Wyniki wyszukiwania - Biblioteka Nauki

1

Simple Adaptive Filter as a Part of Information System for Market Data Analysis

100%

Janowicz M. , Kietlińska K. , Zembrzuski A.

|

nr 4

221-228

EN

Application of the simple least mean squares (LMS) adaptive filter of to the Warsaw Exchange Market (GPW) has been analyzed using stocks belonging to WIG20 group as examples. LMS filter has been used as a binary classifier, that is, to forecast the sign of changes in the (normalized) stock values. Two kinds of data has been used, namely, the differenced and double-differenced normalized close values of stocks. It has been shown that while the predictive power of LMS filter is virtually zero for the differenced series, it rises significantly in the case of double-differenced series for all analyzed stocks. We attribute this to the better stationarity properties of the double-differenced time series.

2

Filtering of Industrial Data using the Artifficial Neural Networks

88%

Stanisławczyk A. , Talar J. , Jarosz P. , Kusiak J.

|

tom Vol. 7, No. 2

311-316

EN

The data sets, which describe the parameters of any real industrial process, are usually noisy and often not complete. Moreover, the analysis of the data sets is complicated because of the measurement noise of different kinds. The filtering process of the data with the imposed noise is a complex problem and it is difficult to find appropriate general filtering method, which gives the reliable results. Sometimes, the filtering procedure eliminates important information, and sometimes leaves the unnecessary noise. This situation causes many problems with the gathering of the data, which can be useful in modelling of the considered industrial process. The main objective of the work is elaboration of the filtering procedures of the data sets obtained from the copper flash smelting process. The filtered data will serve to work out the Artificial Neural Network based control system of the copper flash smelting process. The existing models of that process are very simplified or based on the FEM models [1-4]. These models are useless from the point of view of the control system, because of its low accuracy and a long computation time. The idea of the control system of the copper flash smelting process is based on the artificial neural networks model [5,6]. The registered in the industrial conditions data are not suitable for the further analysis and modelling of the process. Therefore, the elaboration of the model must be preceded with the filtering of the data. Different techniques were applied to filtering of the noisy industrial data: Fourier Transform Method and techniques based on the Artificial Neural Networks. The filtered data sets were used to creation of the ANN model of the copper flash smelting process. The paper presents the results of filtering of the industrial data and the results of prediction of the chosen parameters of the copper flash smelting process using ANN model elaborated on the base of filtered data.

PL

W procesie modelowania obiektów przemysłowych często napotyka się na trudności związane ze specyfikacją i sposobem akwizycji danych opisujących rzeczywisty obiekt. Rejestrowane dane są zaszumione oraz często niekompletne. Również nie wszystkie istotne parametry mogą być rejestrowane. Filtrowanie danych z nakładającymi się szumami oraz zakłóceniami jest bardzo złożonym problemem, a znalezienie uniwersalnej metody filtrowania, która dawałaby wiarygodne rezultaty jest zadaniem skomplikowanym. Czasem procedury filtrowania eliminują istotne informacje, innym razem pozostawiają zbędny szum. Dlatego też, rejestrowane dane są często nieużyteczne dla dalszej analizy i modelowania procesu. Celem pracy jest prezentacja opracowanej procedury filtrowania, która pozwala na eliminowanie tych komponentów sygnałów wyjściowych, które nie mogą być przewidywane na podstawie rejestrowanych sygnałów wejściowych. Zaproponowany algorytm filtrowania danych wykorzystuje zalety różnych technik: filtrów adaptacyjnych, metody transformaty Fouriera oraz technik opartych o sztuczne sieci neuronowe. Opisano metodę filtrowania danych przemysłowych oraz zaprezentowano zastosowanie jej do filtrowania danych pochodzących z pieca do zawiesinowego wytopu miedzi.

3

Simple adaptive filter as a part of information system for market data analysis

75%

Janowicz M. , Kietlińska K. , Zembrzuski A.

|

tom Vol. 3, No. 4

221--228

EN

Application of the simple least mean squares (LMS) adaptive filter of to the Warsaw Exchange Market (GPW) has been analyzed using stocks belonging to WIG20 group as examples. LMS filter has been used as a binary classifier, that is, to forecast the sign of changes in the (normalized) stock values. Two kinds of data has been used, namely, the differenced and double differenced normalized close values of stocks. It has been shown that while the predictive power of LMS filter is virtually zero for the differenced series, it rises significantly in the case of double-differenced series for all analyzed stocks. We attribute this to the better stationarity properties of the double differenced time series.

4

Zastosowanie technik przetwarzania obrazów do identyfikacji śladów obróbki ściernej

63%

Łukianowicz C.

|

tom R. 91, nr 11

1020--1022

PL

Przedstawiono podstawy wybranych technik przetwarzania obrazów opartych na przekształceniach Fouriera, Radona i Hougha, które są stosowane do szybkiej identyfikacji śladów obróbki na powierzchniach obrobionych ściernie. Pokazano przykład programu pozwalającego na identyfikację śladów obróbki.

EN

The principles of selected image processing techniques based on Fourier, Radon and Hough transformations are presented. The techniques can be used to quick identification of the machined marks on surfaces after abrasive machining. Example of software that allow the identification of machined marks is shown.

5

Metody badań ekspresji mowy u osób po usunięciu krtani

63%

Pietruch R. , Michalska M. , Konopka W. , Grzanka A.

|

tom Vol. 1, no. 1/2

175--182

PL

Artykuł ma na celu zaprezentowanie sposobów komputerowego przetwarzania obrazów i dźwięków wykorzystywanych w badaniach pacjentów po usunięciu krtani. Metody komputerowe mają na celu wizualizację widma głosu pacjentów, umożliwienie komputerowej analizy otrzymanych obrazów, wyselekcjonowanie najważniejszych cech sygnałów, zarchiwizowanie danych oraz analizę systematyczną otrzymanych wyników. Celem badań jest porównanie obiektywnych właściwości sygnałów z subiektywną oceną postępu pacjenta w rehabilitacji.

EN

The paper shows the methods for processing speech signals and imaging power spectral density of speech. The methods were applied in medicine as a tool for improving the patients' rehabilitation after tracheotomy. The adaptive algorithms and transversal filters were implemented to estimate the transfer function of human speech modeling tract. The estimation methods were based on autoregressive model. The pilot study on speakers' images, especially movements of lips and jaw, and their correlation with speech frequency has been presented.

6

Impulsive noise cleaning by smoothing of images using fast median method (FMM)

63%

Velu C. M. , Prabakaran N. , Vivekanandan P.

|

tom Vol. 13, no 3-4

19-30

EN

The objective of this paper is to propose new approaches FMM for removing impulsive noise in images so as to smooth the image for further processing. The various methods like Laplacian filter. Gaussian filter. Mean filter, Mode filter, Maximum filter, Minimum filter, Hybrid filter, Adaptive filter, Low pass filter, High pass filter, Hybrid filter and Uniform filter are discussed. In this paper, a new approach is proposed to use the FMM, which is obtained by computing median in each row, again median is calculated for medians of each row of a convolution mask. In this method, for example, for a 3 x 3 mask, left and right gray values are loaded along with center pixel of each row or each column and these values are sorted in order. The new center value is considered as median value, with this new value, smoothing of an image is achieved. In this method, a smoothed image is computed by employing just an auxiliary function swap, which yields less computation time.