Modeling Corrupted Time Series Data via Nonsingleton Fuzzy Logic System

2015 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

Wagner

Aladi

2015

A major asset of fuzzy logic systems is dealing with uncertainties arising in their various applications, thus it is important to make them achieve this task as effectively and comprehensively as possible. While singleton fuzzy logic systems provide some capacity to deal with such uncertainty aspects, nonsingleton fuzzy logic systems (NSFLSs) have further enhanced this capacity, particularly in handling input uncertainties. This paper proposes a novel approach to NSFLSs, which further develops this potential by changing the method of handling input fuzzy sets within the inference engine. While the standard approach is getting the maximum of the intersection between input's and antecedent's fuzzy sets (in the "pre-filtering" stage), it is proposed to employ the centroid of the intersection as the basis of each rule's firing degree. The motivation is to capture the interaction of input and antecedent fuzzy sets with high fidelity, thus making NSFLSs more sensitive to the input's uncertainty information. The testbed is the common problem of Mackey-Glass time series prediction in the presence of input noise. Analyses of the results show that the new method outperforms the standard approach (by reducing the prediction error) and has potential for a more efficient uncertainty handling in NSFLS applications.

Section: Introductionmentioning

confidence: 99%

Changes under the hood - a new type of non-singleton fuzzy logic system

2015 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

Wagner

Aladi

2015

“…After establishing the theory and application of NSFLS and its application in noisy time-series prediction problems ( [6], [7], [17]), some practical prediction applications were also examined. For example in [18], the Box-Jenkin's gas furnace time series data is used in conjunction with NSFLS-based prediction, showing that the employed NSFLS provides better prediction in comparison to the SFLS. Among the different time-series prediction problems, predicting Mackey-Glass time series [19] has been a benchmark problem in the literature which has been considered by a number of researchers, e.g., in [20]- [23].…”

Section: Other Related Workmentioning

confidence: 99%

Improved Uncertainty Capture for Nonsingleton Fuzzy Systems

IEEE Trans. Fuzzy Syst.

Wagner

Aladi

et al. 2016

(2016) Improved uncertainty capture for non-singleton fuzzy systems. IEEE Transactions on Fuzzy Systems, 24 (6). pp. 1513 -1524 . ISSN 1941 Access from the University of Nottingham repository: http://eprints.nottingham.ac.uk/45444/1/Improved%20Uncertainty%20Capture%20for %20Non-Singleton%20Fuzzy%20Systems.pdf Copyright and reuse:The Nottingham ePrints service makes this work by researchers of the University of Nottingham available open access under the following conditions. This article is made available under the University of Nottingham End User licence and may be reused according to the conditions of the licence. For more details see: http://eprints.nottingham.ac.uk/end_user_agreement.pdf A note on versions:The version presented here may differ from the published version or from the version of record. If you wish to cite this item you are advised to consult the publisher's version. Please see the repository url above for details on accessing the published version and note that access may require a subscription.For more information, please contact eprints@nottingham.ac.uk 1 Improved Uncertainty Capture for Non-Singleton Fuzzy SystemsAmir Pourabdollah, Member, IEEE, Christian Wagner, Senior Member, IEEE, Jabran Hussain Aladi, Student Member, IEEE and Jonathan M. Garibaldi, Member, IEEE Abstract-In non-singleton fuzzy logic systems (NSFLSs), input uncertainties are modelled with input fuzzy sets in order to capture input uncertainty (e.g., sensor noise). The performance of NSFLSs in handling such uncertainties depends on both: the appropriate modelling in the input fuzzy sets of the uncertainties present in the system's inputs, and on how the input fuzzy sets (and their inherent model of uncertainty) interact with the antecedent and thus affect the inference within the remainder of the NSFLS. This paper proposes a novel development on the latter. Specifically, an alteration to the standard composition method of type-1 fuzzy relations is proposed, and applied to build a new type of NSFLS. The proposed approach is based on employing the centroid of the intersection of input and antecedent sets as origin of the firing degree, rather than the traditional maximum of their intersection, thus making the NSFLS more sensitive to changes in the input's uncertainty characteristics. The traditional and novel approach to NSFLSs are experimentally compared for two well-known problems of Mackey-Glass and Lorenz chaotic time series predictions, where the NSFLSs' inputs have been perturbed with different levels of Gaussian noise. Experiments are repeated for system training under noisy and noise-free conditions. Analyses of the results show that the new method outperforms the traditional approach. Moreover, it is shown that while formally more complex, in practice, the new method has no significant computational overhead compared to the standard approach.

“…Particularly there are a few research works on using varieties of moving average method within the development of predictive models by fuzzy logic 1 By definition, the core or the kernel of a fuzzy set is the set of all values where their membership grade is 1, i.e. the 1-cut of the fuzzy set [17].…”

Section: Background and Motivationmentioning

confidence: 99%

“…The applied techniques are ranging from type-1 to type-2 FLSs, and from singleton to nonsingleton FLS configurations (as shown, for example, in [1]- [7] ). Non-singleton fuzzification is one of the known approaches to provide a capacity for noise/uncertainty handling in FLSs used for such purposes.…”

Section: Introductionmentioning

confidence: 99%

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

2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

John

Garibaldi

2017

A note on versions:The version presented here may differ from the published version or from the version of record. If you wish to cite this item you are advised to consult the publisher's version. Please see the repository url above for details on accessing the published version and note that access may require a subscription.For more information, please contact eprints@nottingham.ac.uk 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.