A new dynamic approach for non-singleton fuzzification in noisy time-series prediction

Pourabdollah, A ORCID: https://orcid.org/0000-0001-7737-1393, John, R and Garibaldi, JM, 2017. A new dynamic approach for non-singleton fuzzification in noisy time-series prediction. In: 2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), Naples, Italy, 9-12 July 2017. Piscataway, NJ: Institute of Electrical and Electronics Engineers, pp. 1171-1176. ISBN 9781509060344

Preview

Text 10623_Pourabdollah.pdf - Post-print Download (682kB) | Preview

Abstract

Non-singleton fuzzification is used to model uncertain (e.g. noisy) inputs within fuzzy logic systems. In the standard approach, assuming the fuzzification type is known, the observed [noisy] input is usually considered to be the core of the input fuzzy set, usually being the centre of its membership function. This paper proposes a new fuzzification method (not type), in which the core of an input fuzzy set is not necessarily located at the observed input, rather it is dynamically adjusted based on statistical methods. Using the weighted moving average, a few past samples are aggregated to roughly estimate where the input fuzzy set should be located. While the added complexity is not huge, applying this method to the well-known Mackey-Glass and Lorenz time-series prediction problems, show significant error reduction when the input is corrupted by different noise levels.

Item Type:	Chapter in book
Creators:	Pourabdollah, A., John, R. and Garibaldi, J.M.
Publisher:	Institute of Electrical and Electronics Engineers
Place of Publication:	Piscataway, NJ
Date:	2017
ISBN:	9781509060344
Identifiers:	Number Type 10.1109/FUZZ-IEEE.2017.8015575 DOI
Divisions:	Schools > School of Science and Technology
Record created by:	Jonathan Gallacher
Date Added:	06 Apr 2018 08:19
Last Modified:	06 Apr 2018 08:19
URI:	https://irep.ntu.ac.uk/id/eprint/33210

Actions (login required)

Edit View

Statistics

Views

Downloads