Abstract
In this chapter, we contribute to the innovative method of time series analysis and forecasting using fuzzy transform and fuzzy natural logic. We will demonstrate that the F-transform is a powerful technique for extraction of the trend-cycle of time series. Further step is automatic linguistic evaluation of the course (tendency) of time series in a specified time slot. The main tool is the first degree F-transform (F1-transform) which makes it possible to estimate average tangent of the given function. We thus obtain an objective result even if the trend is not visually apparent from the graph of the time series.
This paper was supported by the program MŠMT-KONTAKT II, project LH 12229 “Research and development of methods and means of intelligent analysis of time series for the strategic planing problems”. Additional support was given also by the European Regional Development Fund in the IT4Innovations Centre of Excellence project (CZ.1.05/1.1.00/02.0070).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
This logic originates from fuzzy logic in broader sense (FLb-logic) introduced in [4] and developed as extension of the mathematical fuzzy logic.
- 2.
A testing version of LFL Forecaster is available on the web page http://irafm.osu.cz.
- 3.
Of course, at present stage we confine only to a small part of natural language expressions.
- 4.
By abuse of language, we call by direct F-transform both the procedure as well as its result \( \hat{f} \).
- 5.
It is difficult to state that these expressions are synonymous in the strict sense. This requires further linguistic research.
References
Novák, V., Štĕpnička, M., Perfilieva, I., Pavliska, V.: Analysis of periodical time series using soft computing methods. In: Ruan, D., Montero, J. Lu, J., Martnez, L., D’hondt, P., Kerre, E. (eds.) Computational Intelligence in Decision and Control, pp. 55–60. World Scientific, New Jersey (2008)
Novák, V., Štĕpnička, M., Dvořák, A., Perfilieva, I., Pavliska, V., Vavřčková, L.: Analysis of seasonal time series using fuzzy approach. Int. J. Gen. Syst. 39, 305–328 (2010)
Novák, V., Perfilieva, I., Pavliska, V.: The use of higher-order F-transform in time series analysis. In: World Congress IFSA 2011 and AFSS 2011, Surabaya, Indonesia, pp. 2211–2216 (2011)
Novák, V.: Towards formalized integrated theory of fuzzy logic. In: Bien, Z., Min, K. (eds.) Fuzzy Logic and Its Applications to Engineering, Information Sciences, and Intelligent Systems, pp. 353–363. Kluwer, Dordrecht (1995)
Novák, V., Perfilieva, I., Jarushkina, N.G.: A general methodology for managerial decision making using intelligent techniques. In: Rakus-Anderson, E., Yager, R., Ichalkaranje, N., Jain, L. (eds.) Recent Advances in Fuzzy Decision-Making, pp. 103–120. Springer, Heidelberg (2009)
Novák, V.: Reasoning about mathematical fuzzy logic and its future. Fuzzy Sets Syst. 192, 25–44 (2012)
Novák, V., Perfilieva, I., Močkoř, J.: Mathematical Principles of Fuzzy Logic. Kluwer, Boston (1999)
Perfilieva, I.: Fuzzy transforms: theory and applications. Fuzzy Sets Syst. 157, 993–1023 (2006)
Perfilieva, I., Novák, V., Dvořák, A.: Fuzzy transform in the analysis of data. Int. J. Approx. Reason. 48, 36–46 (2008)
Perfilieva, I.: Fuzzy transforms: A challenge to conventional transforms. In: Hawkes, P. (ed.) Advances in Images and Electron Physics, vol. 147, pp. 137–196. Elsevier Academic Press, San Diego (2007)
Perfilieva, I., Dařková, M., Bede, B.: Towards a higher degree F-transform. Fuzzy Sets Syst. 180, 3–19 (2011)
Andĕl, J.: Statistical Analysis of Time Series. SNTL, Praha (1976) (in Czech)
Hamilton, J.: Time Series Analysis. Princeton University Press, Princeton (1994)
Bovas, A., Ledolter, J.: Statistical Methods for Forecasting. Wiley, New York (2003)
Novák, V., Perfilieva, I., Krejnovich, V.: F-transform in the analysis of periodic signals. In: Inuiguchi, M., Kusunoki, Y., Seki, M. (eds.) Proceedimgs of 15th Czech-Japan Seminar on Data Analysis and Decision Making under Uncertainty, Osaka, Japan: Osaka University, pp. 150–158 (2012)
Novák, V.: A comprehensive theory of trichotomous evaluative linguistic expressions. Fuzzy Sets Syst. 159(22), 2939–2969 (2008)
Novák, V.: A formal theory of intermediate quantifiers. Fuzzy Sets Syst. 159(10), 1229–1246 (2008)
Murinová, P., Novák, V.: A formal theory of generalized intermediate syllogisms. Fuzzy Sets Syst. 186, 47–80 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Novák, V., Pavliska, V., Štěpnička, M., Štěpničková, L. (2014). Time Series Trend Extraction and Its Linguistic Evaluation Using F-Transform and Fuzzy Natural Logic. In: Zadeh, L., Abbasov, A., Yager, R., Shahbazova, S., Reformat, M. (eds) Recent Developments and New Directions in Soft Computing. Studies in Fuzziness and Soft Computing, vol 317. Springer, Cham. https://doi.org/10.1007/978-3-319-06323-2_27
Download citation
DOI: https://doi.org/10.1007/978-3-319-06323-2_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-06322-5
Online ISBN: 978-3-319-06323-2
eBook Packages: EngineeringEngineering (R0)