Wyniki wyszukiwania - BazTech

1

A comparative study of CNN, LSTM, BiLSTM, AND GRU architectures for tool wear prediction in milling processes

Zegarra Fabio C., Vargas-Machuca Juan, Coronado Alberto M.

Journal of Machine Engineering

|

2023

|

Vol. 23, No. 4

122--136

EN

Accurately predicting machine tool wear requires models capable of capturing complex, nonlinear interactions in multivariate time series inputs. Recurrent neural networks (RNNs) are well-suited to this task, owing to their memory mechanisms and capacity to construct highly complex models. In particular, LSTM, BiLSTM, and GRU architectures have shown promise in wear prediction. This study demonstrates that RNNs can automatically extract relevant information from time series data, resulting in highly precise wear models with minimal feature engineering. Notably, this approach avoids the need for excessively large window sizes of data points during model training, which would increase model complexity and processing time. Instead, this study proposes a procedure that achieves low prediction errors with window sizes as small as 100 data points. By employing Bayesian hyperparameter optimization and two preprocessing techniques (detrend and offset), RMSE errors consistently fall below 10. A key difference in this study is the use of boxplots to provide a better representation of result variability, as opposed to solely reporting the best values. The proposed approach matches more complex state of-the-art. methods and offers a powerful tool for wear prediction in engineering applications.

2

Integrated preprocessing techniques with linear stochastic approaches in groundwater level forecasting

Azari Arash, Zeynoddin Mohammad, Ebtehaj Isa, Sattar Ahmed M. A., Gharabaghi Bahram, Bonakdari Hossein

Acta Geophysica

|

2021

|

Vol. 69, no. 4

1395--1411

EN

Accurate modeling of groundwater level (GWL) is a critical and challenging issue in water resources management. The GWL fuctuations rely on many nonlinear hydrological variables and uncertain factors. Therefore, it is important to use an approach that can reduce the parameters involved in the modeling process and minimize the associated errors. This study presents a novel approach for time series structural analysis, multi-step preprocessing, and GWL modeling. In this study, we identifed the time series deterministic and stochastic terms by employing a one-, two-, and three-step preprocessing techniques (a combination of trend analysis, standardization, spectral analysis, diferencing, and normalization techniques). The application of this approach is tested on the GWL dataset of the Kermanshah plains located in the northwest region of Iran, using monthly observations of 60 piezometric stations from September 1991 to August 2017. By removing the dominant nonstationary factors of the GWL data, a linear model with one autoregressive and one seasonal moving average parameter, detrending, and consecutive non-seasonal and seasonal diferencing were created. The quantitative assessment of this model indicates the high performance in GWL forecasting with the coefcient of determination (R2 ) 0.94, scatter index (SI) 0.0004, mean absolute percentage error (MAPE) 0.0003, root mean squared relative error (RMSRE) 0.0004, and corrected Akaike’s information criterion (AICc) 151. Moreover, the uncertainty and accuracy of the proposed linear-based method are compared with two conventional nonlinear methods, including multilayer perceptron artifcial neural network (MLP-ANN) and adaptive neuro-fuzzy inference systems (ANFIS). The uncertainty of the proposed method in this study was±0.105 compared to±0.114 and±0.126 for the best results of the ANN and the ANFIS models, respectively.

3

lpopt : A Rule Optimization Tool for Answer Set Programming

Bichler Manuel, Morak Michael, Woltran Stefan

Fundamenta Informaticae

|

2020

|

Vol. 177, nr 3/4

275--296

EN

State-of-the-art answer set programming (ASP) solvers rely on a program called a grounder to convert non-ground programs containing variables into variable-free, propositional programs. The size of this grounding depends heavily on the size of the non-ground rules, and thus, reducing the size of such rules is a promising approach to improve solving performance. To this end, in this paper we announce lpopt, a tool that decomposes large logic programming rules into smaller rules that are easier to handle for current solvers. The tool is specifically tailored to handle the standard syntax of the ASP language (ASP-Core) and makes it easier for users to write efficient and intuitive ASP programs, which would otherwise often require significant hand-tuning by expert ASP engineers. It is based on an idea proposed by Morak and Woltran (2012) that we extend significantly in order to handle the full ASP syntax, including complex constructs like aggregates, weak constraints, and arithmetic expressions. We present the algorithm, the theoretical foundations on how to treat these constructs, as well as an experimental evaluation showing the viability of our approach.

4

The Impact and Importance of Fabric Image Preprocessing for the New Method of Individual Inter-Thread Pores Detection

Owczarek Magdalena

Autex Research Journal

|

2020

|

Vol. 20, no. 3

250--262

EN

The paper describes the impact and importance of preprocessing methods of fabric image for detection of inter-thread pores (ITP), which is a new method of individual ITP identification. The aim of this experiment is to identify precisely every individual ITP of fabric structure by using optimal preprocessing algorithm for further quantitative, morphometric structural analysis of specialized fabrics (barriers, industrial filters, composites, others) in context of air permeability, flow resistance, UV radiation, viruses penetration, thermal comfort by estimation fabric porosity, especially macroporosity parameters and cover factor. The correct identification of individual ITP depends on the acquisition method and the preprocessing algorithm. It was conducted by analyzing the adaptation of digital image preprocessing methods for two structures of plain weave fabric in two magnification zooms, 1.25 and 0.8. Preprocessing operations were performed in the area of spatial operations of the image. The optimal preprocessing algorithm includes low-pass filtering, histogram equalization, nonlinear filtering, thresholding, and morphological operation. This algorithm was selected based on the factors developed by the author (ITP detection, RID factor—a difference between the real and model ITP areas) which rely on the ITP size, shape, and location. The graphic view of the ITP contour position on the fabric image is a verification element in the optimal preprocessing algorithm. The presented results of the air permeability of two different plain weave structures confirm the need to optimize the algorithm of pre-image processing methods to precisely detect each individual ITP in the fabric image.

5

Performance evaluation of African breadfruit (Treculia africana) seed dehuller

Obi O. F., Akubuo C. O.

Agricultural Engineering

|

2018

|

Vol. 22, No. 4

51--60

EN

This paper reports the effect of the parboiling time on dehulled kernel out-turns (DKO) of African breadfruit seeds, and the most recent effort to upgrade an existing dehuller and its performance. Two common and readily available varieties - Treculia var. africana and var. inverse were used in the study. The seeds were parboiled for 0 (control), 2, 5, 8, 11 and 14 minutes and then dehulled. The result revealed that the parboiling time had a significant effect on the DKO of the two varieties of the seed. The DKO increased from 0 to 5 min of the treatment, after which it decreased considerably up to 14 min of the parboiling time. The obtained data were used to develop a non-linear quadratic regression model to predict the DKO as a function of the parboiling time. The performance evaluation of the breadfruit seeds dehuller revealed that it was significantly influenced by the variety.

PL

Artykuł ten przedstawia wpływ czasu gotowania na uzysk łuskanego ziarna afrykańskiego drzewa chlebowego oraz niedawne wysiłki w kierunku ulepszenia istniejącej łuskarki i jej działania. Do badań użyto dwie pospolite i dostępne odmiany Treculia var. africana oraz var. inverse. Ziarna gotowano przez 0, 2, 5, 8, 11 i 14 minut a następnie łuskano. Wyniki pokazały, że czas gotowania miał istotny wpływ na uzysk ziarna łuskanego dwóch odmian ziarna. Uzysk ziarna łuskanego zwiększał się w ciągu 0-5 minut obróbki, po czym po 14 minutach gotowania drastycznie zmalał. Uzyskane dane zostały wykorzystane do przygotowania nieliniowego kwadratowego modelu regresji służącego do przewidywania uzysku ziarna łuskanego w funkcji czasu gotowania. Ocena działania łuskarki wykazała, że było ono uzależnione od odmiany.

6

Rola cyfrowych narzędzi w projektowaniu architektury

Ciepłucha W.

Środowisko Mieszkaniowe

|

2017

|

nr 19

63--73

PL

Building Information Modeling usprawnia projektowanie, budowę i zarz ądzanie cyklem życia wszystkich obiektów środowiska budowlanego. Celem jest tworzenie cyfrowego modelu, który przedstawia skoordynowane, wiarygodne informacje o projekcie budowlanym na różnych etapach jego realizacji. Płaska dokumentacja techniczna jest zastąpiona cyfrowym modelem 3D. Model przedstawia zapisane cyfrowo odzwierciedlenie fizycznych i funkcjonalnych właściwości obiektu. BIM umożliwia projektantom podejmowanie trafnych, szybkich i świadomych decyzji, dzięki którym podnoszona jest jakość projektu. Technologia pomaga w różnych środowiskach przewidywać konsekwencje podjętych decyzji. Zgromadzone dane możemy porównywać, analizować, wykrywać kolizje i nanosić zmiany. Zmniejsza się ilość błędów, skraca się czas analiz i na każdym etapie pracy z projektem możemy dopracowywać poszczególne elementy. Model umożliwia współpracę w jednym standardzie we wszystkich branżach, które biorą udział w procesie projektowym.

EN

Building Information Modelling (BIM) streamlines the design, construction, and lifecycle management of all building environments. The goal is to create a digital model that provides coordinated, reliable information on the construction project at various stages of its implementation. The two-dimensional technical documentation is replaced by a digital 3D model. The model shows the digitally rendered physical and functional properties of the object. BIM enables designers to make relevant, quick and informed decisions that enhance the quality of the project. Technology helps to predict the consequences of the decisions in different environments. The collected data can be compared, analyzed, cleared for collision, and modified. The number of errors is reduced, the analysis time is reduced, and specific elements can be fine-tuned at each stage of the project. The model enables one-stop collaboration in all industries involved in the design process.

7

CCR: A combined cleaning and resampling algorithm for imbalanced data classification

Koziarski M., Woźniak M.

International Journal of Applied Mathematics and Computer Science

|

2017

|

Vol. 27, no. 4

727--736

EN

Imbalanced data classification is one of the most widespread challenges in contemporary pattern recognition. Varying levels of imbalance may be observed in most real datasets, affecting the performance of classification algorithms. Particularly, high levels of imbalance make serious difficulties, often requiring the use of specially designed methods. In such cases the most important issue is often to properly detect minority examples, but at the same time the performance on the majority class cannot be neglected. In this paper we describe a novel resampling technique focused on proper detection of minority examples in a two-class imbalanced data task. The proposed method combines cleaning the decision border around minority objects with guided synthetic oversampling. Results of the conducted experimental study indicate that the proposed algorithm usually outperforms the conventional oversampling approaches, especially when the detection of minority examples is considered.

8

Computer-aided analysis of data from evaluation sheets of subjects with autism spectrum disorders

Pancerz K., Derkacz A., Mich O., Gomula J.

Bio-Algorithms and Med-Systems

|

2016

|

Vol. 12, no. 3

109--116

EN

In this paper, we deal with the problem of the initial analysis of data from evaluation sheets of subjects with autism spectrum disorders (ASDs). In the research, we use an original evaluation sheet including questions about competencies grouped into 17 spheres. An initial analysis is focused on the data preprocessing step including the filtration of cases based on consistency factors. This approach enables us to obtain simpler classifiers in terms of their size (a number of nodes and leaves in decision trees and a number of classification rules).

9

Preprocessing and Storing High - Throughput Sequencing Data

Świercz A., Bosak B., Chłopkowski M., Hoffa A., Kasprzak M., Kurowski M., Piontek T., Błażewicz J.

Computational Methods in Science and Technology

|

2014

|

Vol. 20, No. 1

9--20

EN

DNA sequencing is a process of recognizing DNA sequences of genomes. The process consists in reading short sequences, that are subsequences of a genome, and merging them into longer sequences, preferably the whole genome. In the first phase even billions of short sequences are read at once. To simplify and speed up the second phase, we develop a pipeline of preprocessing the initial set of short sequences that is removing low quality reads and duplicated reads.We also propose a method for preliminary joining overlapping sequences, which resulted in decreasing the cardinality of initial sets to 13.9% and 27.8%. We also examine possible ways to store the huge amount of experimental data. We compare different compression methods, from which the best appeared to be DSRC, developed for special type of text files containing short sequences and their quality. We test the parameters for TCP data transferring to find the best transfer rate.

10

A study on influence of normalization methods on music genre classification results employing kNN algorithm

Rosner A., Michalak M., Kostek B.

Studia Informatica

|

2013

|

Vol. 34, nr 2A

411--423

EN

This paper presents a comparison of different normalization methods applied to the set of feature vectors of music pieces. Test results show the influence of min-max and Zero-Mean normalization methods, employing different distance functions (Euclidean, Manhattan, Chebyshev, Minkowski) as a pre-processing for genre classification, on k-Nearest Neighbor (kNN) algorithm classification results.

PL

Artykuł przedstawia porównanie różnych metod normalizacji zastosowanych do zbioru wektorów cech utworów muzycznych. Wyniki testów prezentują wpływ zastosowania metod normalizacji min-max oraz Zero-Mean z użyciem różnych funkcji odległości (Euklidesowej, Manhattan, Czebyszewa, Minkowskiego) w procesie wstępnego przetwarzania w klasyfikacji gatunków muzycznych z wykorzystaniem algorytmu klasyfikacji k-Najbliższych Sąsiadów (kNN).

11

Wpływ wstępnego przetwarzania danych na jakość krótkoterminowych prognoz zapotrzebowania na energię elektryczną

Nęcka K.

Inżynieria Rolnicza

|

2013

|

R. 17, nr 3, t. 1

291--299

PL

Celem pracy była analiza wpływu różnych metod wstępnego przetwarzania danych wejściowych, takich jak np. średnia ruchoma, wyrównywanie wykładnicze, filtr 4253H, na jakość prognoz godzinowego zapotrzebowania na energię elektryczną opracowanych metodami regresyjnymi. Cel pracy zrealizowano na podstawie badań własnych wykonanych w rozdzielni nN, zlokalizowanej na terenie nowoczesnej ubojni drobiu w południowej części Małopolski. Wykonane analizy skupień metodą k-średnich i metodą EM pokazały, że ze względu na podobieństwo przebiegu godzinowego zapotrzebowania na energię elektryczną optymalny będzie podział dni tygodnia na 3 skupienia, tj. dni robocze, dni poprzedzające dzień wolny od pracy oraz dni wolne od pracy, i budowa trzech niezależnych modeli. W zastosowaniach praktycznych najważniejszym parametrem oceny modeli jest sumaryczna wartość rzeczywistej ilości energii bilansującej ΔESR. Dla większości budowanych modeli na bazie zmiennych przekształconych zaobserwowano zmniejszenie wartości wskaźnika ΔESR względem modeli budowanych w oparciu o zmienną egzogeniczną nieprzekształconą. Największe, ponad 6% zmniejszenie wartości analizowanego wskaźnika uzyskano w modelu III dla zmiennej wejściowej wygładzonej oknem Daniela o rozpiętości 5. Ze względu na najniższą wartość sumarycznej ilości energii bilansującej w zastosowaniach praktycznych powinny być jednak preferowane modele budowane na bazie szeregu czasowego godzinowego zużycia energii elektrycznej dla całego zakładu wygładzonego filtrem 4253H.

EN

The objective of this study was to analyse the influence of different methods of preprocessing of the input data, such as moving average, exponential smoothing, filter 4253H on the quality of forecasts of hourly demand for electricity developed with regression methods. The objective of the study was carried out on the basis of own research carried out in the nN switchboard, located on the territory of a modern poultry slaughterhouse in the southern part of Małopolska region. The cluster analysis carried out with k-means and the EM method has shown that due to the similarity of the course of hourly demand for electricity division of weekdays into three days of cluster that is, working days, days preceding the days off, days off and construction of three independent models will be optimal. The total value of the actual amount of balancing energy ΔESR is the most important parameter of the models assessment in the practical applications. For majority of models constructed on the basis of the transformed variables, the decrease in the rate ΔESR towards models constructed based on exogenous not transformed variable was reported. The largest over 6% reduction in the value of the analysed indicator was obtained in model III for the input variable smoothed with 5th span Daniel window. Due to the lowest value of the total amount of balancing energy in practical applications, models built on the basis of a time series of hourly electricity consumption for the entire plant smoothed filter 4253H should be preferred.

12

A rainfall forecasting method using machine learning models and its application to the Fukuoka city case

Sumi S. M., Zaman M. F., Hirose H.

International Journal of Applied Mathematics and Computer Science

|

2012

|

Vol. 22, no. 4

841-854

EN

In the present article, an attempt is made to derive optimal data-driven machine learning methods for forecasting an average daily and monthly rainfall of the Fukuoka city in Japan. This comparative study is conducted concentrating on three aspects: modelling inputs, modelling methods and pre-processing techniques. A comparison between linear correlation analysis and average mutual information is made to find an optimal input technique. For the modelling of the rainfall, a novel hybrid multi-model method is proposed and compared with its constituent models. The models include the artificial neural network, multivariate adaptive regression splines, the k-nearest neighbour, and radial basis support vector regression. Each of these methods is applied to model the daily and monthly rainfall, coupled with a pre-processing technique including moving average and principal component analysis. In the first stage of the hybrid method, sub-models from each of the above methods are constructed with different parameter settings. In the second stage, the sub-models are ranked with a variable selection technique and the higher ranked models are selected based on the leave-one-out cross-validation error. The forecasting of the hybrid model is performed by the weighted combination of the finally selected models.

13

Preprocessing symulacji numerycznej procesów spalania w pojedynczej komorze silnika o zapłonie samoczynnym

Kosma Z., Kalbarczyk R., Piechnik B., Różycki A.

Logistyka

|

2011

|

nr 6

PL

Praca przedstawia zagadnienia związane z preprocessingiem procesów spalania w silniku o zapłonie samoczynnym. Jest to pierwszy etap prac związanych z analizą numeryczną silnika diesla zasilanego dwupaliwowo. Prezentowany jest sposób realizacji preprocessingu. Do generowania siatek zostało użyte oprogramowanie firmy Ansys. Nakreślono sposób generowania siatek dynamicznych dla zmiennej geometrii.

EN

The paper presents issues related to preprocessing combustion engine ignition. This is the first stage of work on the numerical analysis of the bi-fuel powered diesel engine. Presented method is an implementation of preprocessing. Grids were generated with Ansys software. It presents how to generate dynamic meshes for variable geometry.

14

HMM-based Online Handwritten Gurmukhi Character Recognition

Sharma A., Kumar R., Sharma R. K.

Machine Graphics and Vision

|

2010

|

Vol. 19, No. 4

439-449

EN

This paper presents a hidden Markov model-based online handwritten character recognition for Gurmukhi script. We discuss a procedure to develop a hidden Markov model database in order to recognize Gurmukhi characters. A test with 60 handwritten samples, where each sample includes 41 Gurmukhi characters, shows a 91.95% recognition rate, and an average recognition speed of 0.112 seconds per stroke. The hidden Markov model database has been developed in XML using 5330 Gurmukhi characters. This work shall be useful to implement a hidden Markov model in online handwriting recognition and its software development.

15

Online Preprocessing of Handwritten Gurmukhi Strokes

Sharma A., Sharma R. K., Kumar R.

Machine Graphics and Vision

|

2009

|

Vol. 18, No. 1

105-120

EN

In this paper, the authors have implemented preprocessing algorithms for online handwritten Gurmukhi strokes in order to find the improvements in recognition of four high-level features (loop, headline, straight line and dot) of Gurmukhi strokes. Preprocessing algorithms include size normalization and centering, interpolating missing points, smoothing, slant correction and resampling of points. Recognition algorithms for the above mentioned four high-level features are also introduced in this paper. Experiments have been conducted across 60 writers and 5%, 3.33%, 6.66% and 8.34% improvements have been observed for recognition of loop, headline, straight line and dot features, respectively, after using preprocessing algorithms.

16

Methods as Parameters: A Preprocessing Approach to Higher Order in Java

Bellia M., Occhiuto M.E.

Fundamenta Informaticae

|

2008

|

Vol. 85, nr 1-4

35-50

EN

The paper investigates the use of preprocessing in adding higher order functionalities to Java, that is in passing methods to other methods. The approach is based on a mechanism which offers a restricted, disciplined, form of abstraction that is suitable to the integration of high order and object oriented programming. We show how this integration can be exploited in programming through the development of an example. Then, we discuss how the expressive power of the language is improved. A new syntax is introduced for formal and actual parameters, hence the paper defines a translation that, at preprocessing time, maps programs of the extended language into programs of ordinary Java.

17

Additional data preprocessing and feature extraction in automatic classification of heartbeats

Tadejko P.

Zeszyty Naukowe Politechniki Białostockiej. Informatyka

|

2007

|

Z. 2

155-173

EN

The paper presents the classification performance of an automatic classifier of the electrocardiogram (ECG) for the detection abnormal beats with new concept of feature extraction stage. Feature sets were based on ECG morphology and RR-intervals. This paper compares two strategies for classification of annotated QRS complexes: based on original ECG morphology features and proposed new approach - based on preprocessed ECG morphology features. The mathematical morphology filtering and wavelet trans-form is used for the preprocessing of ECG signal. Within this framework, the problem of choosing an appropriate structuring element in mathematical morphology filtering in signal processing was studied. Configuration adopted a Kohonen self-organizing maps (SOM) and Support Vector Machine (SVM) for analysis of signal features and clustering. In this study, a classifiers was developed with LVQ and SVM algorithms using the data from the records recommended by ANSI/AAMI EC57 standard. The performance of the algorithm is evaluated on the MIT-BIH Arrhythmia Database following the AAMI recommendations. Using this method the results of identify beats either as normal or arrhythmias was improved.

PL

Artykuł prezentuje nowe podejście do problemu klasyfikacji zapisów ECG w celu detekcji zachowań chorobowych. Podstawą koncepcji fazy ekstrakcji cech jest proces przetwarzania wstępnego sygnału ECG z wykorzystaniem morfologii matematycznej oraz innych transformacji. Morfologia matematyczna bazując na teorii zbiorów, pozwala zmienić charakterystyczne elementy sygnału. Dwie podstawowe operacje: dylatacja i erozja pozwalają na uwydatnienie lub redukcję wielkości i kształtu określonych elementów w danych. Parametry charakterystyki zapisów ECG stanowią bazę dla wektora cech. Do klasyfikacji przebiegów ECG w pracy wykorzystano samoorganizujące się mapy (SOM) Kohonena z klasyfikatorem LVQ oraz algorytm Support Vector Machines (SVM). Eksperymenty przeprowadzono klasyfikując sygnały pomiędzy trzynaście kategorii rekomendowanych przez standard ANSI/AAMI EC57, to jest: prawidłowy rytm serca i 12 arytmii. Zaproponowany w artykule algorytm opiera się na wykorzystaniu elementarnych operacji morfologii matematycznej i ich kombinacji. Ocenę wyników eksperymentów przeprowadzono na sygnałach z bazy MIT/BIH. Na tej podstawie zaproponowano wyjściową architekturę bloku filtrów morfologicznych dla celów ekstrakcji cech oraz unifikacji wejściowego sygnału ECG jako danych wejściowych do budowy wektora cech.

18

Removal of noise from sodar data using ABL characteristics guided morphological filter

Pal P., Mukherjee A., Chanda B.

Image Processing & Communications

|

2007

|

Vol. 12, no 1

5-15

EN

There is potential of using acoustic sounder system to study boundary layer meteorology. The repeatable patterns on sodar-images become necessary and useful to find suitable techniques for computer analysis and interpretation. Image processing and pattern recognition approaches have been explored for SODAR signal processing. Like all real digital images, sodar-images are also degraded with noise, thereby complicating the sodar-patterns. Since the exact mathematical model of the system is not available, challenges exist to minimise the effect of noise present in the sodar-images. This will lead to better extraction of the sodar-patterns from the sodar-images. Noise cleaning algorithm for sodar-images have been considered here based on the morphology of ABL pattern characteristics. The results of this algorithm compare favourably with the existing methods.

19

Zwiększenie dokładności prognoz ceny energii poprzez zastosowanie preprocessingu oraz modeli nieliniowych

Misiorek A., Weron R.

Przegląd Elektrotechniczny

|

2006

|

R. 82, nr 9

44-46

PL

W pracy zastosowano liniowy model AR do stworzenia prognoz cen z rynków energii elektrycznej Kalifornii (CalPX) i Skandynawii (Nord Pool). Następnie zaproponowano metody umożliwiające zwiększenie dokładności tego typu prognoz - poprzez wykorzystanie preprocessingu (zmniejszającego wpływ skoków procesu w okresie kalibracji) oraz dwustanowego modelu nieliniowego TAR.

EN

In this paper we assess the short-term forecasting power of different time series models in two electricity spot markets - CalPX and Nord Pool. In particular we pay attention to the possibility of improving the accuracy of forecasts either by applying the preprocessing or by using nonlinear time series model - TAR.

20

Combined off-line type signature recognition method

Porwik P., Para T., Smacki Ł., Żuławiński S.

Journal of Medical Informatics & Technologies

|

2006

|

Vol. 10

81--90

EN

In this paper the off-line type signature analysis have been presented. The signature recognition is composed of some features. Different influences of such features were tested and stated. Proposed approach gives good signature recognition level, hence described method can be used in many areas, for example in biometric authentication, as biometric computer protection or as method of the analysis of person's behaviour changes.