Studia Informatica


Volume: 1(7)
Year: 2006
Publishing: Publishing House of University of Podlasie
Scientific Editor: Andrzej Wisniewski
ISSN: 1731-2264

Contents

Bijak K.,
Estimation, Decoding and Forecasting in HMM and Hybrid HMM/ANN Models: a Case of Seismic Events in Poland
pp. 7-17
Abstract: This paper compares performance of a hidden Markov model (HMM) and a hybrid HMM/ANN model in seismic events modeling. Observation variables are assumed to follow a Poisson distribution. Parameters of the discrete-time two-state models are estimated on the basis of data on seismic events that were recorded in Poland from 1991 to 1995. Then, on the basis of the estimation results, the most likely sequences of states of the hidden Markov chains are found and forecasts for January 1996 are made. It is shown that the hybrid model fits better to the data.
Download PDF file
Blachnik M., Duch W., Wieczorek T.,
Heterogeneous distance functions for prototype rules: influence of parameters on probability estimation.
pp. 19-30
Abstract: An interesting and little explored way to understand data is based on prototype rules (P-rules). The goal of this approach is to find optimal similarity (or distance) functions and position of prototypes to which unknown vectors are compared. In real applications similarity functions frequently involve different types of attributes, such as continuous, discrete, binary or nominal. Heterogeneous distance functions that may handle such diverse information are usually based on probability distance measure, such as the Value Difference Metrics (VDM). For continuous attributes calculation of probabilities requires estimations of probability density functions. This process requires careful selection of several parameters that may have important impact on the overall classification of accuracy. In this paper, various heterogeneous distance function based on VDM measure are presented, among them some new heterogeneous distance functions based on different types of probability estimation. Results of many numerical experiments with such distance functions are presented on artificial and real datasets, and quite simple P-rules for several heterogeneous databases extracted.
Download PDF file
Drabowski M., Czajkowski K.,
The Tabu Search approach in coherent co-synthesis of multiprocessors systems
pp. 31-45
Abstract: This paper presents the use of Tabu Search algorithm for solving the problems of coherent synthesis of multiprocessor computer systems. The paper includes a coherent solution of both optimization of partition resources and optimization of tasks scheduling. This publication shows results of computational experiments for different instances of system synthesis problems.
Download PDF file
Kłopotek M.,
Cyclic Bayesian Network – Markov Process Approach
pp. 47-55
Abstract: The paper proposes a new interpretation of the concept of cyclic Bayesian Networks, based on stationary Markov processes over feature vector state transitions.
Download PDF file
Kłopotek M., Rucinski D., Tchórzewski J.,
Dealing with Non-Convexity in Geographic Routing in Smart Dust Networks
pp. 57-64
Abstract: The paper proposes a new approach to greedy geographic routing for sensor networks with non-convex covering structure.
Download PDF file
Kłopotek M., Wierzchoń S., Ciesielski K., Kujawiak M., Dramiński M., Czerski D.,
Map Quality Measurements for GNG and SOM based Document Collection Maps
pp. 65-76
Abstract: The paper presents a proposal of a set of measures for comparison of maps of document collections as well as preliminary results concerning evaluation of their usefulness and expressive power.
Download PDF file
Pilski M., Seredynski F.,
Function optimization using metaheuristics
pp. 77-91
Abstract: The paper presents the results of comparison of three metaheuristics that currently exist in the problem of function optimization. The first algorithm is Particle Swarm Optimization (PSO) - the algorithm has recently emerged. The next one is based on a paradigm of Artificial Immune System (AIS). Both algorithms are compared with Genetic Algorithm (GA). The algorithms are applied to optimize a set of functions well known in the area of evolutionary computation. Experimental results show that it is difficult to unambiguously select one best algorithm which outperforms other tested metaheuristics.
Download PDF file
Podraza R., Dominik A.,
Credibility Coefficients for Objects of Rough Sets
pp. 93-104
Abstract: In this paper focus is set on data reliability. We propose a few methods, which calculate credibility coefficients for objects stored in decision tables. Credibility coefficient of object is a measure of its similarity with respect to the rest of the objects in the considered decision table. It can be very useful in detecting either corrupted data or abnormal and distinctive situations. It is assumed that the proper data appear in majority and can be separated from improper data by exploring mutual resemblance. The proposed methods take advantage of well known and widely used data mining technique - rough sets.
Download PDF file
Przybylski M., Cichocki P.,
Innovative Realization of Quantitative Goals in BDI Agents via Partial Utility Functions
pp. 105-116
Abstract: Agents play an important role in high level artificial intelligence in such areas as distributed decision support, robot control, computer games, etc. Currently, the most popular high-level agent architectures are based on the belief-desire-intention (BDI) model. BDI agents are usually specified in modal logic. This is efficient for defining event goals. However, defining quantitative goals can be very difficult in many popular formalisms. In this paper we propose a method for expressing quantitative goals by associating partial utility functions with agent’s goals. We propose a modified BDI agent architecture which is loosely based on fuzzy logic. In this architecture, approximation of partial derivatives of those functions enables us to use gradient based optimization algorithms in the intention reconsideration step to weight some action specializations. Using the proposed approach allows us to easily combine quantitative and event goals, and consider them all while planning. This paper also describes a simple language which can be used to elegantly describe generic action libraries in accordance to the proposed model.
Download PDF file
Rzecki K., Riegel M.,
Mailing Lists Archives Analyzer
pp. 117-125
Abstract: Article describes chance to explore data hidden in headers of e-mails taken from archive of mailing lists. Scientist part of the article presents a way of transforms information enclosed in Internet resources, explains idea of mailing lists archive and points out knowledge can be taken from. Technical part presents implemented and working system analyzing headers of e-mail messages stored in mailing lists archives. Some example results of this experiment are also given.
Download PDF file
Suchenek M. A.,
On Undecidability of Non-monotonic Logic
pp. 127-132
Abstract: The degree of undecidability of nonmonotonic logic is investigated. A proof is provided that arithmetical but not recursively enumerable sets of sentences definable by nonmonotonic default logic are elements of Dn+1 but not Sn nor Pn for some n>= 1 in Kleene-Mostowski hierarchy of arithmetical sets.
Download PDF file
Tchórzewski J., Rucinski A.,
Model and Implementation Of System Evolving Algorithm with Distributed Beginning Population
pp. 133-146
Abstract: This paper shows some results of using artificial intelligence methods for searching the new state of development system of electro energetic transmission network. In particular, is using evolving algorithm. Some experiments are prepared in MATLAB and Simulink environment.
Download PDF file
Trojanowski K., Grzegorzewski M.,
A Look Inside The Artificial Immune Algorithm Inspired by Clonal Selection Principle
pp. 147-160
Abstract: Artificial Immune Systems inspired by clonal selection principle (called clonal selection algorithms) have already been successfully applied to pattern recognition tasks. In this paper we present our implementation of one of them, called CLONCLAS, and discuss its behavior in application to recognition of a set of binary patterns. The algorithm performs process of learning based on a set of training data including patterns which belong to ten previously unknown classes and finally generates a group of classifiers which are able to assign the testing input patterns to appropriate classes. Our experiments were performed for a set of commonly known similarity measures of binary strings to select the most efficient of them. We also observed a phenomenon of transformation of memory contents in subsequent phases of iterated process of the system learning.
Download PDF file
Vetulani Z.,
Tradition and New Challenges for the HLT Community
pp. 161-177
Abstract: The domain of Human Language Technologies is a fascinating and challenging area of research and development. We introduce the reader into this domain, present its tradition and recent challenges.
Download PDF file
Walczak R.,
Expert system on efficiency evaluation of continuous flow grain dryer
pp. 179-193
Abstract: The purpose of the paper is to present a concept of energy efficiency and financial evaluation of counterflow dryer. Energy efficiency and many other efficiency indexes of the dryer and all additional devices like heater, heat exchangers, tubing and fans are calculated. Expert system provides also the financial evaluation of the investment. Many investments could be considered. The system provides the user with suggestions about the best dryer for him/her. Expert system also enables evaluation of energy saving improvements. The energy savings for dryer installation sections are calculated. Cost savings are compared with investment value. The best energy saving project could be selected on the base of selection algorithm. Expert system could be used for existing and new-designed dryers.
Download PDF file
Wasielewska K., Bagiński M.,
LCS and GP Approaches to Multiplexer’s Problem
pp. 195-206
Abstract: In this paper we present the use of learning classifier systems and genetic programming to solving multiplexer’s problem. The function of multiplexer is the popular apparatus of researches which is used to investigate the effectiveness of systems based on evolutionary algorithms. It turns out that the eXtended Classifier System (XCS) learns the problem of multiplexer effectively and Genetic Programming (GP) finds the form of function of multiplexer correctly.
Download PDF file
Wisniewski A.,
On mapping onto self-organized criticality
pp. 207-216
Abstract: In the report we have discussed a few aspects of SOC concept which in general have strongly influence on explicitness of mapping process. SOC idea is based on group of models and/does not seem to give quite clear instructions whether mapped phenomena exhibit SOC or not. To present the problem we have performed a computer simulation in order to investigate the effect of the critical point within the system evolution process without conservation. We have considered that on two-dimensional cellular automata whose rule consists of one or two subrules. The first one, based on Conway’s model (or very similar to), has represented the local behavior of transmission processes and has been applied in the experiment synchronously, as a fundamental mode. The second one, called a transport rule, has been applied sequentially. That subrule has described the motion of a fraction of individuals. As a result of comparing models of the various sets of rules for the applied size of lattice, we could find that the modified Conway’s model would be merely treated as subcritical.
Download PDF file
Zhan J., Matwin S., Chang L.,
A Multi-Party Scheme for Privacy-Preserving Clustering
pp. 217-232
Abstract: Preserving data privacy while conducting data clustering among multiple parties is a demanding problem. We address this challenging problem in the following scenario: without disclosing their private data to each other, multiple parties, each having a private data set, want to collaboratively conduct k-medoids clustering. To tackle this problem, we develop secure protocols for multiple parties to achieve this dual goal. The solution is distributed, i.e., there is no central, trusted party having access to all the data. Instead, we define a protocol using homomorphic encryption and digital envelope techniques to exchange the data while keeping it private.
Download PDF file
Zhan J., Chang L., Matwin S.,
How To Construct Support Vector Machines Without Breaching Privacy
pp. 233-244
Abstract: This paper addresses the problem of data sharing among multiple parties in the following scenario: without disclosing their private data to each other, multiple parties, each having a private data set, want to collaboratively construct support vector machines using a linear, polynomial or sigmoid kernel function. To tackle this problem, we develop a secure protocol for multiple parties to conduct the desired computation. In our solution, multiple parties use homomorphic encryption and digital envelope techniques to exchange the data while keeping it private. All the parties are treated symmetrically: they all participate in the encryption and in the computation involved in learning support vector machines.
Download PDF file
Novikow S.,
Method of Logical Synthesis of Integrated Circuits in basis K-PLA
pp. 247-253
Abstract: Modern Computer-Aided Design systems of Very Large Scale Integration allow to use the chips with thousands of components as element's modules of electronic circuits. For example, ULSI - chip has complexity more than 20000 transistors. One of perspective chips (Programmable Logic Chip) has the architecture of a Programmable Logic Array (PLA). PLA can be programmed in a laboratory to perform complex functions with the help of a special equipment called by programmer (similar as PROM blower).
Download PDF file
Timofeev A. O.,
Basic solutions for a program system for dynamic systems simulation
pp. 255-263
Abstract: The article presents basic solutions of the Amethyst program system. The system generates interactive applications for simulating complex dynamic systems. The method of presenting the information about the state of the simulated objects and method of calculating the component state are proposed. Method of decentralized processing the signal delays and filtering is discussed. Method of analog objects simulating is proposed. The article presents examples of projects produced for C++ Builder, Visual C++ and Visual Basic 2005 environment projects. The executable times of simulation are compared for the above mentioned environment applications.
Download PDF file
Wolski M., Stasiak A.,
New features in UML syntax and semantics
pp. 265-276
Abstract: This paper is an overview of the most important new features introduced to version 2.0 of Unified Modeling Language. We denote the changes to existing diagram and present four new modeling techniques. We present the changes in definitions of syntax, semantics and pragmatics of behavioral and static models of systems designed with UML 2.0. Particular emphasis is put on the changes to sequence and activity diagrams and to component diagrams. The newly introduced diagrams, unknown in previous UML versions – interaction overview diagrams, timing diagrams, composite structure diagrams and package diagrams – are described with the most detail.
Download PDF file
Barczak A., Fedorczyk Ł.,
Concept and Implementation of Module of Monitoring Condition of Scattered Computer Resources Security
pp. 279-290
Abstract: In this paper the architecture of system managing security of scattered computer resources is presented.The maine functions of monitoring module are cahracterized, also its model and implementation is presented.
Download PDF file
Barczak A., Mościcki A.,
Efficiency of Technology of Access to Databases
pp. 293-310
Abstract: In this paper the evolution of technologis of access to databases is presented. For definite sysytems of databases’ management (databases servers) and technologis of access, there was made an experiment, enabling to estimate the avarage of time of answering (realizeing), definite types of questions- what means eficiency of each technologis.
Download PDF file