Journal:Informatica
Volume 14, Issue 3 (2003), pp. 337–348
Abstract
In the paper the sequential nonlinear mapping has been investigated in order to reveal its features. The method was investigated by a plenty of experiments using various sorts of data. For illustrations there are presented results using “marginal” data: the first data gives the smallest mapping error, and the other data gives the largest one. The sequential nonlinear mapping has been investigated according ability to differ the data groups (clustering) when at the beginning the number of groups is taken to be less than really exists. It was showed that the sequential nonlinear mapping differs the groups of data well even though the number of them is taken to be less by one than really exists. The experiments show that the factor for correction co‐ordinates on the plane for the sequential nonlinear mapping can be taken in the range from 0.25 to 0.75. Mapping errors depend on both the sort of initial conditions and the nature of data.
Journal:Informatica
Volume 14, Issue 3 (2003), pp. 323–336
Abstract
This paper analyses coupled control of a nonlinear, time‐varying plant. Uncoupled and coupled direct adaptive controllers, based on fuzzy logics, are synthesized to control the water level and the air pressure in a closed tank. The satisfactory efficiency of the controllers is experimentally demonstrated running the plant under the different working conditions. Coupled fuzzy controllers are compared with the uncoupled fuzzy controllers.
Journal:Informatica
Volume 14, Issue 3 (2003), pp. 295–322
Abstract
This paper considers an information aspect of the problem of the joint filtering and generalized extrapolation, when the output of observation channels (data transmission) is the realizations set of the processes with continuous and discrete time, which depend on both the current and the past values of unobservable process (useful signal). The relations defining time evolution of Shannon information are obtained. The particular problems of the memory channels information efficiency and optimal transmission of stochastic processes, with applying the general results are considered.
Journal:Informatica
Volume 14, Issue 3 (2003), pp. 289–294
Abstract
Smart card has been adopted to various applications. In 2000, Hwang and Li proposed a remote user authentication scheme, which is also using smart card. Nine months later, Chan and Cheng pointed out that there is a weakness in the remote authentication scheme proposed by Hwang and Li. In this paper, we show that Chan and Cheng's attack does not work well because they did not consider the format of user's identity. In addition, we propose several ways to solve the problem of Chan and Cheng's attack.
Journal:Informatica
Volume 14, Issue 3 (2003), pp. 277–288
Abstract
In the paper, we present an algorithm that can be applied to protect data before a data mining process takes place. The data mining, a part of the knowledge discovery process, is mainly about building models from data. We address the following question: can we protect the data and still allow the data modelling process to take place? We consider the case where the distributions of original data values are preserved while the values themselves change, so that the resulting model is equivalent to the one built with original data. The presented formal approach is especially useful when the knowledge discovery process is outsourced. The application of the algorithm is demonstrated through an example.
Journal:Informatica
Volume 14, Issue 2 (2003), pp. 259–272
Abstract
This paper considers the main positions of one‐sided and two‐sided problems. For one‐sided problems only the method of solution “the distance to the ideal point” is discussed in the actual version. For two‐sided problems a distinction is made between games with rational behaviour and games against nature. The main strategic principles are as follows: simple min‐max principle, extended min‐max principle, Wald's rule, Savage criterion, Hurwicz's rule, Laplace's rule, Bayes's rule, Hodges‐Lehmann rule. Questions of transforming the decision‐making matrix are considered. The article gives the description of a software as well as an example of an investment variant estimation.
Journal:Informatica
Volume 14, Issue 2 (2003), pp. 251–258
Abstract
This paper investigates a class of sharp integral means inequalities involving fractional calculus operators of certain analytic functions with negative coefficients. Some consequences of the main result are also mentioned.
Journal:Informatica
Volume 14, Issue 2 (2003), pp. 237–250
Abstract
Reinforcement learning addresses the question of how an autonomous agent can learn to choose optimal actions to achieve its goals. Efficient exploration is of fundamental importance for autonomous agents that learn to act. Previous approaches to exploration in reinforcement learning usually address exploration in the case when the environment is fully observable. In contrast, we study the case when the environment is only partially observable. We consider different exploration techniques applied to the learning algorithm “Utile Suffix Memory”, and, in addition, discuss an adaptive fringe depth. Experimental results in a partially observable maze show that exploration techniques have serious impact on performance of learning algorithm.
Journal:Informatica
Volume 14, Issue 2 (2003), pp. 223–236
Abstract
A quick gradient training algorithm for a specific neural network structure called an extra reduced size lattice‐ladder multilayer perceptron is introduced. Presented derivation of the algorithm utilizes recently found by author simplest way of exact computation of gradients for rotation parameters of lattice‐ladder filter. Developed neural network training algorithm is optimal in terms of minimal number of constants, multiplication and addition operations, while the regularity of the structure is also preserved.
Journal:Informatica
Volume 14, Issue 2 (2003), pp. 213–222
Abstract
This paper discusses the linear periodically time‐varying (LPTV) system parameter estimation using a block approach. An block algorithm is proposed for optimal estimation of the parameters of LPTV system from the input sequence and the output sequence corrupted by additive Gaussianly distributed noise. In the proposed method, the least squares error criterion has been used.The algorithm provides a useful computational tool based on an appropriate theoretical foundation for parameter estimation of linear time‐invariant (LTI) systems from input and output data. Simulation results are presented that demonstrate the performance of the approach.