Computer Science Journal (AGH University of Science and Technology, Krakow)
Not a member yet
476 research outputs found
Sort by
Evolutionary Multi-Agent Systems in Non-Stationary Environments
Get PDFIn the article the performance of an evolutionary multi-agent system in dynamic optimization is evaluated in comparison to classical evolutionary algorithms. The starting point is a general introduction describing the background, structure and behaviour of EMAS against classical evolutionary techniques. Then the properties of energy-based selection are investigated to show how it may influence the diversity of the population in EMAS. The considerations are illustrated by experimental results based on the dynamic version of the well-known, high-dimensional Rastrigin function benchmark
HARDWARE AND SOFTWARE ARCHITECTURES FOR RECONFIGURABLE TIME-CRITICAL CONTROL TASKS
Get PDFThe most popular configuration of the controlled laboratory test-rigs is the personalcomputer (PC) equipped with the I/O board. The dedicated software components allowsto conduct a wide range of user-defined tasks. The typical configuration functionality canbe customized by PC hardware components and their programmable reconfiguration. Thenext step in the automatic control system design is the embedded solution. Usually, thedesign process of the embedded control system is supported by the high-level software. Thededicated programming tools support multitasking property of the microcontroller by selectionof different sampling frequencies of algorithm blocks. In this case the multi-layer andmultitasking control strategy can be realized on the chip. The proposed solutions implementrapid prototyping approach. The available toolkits and device drivers integrate system-leveldesign environment and the real-time application software, transferring the functionality ofMATLAB/Simulink programs to PCs or microcontrolers application environment
INTEGRATION PLATFORM AS CENTRAL SERVICE OF DATA REPLICATION IN DISTRIBUTED MEDICAL SYSTEM
Get PDFThe paper presents the application of Java Integration Platform (JIP) to data replicationin the distributed medical system. After an introductory part on the medical system’s architecture,the focus shifts to a comparison of different approaches that exist with regard totransferring data between the system’s components. A description is given of the historicaldata processing and of the whole area of the JIP application to the medical system
POLISH PHONEME STATISTICS OBTAINED ON LARGE SET OF WRITTEN TEXTS
Get PDFThe phonetical statistics were collected from several Polish corpora. The paper is a summaryof the data which are phoneme n-grams and some phenomena in the statistics. Triphonestatistics apply context-dependent speech units which have an important role in speech recognitionsystems and were never calculated for a large set of Polish written texts. The standardphonetic alphabet for Polish, SAMPA, and methods of providing phonetic transcriptions are described
OPTIMIZATION OF SIMULATION MODEL PARAMETERS FOR SOLIDIFICATION OF METALS WITH USE OF AGENT-BASED EVOLUTIONARY ALGORITHM
Get PDFThe finite elements method (FEM) is currently widely used for simulation of thermal processes.However, one of still unresolved problems remains proper selection of mathematicalmodel parameters for these processes. As far as modelling of cooling casts in forms is concerned,particular difficulties appear while estimating values of numerous coefficients suchas: heat transport coefficient between metal and form, specific heat, metal and form heatconduction coefficient, metal and form density. Coefficients mentioned above depend not onlyon materials properties but also on temperature. In the paper the idea of optimalizationof simulation method parameters based on adaptive adjustment of curve representing simulationresult and result obtained in physical experiment is presented along with the ideaof evolutionary and agent-based evolutionary optimization system designed to conduct suchoptimizations. Preliminary results obtained with use of ABAQUS system available in ACKCYFRONET and software developed at AGH-UST conclude the paper
On Evolution of Migrating Population with Two Competing Species
No full textComputer experiment study of population evolution and its dynamics is presented for two competing species A and B which share two habitats (1 and 2) of limited environmental capacity. The Penna model of biological aging, based on concept of defective mutation accumulation was adopted for migrating population. In this paper we assume and concentrate on the case when only one species A is mobile. For isolated habitats and for any initial population, we get at equilibrium spatial population distribution (A, B) between the two locations - A occupies location 1 while B-species is present in 2. The effect of migration between habitats is reported for some migration scenarios. With increasing migration we get a sequence (A, B) -> (A, A&B) -> (A, A) -> (B, B) distribution. Another scenarios bring different sequences of population distribution, size and characteristics
h-RELATION PERSONALIZED COMMUNICATION STRATEGY
Get PDFThis paper considers the communication patterns arising from the partition of geometricaldomain into sub-domains, when data is exchanged between processors assigned to adjacentsub-domains. It presents the algorithm constructing bipartite graphs covering the graphrepresentation of the partitioned domain, as well as the scheduling algorithm utilizing thecoloring of the bipartite graphs. Specifically, when the communication pattern arises from thepartition of a 2D geometric area, the planar graph representation of the domain is partitionedinto not more than two bipartite graphs and a third graph with maximum vertex valency 2,by means of the presented algorithm. In the general case, the algorithm finds h−1 or fewerbipartite graphs, where h is the maximum number of neighbors. Finally, the task of messagescheduling is reduced to a set of independent scheduling problems over the bipartite graphs.The algorithms are supported by a theoretical discussion on their correctness and efficiency
Comparison of two kinds of fuzzy arithmetic, LR and OFN, applied to fuzzy observation of the cofferdam water level
Get PDFThis paper presents certain important aspects of the fuzzy logic extension, one of which is OFN. It includes basic definitions of that discipline. It also compares fuzzy logic arithmetic with the arithmetic of ordered fuzzy numbers in L-R notation. Computational experiments were based on fuzzy observation of the impounding basin. The results of the study show that there is a connection between the order of OFN number and trend of changes in the environment. The experiment was carried out using computer software developed specially for that purpose. When comparing the arithmetic of fuzzy numbers in L-R notation with the arithmetic of ordered fuzzy numbers on the grounds of the experiment, it has been concluded that with fuzzy numbers it is possible to expand the scope of solutions in comparison to fuzzy numbers in classic form. The symbol of OFN flexibility is the possibility to determine the X number that always satisfies the equation A+X=C, regardless of the value of arguments. Operations performed on OFN are less complicated, as they are performed in the same way regardless the sign of the input data and their results are more accurate in the majority of cases. The promising feature of ordered fuzzy numbers is their lack of rapidly growing fuzziness. Authors expect to see implication of that fact in practice in the near future
UNSUPERVISED LABELING OF DATA FOR SUPERVISED LEARNING AND ITS APPLICATION TO MEDICAL CLAIMS PREDICTION
Get PDFThe task identifying changes and irregularities in medical insurance claim pay-ments is a difficult process of which the traditional practice involves queryinghistorical claims databases and flagging potential claims as normal or abnor-mal. Because what is considered as normal payment is usually unknown andmay change over time, abnormal payments often pass undetected; only to bediscovered when the payment period has passed.This paper presents the problem of on-line unsupervised learning from datastreams when the distribution that generates the data changes or drifts overtime. Automated algorithms for detecting drifting concepts in a probabilitydistribution of the data are presented. The idea behind the presented driftdetection methods is to transform the distribution of the data within a slidingwindow into a more convenient distribution. Then, a test statistics p-value ata given significance level can be used to infer the drift rate, adjust the windowsize and decide on the status of the drift. The detected concepts drifts areused to label the data, for subsequent learning of classification models by asupervised learner. The algorithms were tested on several synthetic and realmedical claims data sets
APPLICATION OF WATERLOO MAPLE 9.5 AND WOLFRAM MATHEMATICA 5.1 SOFTWARE FOR ANALYTIC SOLVING OF CERTAIN NONLINEAR PARTIAL DIFFERENTIAL EQUATIONS OF PHYSICS
Get PDFIn the current paper some applications of the packet MAPLE (v. 9.5) for analytic solving ofcertain nonline partial differential equations have been presented. Additionally, for graphicpresentation of the found solutions packet MATHEMATICA (v. 5.1) has been applied