A Feedback Transformation of the Planning Problems

This paper proposes a problem transformation method, called feedback transformation method, for solving the planning problems. Some basic notions from the theory of problem transformation are introduced. Two measures of problem complexity are defined. Algebraic properties of the feedback transformation are investigated. Finally, a partial relationship between the problem transformation and decomposition methods is established. Received: January 21, 1994; revised version: May 25, 1998     

Immobilization of hospital waste incineration ashes in glass-ceramic composites

In the paper process of sintering of hospital incineration ash as a counterpart of low-level active waste with borosilicate glass frit is presented. It is shown that low porosity glass-ceramic waste-form can be obtained at a temperature range of 850–900 °C. In the sinter, the main crystal phases are wollastonite and aegirine-augite pyroxenes which have a large isomorphous capacity of binding hazardous elements. The crystal phases are fully encapsulated by the glass that provides additional protection against environmental influence. Thus, multibarrier material can be obtained at a temperature considerably lower than vitrification. This, in turn, can improve the economics of immobilization process.     

Ensemble Online Classifier Based on the One-Class Base Classifiers for Mining Data Streams

The problem addressed in this study concerns mining data streams with concept drift. The goal of the article is to propose and validate a new approach to mining data streams with concept-drift using the ensemble classifier constructed from the one-class base classifiers. It is assumed that base classifiers of the proposed ensemble are induced from incoming chunks of the data stream. Each chunk consists of prototypes and information about whether the class prediction of these instances, carried-out at earlier steps, has been correct. Each data chunk can be updated by using the instance selection technique when new data arrive. When a new data chunk is formed, the ensemble model is also updated on the basis of weights assigned to each one-class classifier. In this article, two well-known instance-based learning algorithms—the CNN and the ENN—have been adopted to solve the one-class classification problems and, consequently, update the proposed classifier ensemble. The proposed approaches have been validated experimentally, and the computational experiment results are shown and discussed. The experiment results prove that the proposed approach using the ensemble classifier constructed from the one-class base classifiers with instance selection for chunk updating can outperform well-known approaches for data streams with concept drift.     

Improved dynamic routing algorithms in elastic optical networks

The considered Routing, Modulation Level and Spectrum Allocation (RMLSA) problem covers path length minimization while still meeting the spectrum continuity constraints, non-overlapping spectra constraints, spectrum contiguity constraints, and choice of modulation level. In this problem, the relationship between spectrum connection and bit rate of the incoming request has been taken into account. In this paper, two algorithms have been proposed. The first one is based on a set of shortest paths whose lengths are determined by the number of links in the network. The second one is a modified version of Dijkstra’s algorithm. Modification of this algorithm is based on introduction of weights of the network links depending on the utilization of the links and the introduction of a aggregated spectrum of the path that is being selected. Extensive research has shown that algorithms reject the lower traffic volume as compared to well-known algorithms proposed in literature.     

Designing RBF Networks Using the Agent-Based Population Learning Algorithm

Radial Basis Function Neural Networks (RBFNs) are nowadays quite popular due to their ability to discover and approximate complex nonlinear dependencies within the data under analysis. Performance of the RBF network depends on numerous factors related to its initialization and training. The paper proposes an approach to the radial basis function networks design, where initial parameters of the network, output weights and parameters of the transfer function are set using the proposed agent-based population learning algorithm (PLA). The algorithm is validated experimentally. Advantages and main features of the PLA-based RBF designs are discussed basing on results of the computational experiment.     

Biofilm formation by lactobacilli and resistance to stress treatments

We investigated biofilm formation by six lactobacilli isolates and tested the resistance of biofilm and planktonic Lactobacillus plantarum B1 and Lactobacillus paracasei W1 to ethanol (ET) and acetic acid (AA). The viability of both isolates was considerably affected by ET, with a higher reduction observed in the planktonic cells, whereas AA was harmful only to L. paracasei W1. Cells that had intact (Syto^® 9⁺PI⁻) and compromised (Syto^® 9⁻PI⁺) membranes, and adopted intermediate states with different concentrations of the probes, i.e., Syto^® 9⁺PI⁺ and Syto^® 9⁻PI⁻, were identified following flow cytometry. We linked Syto^® 9⁺PI⁺ to the planktonic cells and clarified on Syto^® 9⁻PI⁻ cells, which after being sorted could regain growth better in biofilm cells. Based on confocal laser scanning microscopy, numerous cells had damaged membranes in the ET-treated biofilm, while half the cells in the AA-treated biofilm maintained their membrane integrity.     

Magnetic and magnetoelectric properties of nickel ferrite–lead iron niobate relaxor composites

Magnetoelectric effect in bulk ceramic and multilayer (laminated) structures consisting of 6 nickel ferrite and 7 lead iron niobate relaxor (PFN) layers was investigated. This paper describes the synthesis and tape-casting process for ferrimagnetic Ni_0.3Zn_0.62Cu_0.08Fe₂O₄ ferrite and multiferroic relaxor Pb(Fe_0.5Nb_0.5)O₃. X-ray analysis and studies of the electrical and magnetic properties were performed for bulk and layered composites. Complex impedance and dielectric permittivity of bulk and layered composites were studied in a temperature range from ?40 to 300 °C and a frequency range of 10 Hz to 2 MHz. Magnetic hysteresis, ZFC–FC curves and dependencies of magnetization versus temperature for nickel ferrite, PFN relaxor and magnetoelectric composites were measured with a vibrating sample magnetometer (VSM) in an applied magnetic field up to 85 kOe at ?269 °C. Magnetoelectric effect at room temperature was investigated as a function of static magnetic field (0.3–6.5 kOe).     

AGENT-BASED APPROACH TO THE DESIGN OF RBF NETWORKS

This article proposes a novel approach to the radial basis function network (RBFN) design. Its main idea is to apply the agent-based population learning algorithm to the task of initialization and training RBFNs. The approach allows for an effective network initialization and estimation of its output weights. The initialization involves two stages, where in the first one initial clusters are produced using the similarity-based procedure and next, in the second stage, prototypes (centroids) from the thus-obtained clusters are selected. The agent-based population learning algorithm is used to select prototypes. In the proposed implementation of the algorithm, both tasks—RBFN initialization and RBFN training—are carried out by a team of agents executing various local search procedures and cooperating with a view to determine the solution to the RBFN design problem at hand. The performance of the RBFN constructed using the proposed agent-based approach is analyzed and evaluated. The proposed approach is also compared with different RBFN initialization and training procedures in the literature.