Wyniki wyszukiwania - BazTech

1

Data irregularities in discretisation of test sets used for evaluation of classification systems: A case study on authorship attribution

Stańczyk Urszula, Zielosko Beata

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2021

|

Vol. 69, nr 4

art. no. e137629

EN

When patterns to be recognised are described by features of continuous type, discretisation becomes either an optional or necessary step in the initial data pre-processing stage. Characteristics of data, distribution of data points in the input space, can significantly influence the process of transformation from real-valued into nominal attributes, and the resulting performance of classification systems employing them. If data include several separate sets, their discretisation becomes more complex, as varying numbers of intervals and different ranges can be constructed for the same variables. The paper presents research on irregularities in data distribution, observed in the context of discretisation processes. Selected discretisation methods were used and their effect on the performance of decision algorithms, induced in classical rough set approach, was investigated. The studied input space was defined by measurable style-markers, which, exploited as characteristic features, facilitate treating a task of stylometric authorship attribution as classification.

2

The domination over time and its discretisation

Abbasnezhad Nazanin, Mehri-Takmeh Javad, Vakili Javad

Operations Research and Decisions

|

2020

|

Vol. 30, No. 1

5--24

EN

Domination in graphs is well known and has been an extensively researched branch of graph theory. Since the variation over time is one of the important properties of real-world networks, we study the influence of time on the domination problem. In this paper, we introduce the domination over time problem, including time delay on arcs. Then, an optimal solution to its discretisation is obtained, which is the solution of the original problem.

3

Wykorzystanie inżynierii odwrotnej w procesie odbudowy elementów przekładni ślimakowej

Skoczylas L., Wydrzyński D., Bełzo A., Lenar A.

Przegląd Mechaniczny

|

2018

|

nr 11

37--41

PL

W artykule przedstawiono ideę inżynierii odwrotnej w kontekście szybkiego prototypowania przy regeneracji przekładni ślimakowej. Istotą problemu jest odtworzenie ślimacznicy, która uległa zniszczeniu. Stopień jej degradacji uniemożliwia pozyskanie podstawowych informacji na temat geometrii ślimaka oraz korpusu przekładni. Wskazane elementy nie nosiły śladów nadmiernego zużycia. W pierwszym etapie przeprowadzono pomiary, omówiono zastosowane metody oraz sposób ich wykorzystania. Zebrane dane pomiarowe posłużyły do obliczenia parametrów uzwojenie ślimaka, a w konsekwencji uzębienia ślimacznicy. Na ich podstawie powstał model CAD. Etap finalny to przygotowanie strategii obróbki za pomocą CAM oraz jej realizacja na obrabiarce CNC. Działania ukierunkowano na szybką odbudowę elementu. Zwrócono również uwagę na zachowanie uzasadnionej relacji kosztów do stawianych wymagań.

EN

The article presents the idea of reverse engineering in the context of rapid prototyping during the regeneration of the worm gear. The nub of the problem is to regenerate the worm-wheel which has been destroyed. The degree of its degradation makes it impossible to obtain the basic datacincerned the toothed-wheel rim. Because of the reasonsmentioned above, this article is focused on the analysis of the worm geometry and the gear casing. No sings of excessive wear werefound on the indicated parts. At the first stage the measurements were carried out, the applied methods were described and the technique of these methods usage were discussed. The collected data was used of calculate the parameters of the worm’s lead and consequently the tooth’s of the worm-wheel. Based on the calculations, the CAD model was created. The final stage is the preparation of a maching strategy with the CAM software usage and its implementation in the process with a CNC machine application. The activities were focused on the quick reconstruction of the part. The attention was also paid to balancethe costs and the requirements set.

4

Wpływ nachylenia eksploatowanego pokładu na prognozowany rozkład obniżeń na powierzchni

Ścigała R., Żyła B.

Wiadomości Górnicze

|

2016

|

R. 67, nr 7-8

423--430

PL

W artykule przedstawiono wpływ dyskretyzacji nachylonego pola eksploatacyjnego na kształt profilu prognozowanej asymptotycznej niecki obniżeniowej. Problem dotyczy sytuacji, kiedy zmienna głębokość elementarnych pól aproksymujących geometrię pola eksploatacyjnego powoduje zaburzenia profilu prognozowanej niecki obniżeniowej. Za pomocą opracowanego w programie Wolfram Mathematica modelu obliczeniowego porównano profile niecek uzyskanych przy założeniu ciągłości pola eksploatacyjnego o stałym nachyleniu oraz niecek uzyskanych przy różnych sposobach podziału tego pola za pomocą dyskretnych elementów złożowych.

EN

The article presents the impact of discretisation of inclined exploitation panel on the shape of profile of predicted asymptotic subsiding trough. The problem concerns the situation when a variable depth of elementary fields approximating the geometry of the exploitation panel causes disturbances of the profile of a projected subsiding trough. Using a computational model developed in the Wolfram Mathematica software profiles of troughs obtained under the assumption of continuity of the exploitation panel with a constant slope and troughs obtained at different ways of dividing of the panel using discrete components of deposit have been compared.

5

Influence of the discretisation net on the accuracy of results in a diagnostic model for wind field adjustment

Brzozowska L.

Journal of Theoretical and Applied Computer Science

|

2013

|

Vol. 7, nr 2

31--44

EN

Computational efficiency of model is a key factor which determines its practical application. The paper presents the algorithms which ensure the computational efficiency of a model of the air velocity field. The main step of modelling the air velocity field by means of the diagnostic model is the procedure of adjusting the initial field. The initial wind field is computed by interpolation of data from meteorological stations. The goal of adjusting the initial field is to ensure that the air velocity field satisfies the continuity equation in an area with a complex landform. The task is reduced to solving the Poisson equation. Finite difference methods with equidistant and non-equidistant nodes are applied. The discretisation net must be properly dense for a complex terrain. For an equidistant net this means that the computing time is extended and a numerical simulation might not be efficient. This problem can be reduced by using a non-equidistant mesh, in which the nodes near the places where we expect a significant change in the air velocity are condensed. In this paper the nonequidistant net is adapted for an example of terrain with an isolated hill. The hybrid approach is proposed in this work. The parabolic function for node distribution is used in the horizontal direction when in the vertical direction the Chebyshev nodes are applied. The results of the numerical analysis show the usefulness of a non-equidistant net in terms of accuracy and computational effectiveness.

6

Symulacje numeryczne drgań zespołu elektrod osadczych

Nowak A., Brzozowski K.

Logistyka

|

2011

|

nr 6

PL

W pracy przedstawiono wyniki symulacji numerycznej drgań układu elektrod osadczych stanowiących fragment sekcji odpylającej w elektrofiltrze suchym. Symulacje przeprowadzono z użyciem modelu numerycznego wykorzystującego metodę hybrydową, stanowiącą połączenie metody sztywnych elementów skończonych oraz metody odkształcalnych elementów skończonych. Szczególną uwagę poświęcono problemowi oceny wpływu przyjętego sposobu dyskretyzacji na wyniki obliczeń. Wykazano stabilność uzyskiwanych wyników w zakresie obliczanych przemieszczeń, prędkości i przyspieszeń po zastosowaniu odpowiednio gęstego podziału elektrod na pojedyncze elementy.

EN

The paper presents some results of numerical analysis of vibrations of collecting electrodes being a part of a dust removal system of electrostatic precipitators. A numerical model is formulated by means of a hybrid method, which combines the finite element method (FEM) and the rigid finite element method (RFEM). In the paper the influence of discretisation on calculation results is discussed. It is shown that stability of velocities and accelerations calculated has been achieved for an appropriate number of elements into which the electrodes have been divided.

7

Type-reduction of the discretised interval type-2 fuzzy set : approaching the continuous case through progressively finer discretisation

Greenfield S., Chiclana F.

Journal of Artificial Intelligence and Soft Computing Research

|

2011

|

Vol. 1, No. 3

183--193

EN

The defuzzification of a type-2 fuzzy set is a two stage process consisting of firstly type-reduction, and secondly defuzzification of the resultant type-1 set. This paper considers three approaches to discrete interval type-reduction: 1. The exhaustive method which produces the Type-Reduced Set, 2. the Greenfield-Chiclana Collapsing Defuzzifier which gives rise to the Representative Embedded Set Approximation, and 3. the Nie-Tan Method from which the Nie-Tan Set is derived. In the discrete case these three type-1 sets are distinct. The behavior of the three sets under fine discretisation is investigated experimentally, in order to shed light on the relationships between the continuous versions of these type-1 sets.

8

The pipe of samples visualization method as base for evolutionary data discretisation

Czerniak J., Dobrosielski W.

Metody Informatyki Stosowanej

|

2010

|

nr 3 (23)

57-67

EN

This article shows the application of the authors’ own method for visualizing multidimensionality, i.e. so called Pipe of Samples, which makes possible to visualize up to 360 dimensions. This approach constituted the base for development of evolutionary discretisation algorithm dedicated for pre-processing of data to be processed using rough sets theory. The study presents operators of crossing, mutation and selection. Structures of the algorithm data have been prepared on the basis of the aforementioned visualization so that each of the achieved individuals described one complete discretisation solution. Hence, in the proposed approach, the population is a set of many complete discretisations of all the attributes. The solution is optimized by means of evolutionary search for the optimum. The study includes results of experiments that compared LDGen adaptation algorithm with other discretisation methods used in rough sets theory. As main components of the article may be regarded such elements like visualisation method, evolutionary data discretisation method including dedicated operators and discussion on the results of experiments.