurrent and convolutional neural networks,” Results in Physics, vol. 24, 104137, 2021.