Harnessing Emerging Knowledge and Extensibility Techniques for Stationarity and Normalization in Multi-Agent Time Series Forecasting
Received: 7 April 2025 | Revised: 14 May 2025, 25 May 2025, and 7 June 2025 | Accepted: 9 June 2025 | Online: 6 October 2025
Corresponding author: P. P. G. Dinesh Asanka
Abstract
This study introduces a novel multi-agent approach designed to optimize time series forecasting through an efficient normalization framework. The proposed architecture leverages the knowledge-emerging and extensibility properties, enabling an adaptive and scalable forecasting performance. The system is evaluated using the Hiroshima human mobility dataset. It consists of two key components: (1) a stationarity verification module employing the Augmented Dickey-Fuller (ADF) test and (2) a dynamic normalization module that selects the optimal technique based on ADF statistics and p-values. Five normalization methods—MaxAbs, MinMax, Log, Z-Score, and Sigmoid are analyzed to determine the most effective approach for different time series characteristics. Additionally, knowledge-emerging techniques, specifically the J48 decision tree algorithm, are integrated to enhance the system's predictive efficiency. Experimental results demonstrate the effectiveness of the proposed multi-agent architecture in improving the accuracy and adaptability of time series forecasting.
Keywords:
time series, stationary testing, normalization, multi-agent architectureDownloads
References
L. H. Le, "Time series analysis and applications in data analysis, forecasting and prediction," HPU2 Journal of Science: Natural Sciences and Technology, vol. 3, no. 1, pp. 20–29, Apr. 2024.
M. F. Rizvi, "ARIMA Model Time Series Forecasting," International Journal for Research in Applied Science and Engineering Technology, vol. 12, no. 5, pp. 3782–3785, May 2024.
J. Shi, M. Jain, and G. Narasimhan, "Time Series Forecasting Using Various Deep Learning Models," World Academy of Science, Engineering and TechnologyInternational Journal of Computer and Systems Engineering, vol. 16, no. 6, pp. 224–232, 2022.
W. Du et al., "TSI-Bench: Benchmarking Time Series Imputation." arXiv, Oct. 31, 2024.
H. Pehlivan, "A novel outlier detection method based on Bayesian change point analysis and Hampel identifier for GNSS coordinate time series," EURASIP Journal on Advances in Signal Processing, vol. 2024, no. 1, Apr. 2024.
J. C. Ooms, "Assessing Stationarity in Univariate Time Series with Applications in Physics and Finance," Bachelor of Science Thesis, Delft University of Technology, Delft, Netherlands, 2012.
A. Roza, E. S. Violita, and S. Aktivani, "Study of Inflation using Stationary Test with Augmented Dickey Fuller & Phillips-Peron Unit Root Test (Case in Bukittinggi City Inflation for 2014-2019)," EKSAKTA: Berkala Ilmiah Bidang MIPA, vol. 23, no. 02, pp. 106–116, Jun. 2022.
C. F. Baum, "Tests for stationarity of a time series," Stata Technical Bulletin, vol. 10, no. 57, pp. 36–46, 2001.
A. S. Downes and H. Leon, "Testing for unit roots: An empirical investigation," Economics Letters, vol. 24, no. 3, pp. 231–235, Jan. 1987.
S. Kappal, "Data Normalization using Median & Median Absolute Deviation (MMAD) based Z-Score for Robust Predictions vs. Min – Max Normalization," London Journals Press, vol. 19, no. 4, pp. 39–44.
L. Lavitas and T. Zhang, "A Time‐Symmetric Self‐Normalization Approach for Inference of Time Series," Journal of Time Series Analysis, vol. 39, no. 5, pp. 748–762, Sep. 2018.
A. I. Abubakar, H. Chiroma, and S. Abdulkareem, "Comparing performances of neural network models built through transformed and original data," in 2015 International Conference on Computer, Communications, and Control Technology (I4CT), Kuching, Sarawak, Malaysia, Apr. 2015, pp. 364–369.
H. R. Fogno Fotso, C. V. Aloyem Kazé, and G. D. Kenmoe, "Optimal Input Variables Disposition of Artificial Neural Networks Models for Enhancing Time Series Forecasting Accuracy," Applied Artificial Intelligence, vol. 34, no. 11, pp. 792–815, Sep. 2020.
Y. Xiang, J. Smith, and J. Kroes, "Multiagent Bayesian Forecasting of Time Series with Graphical Models," in Proceedings of the Twenty-Second International FLAIRS Conference, Sanibel Island, Florida, USA, 2009.
" Š. Raudys and I. Zliobaite, "The Multi-Agent System for Prediction of Financial Time Series," in Lecture Notes in Computer Science, Berlin, Heidelberg: Springer Berlin Heidelberg, 2006, pp. 653–662.
Y. Yuan, X. Weng, Y. Ou, and K. Kitani, "AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting," in Proceedings of the IEEE/CVF international conference, Oct. 2021, pp. 9813–9823.
D. A. Grigoriev and A. A. Musaev, "Distributed Multi-Expert Forecasting System for Non-Stationary Processes," in 2023 International Russian Automation Conference (RusAutoCon), Sochi, Russian Federation, Sep. 2023, pp. 369–373.
M. V. Muntean and D. Onita, "Agent for Preprocessing and Forecasting Time-Series Data," in 2018 10th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Iasi, Romania, Jun. 2018, pp. 1–4.
B. Sanwouo, C. Quinton, and R. Rouvoy, "TS-Pothole: automated imputation of missing values in univariate time series," Neural Computing and Applications, vol. 36, no. 36, pp. 22923–22955, Dec. 2024.
P. D. Asanka, C. Rajapakshe, and M. Takahashi, "Identifying Unusual Human Movements Using Multi-Agent and Time-Series Outlier Detection Techniques," in 2023 3rd International Conference on Advanced Research in Computing (ICARC), Belihuloya, Sri Lanka, Feb. 2023, pp. 1–6.
P. Asanka and C. Rajapakshe, "A Study on Outlier Correction Techniques Using Multi-agent Techniques for the Accurate Predictions of Human Mobility," in Smart Innovation, Systems and Technologies, Singapore: Springer Nature Singapore, 2025, pp. 239–248.
"Floating population data." Accessed: May 31, 2025. [Online]. Available: https://agoop-co-jp.translate.goog/service/dynamic-population-data/?_x_tr_sl=ja&_x_tr_tl=en&_x_tr_hl=en.
P. Sokannit and P. Chujai, "Forecasting Household Electricity Consumption Using Time Series Models," International Journal of Machine Learning and Computing, vol. 11, no. 6, pp. 380–386, Nov. 2021.
S. N. Nnamchi, Z. O. Jagun, M. A. Ijomah, O. A. Nnamchi, and J. D. Busingye, "Time Series Analysis of Global Energy Indices: Logarithmic and Normalized Techniques for Developmental Studies," Energy Economics Letters, vol. 9, no. 1, pp. 1–19, Jan. 2022.
Downloads
How to Cite
License
Copyright (c) 2025 P. P. G. Dinesh Asanka, Chathura Rajapakshe, Masakazu Takahashi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
