Péter Várlaki

Stability of interpolative fuzzy KH controllers

The classical approaches in fuzzy control (Zadeh and Mamdani) deal with dense rule bases. When this is not the case, i.e. in sparse rule bases, one has to choose another method. Fuzzy rule interpolation [proposed first by Koczy and Hirota, Internat. J. Approx. Reason. 9 (1993) 197-225] offers a possibility to construct fuzzy controllers (KH controllers) under such conditions. The main result of this paper shows that the KH interpolation method is stable. It also contributes to the application oriented use of Balazs-Shepard interpolation operators investigated extensively by researchers in approximation theory. The numerical analysis aspect of the result contributes to the well-known problem of finding a stable interpolation method in the following sense. We would like to approximate a function that is only known at distinct points (e.g. where it can be measured). Since measurement errors cannot be eliminated in practice, it is a natural requirement that the interpolation method should be stable independently from the selection of measurement points. The classical interpolation methods generally do not fulfil this condition, only with certain strong restrictions concerning the measurement points. If we neglect the classical form of the approximating function (polynomial and trigonometrical), we can produce better behaving approximation. The KH controller approximating function, being a simple fractional function, fulfils the stability condition. This can also be interpreted as KH controllers are universal approximators in the space of continuous functions (with respect to, e.g., the supremum norm).

An overview of research trends in CogInfoCom

Cognitive infocommunications (CogInfoCom) is an interdisciplinary field that targets engineering applications based on emergent synergies between ICT and the cognitive sciences. The unique perspective of CogInfoCom enables researchers to focus on both the qualitative and quantitative analysis of cognitive capabilities in application areas where humans are becoming increasingly entangled with and dependent on intelligent networked services. An international conference on the field has been held every year since 2010, and the two most recent events have been supported by the IEEE. In this paper, we provide an overview of the various research directions which have been represented at the conference series, and which have as a result gained strong relevance to CogInfoCom during the past few years.

3D model estimation from multiple images

3D reconstruction plays a very important role in computer vision. The determination of the 3D model from multiple images is of key importance. A 3D reconstruction algorithm is introduced, which is capable to determine the 3D model without any external intervention.

TP model transformation in non-linear system control

The main objective of the paper is to study the recently proposed tensor product distributed compensation (TPDC) based design framework in the case of observer and controller design. The TPDC links the TP model transformation and the parallel distributed compensation (PDC) framework. The study is conducted trough the output feedback control design of the prototypical aeroelastic wing section that is used for the theoretical as well as experimental analysis of two-dimensional aeroelastic behavior and exhibits limit cycle oscillation without control effort. The control strategy is based on a state feedback controller and an observer to estimate the available state values.

An improved index of interactivity for fuzzy numbers

In this paper we will introduce a new index of interactivity between marginal possibility distributions A and B of a joint possibility distribution C. The starting point of our approach is to equip each @c-level set of C with a uniform probability distribution, then the probabilistic correlation coefficient between its marginal probability distributions is interpreted as an index of interactivity between the @c-level sets of A and B. Then we define the index of interactivity between A and B as the weighted average of these indexes over the set of all membership grades. This new index of interactivity is meaningful for the whole family of joint possibility distributions.

Stability of interpolative fuzzy KH-controllers

The classical approaches in fuzzy control (Zadeh and Mamdani) deal with dense rule bases. When this is not the case, i.e. in sparse rule bases one has to choose another method. Fuzzy rule interpolation (proposed first by Koczy and Hirota, 1993, 1996) offers a possibility to construct fuzzy controllers (KH-controllers) under such conditions. On the other hand there is a great demand in finding a stable interpolating method among researchers in the field of mathematical (numerical) analysis. We would like to approximate a function that is only known at distinct points (e.g. where it can be measured). In practice the stability of these method is a natural requirement. The classical methods generally do not fulfill this condition, only with some strong restriction concerning the measured points. If we neglect the classical form of the approximating function (polynomial and trigonometrical), we can get better behaving approximation. The function of the KH-controller approximating function (which is a simple fractional function) fulfills the stability condition.

“System identification” and hermeneutics for long run series of synchronicities in the Pauli-Jung relationship

The paper discusses some characteristic symbolic patterns which can be identified in the long run series of synchronicities in the Pauli-Jung cooperation concerning the long run dream series of Pauli. We try to show the paradigm of the modern system and control theory in the typical identifiable structures and symbolic patterns of dreams and synchronistic phenomena using the contemporary and old approaches of Hermeneutics.

On tensor-product model based representation of neural networks

The approximation methods of mathematics are widely used in theory and practice for several problems. In the framework of the paper a novel tensor-product based approach for representation of neural networks (NNs) is proposed. The NNs in this case stand for local models based on which a more complex parameter varying model can numerically be reconstructed and reduced using the higher order singular value decomposition (HOSVD). The HOSVD as well as the tensor-product based representation of NNs will be discussed in detail.

HOSVD Based Method for Surface Data Approximation and Compression

The main aim of this paper is to introduce a method for approximating surfaces given by a set of discrete points with possible additional parameters. The method uses the higher order singular value decomposition based on canonical form of two-variable TP (tensor product) functions. Except of approximation abilities of this principle, the paper focuses on the compression properties of the method, as well. The method is able to achieve high compression rate in the input data by keeping the error at remarkable lower level.

Dynamic Modelling Of Commercial Road Vehicle Structures From Test Data

The paper discusses the identification of multivariable models for air suspension bus structures using the measured stress response arising from stochastic road profile excitation. The vehicle and noise transfer matrices are identified from the time history of measured data. Applying a special parametrization of the transfer matrices, the modal characteristics can also be directly computed. Models were identified at various selected road categories, road profile variances and speed levels, thus the random vibration analysis of the vehicle can be performed for the whole range of operation. The identified models can be used to determine the global dynamic characteristics of the vehicle for arbitrary road profile excitations and speed levels within the examined range.