Browsing by Subject "pattern recognition"

Now showing 1 - 20 of 24

Access status: Open Access ,
Application of pattern recognition methods to automatic identification of microscopic images of rocks registered under different polarization and lighting conditions
(Wydawnictwa AGH, 2013) Ślipek, Bartłomiej; Młynarczuk, Mariusz
The paper presents the results of the automatic classification of rock images, taken under an optical microscope under different lighting conditions and with different polarization angles. The classification was conducted with the use of four pattern recognition methods: nearest neighbor, k-nearest neighbors, nearest mode, and optimal spherical neighborhoods on thin sections of five selected rocks. During research the CIELAB color space and the 9D feature space were used. The results indicate that changing both lighting conditions and polarization angles results in worsening the classification outcome, although not substantially. During the automatic classification of rocks photographed under different lighting and polarization conditions, the highest number of correctly classified rocks (97%) is given by the nearest neighbor method. The results show that the automatic classification of rocks is possible within a predefined group of rocks. The results also indicate the optimal spherical neighborhoods method to be the safest method out of those tested, which means that it returns the lowest number of incorrect classifications.
Access status: Restricted ,
Bezprzewodowe urządzenie wskazujące z akcelerometrem
(Data obrony: 2016-12-08) Szuba, Paweł
Wydział Informatyki, Elektroniki i Telekomunikacji
Access status: Open Access ,
Cascade algorithm for the reference set size reduction
(Wydawnictwa AGH, 2009) Sierszeń, Artur
Two algorithms of the reference set condensation, one of which is based on finding the mutually furthest points and the other is the modification of the Chang's algorithm, are respectively of the incremental and eliminative type, i.e. the size of the condensed set increases or is reduced as a result of a subsequent iteration. The combination of both aforementioned types of condensation, i.e. the cascade algorithm of condensation, is more effective than each of these algorithms executed sepa-rately.
Computer Methods in Materials Science
AGH University Press (2020-)
ISSN: 2720-4081 e-ISSN: 2720-3948
Access status: Open Access ,
Exploration of cellular automata: a comprehensive review of dynamic modeling across biology, computer and materials science
(Wydawnictwa AGH, 2023) Vodka, Oleksii O.; Shapovalova, Mariia I.
This paper delves into the expansive world of cellular automata (CA), abstract models of computation comprised of cells that interact based on predefined rules. Originating from John von Neumann’s work in the 1940s, CA has evolved into a multidisciplinary field with applications ranging from mathematical concepts to complex simulations of biological, physical, computer science, material science, and social systems. The paper reviews its historical development, emphasizing John Conway’s influential Game of Life and Burk’s seminar collection. The authors categorize and explore a myriad of CA topics, including self-replicating automata, the universality of computation, compromises in CA, variants, applications in biological systems, fault-tolerant computation, pattern recognition, CA games, fractals, dynamic properties, complexity, image processing, cryptography, bioinformatics, materials modeling, probabilistic automata, and contemporary research. The significance of cellular automata for materials modeling cannot be overstated and considerable attention has been devoted to the issues of modeling nucleation and recrystallization. The review aims to provide a comprehensive resource for both beginners and experts in the field, shedding light on cellular automata’s dynamic and diverse applications in various aspects of life and scientific inquiry.
Access status: Restricted ,
GPU - Accelerated multidimensional scaling based on particle dynamics
(Data obrony: 2012-06-26) Pyla, Michał
Wydział Elektrotechniki, Automatyki, Informatyki i Elektroniki
Access status: Restricted ,
Identyfikacja osób na podstawie analizy tęczówki
(Data obrony: 2009-12-16) Mokrzycki, Jacek
Wydział Elektrotechniki, Automatyki, Informatyki i Elektroniki
Access status: Open Access ,
Modyfikacja algorytmu Changa z wykorzystaniem metody znajdowania punktów najbliższych
(Wydawnictwa AGH, 2007) Sierszeń, Artur
The modification of Chang's algorithm consisting in replacement of the original method of determining the distance to the nearest point from the same class with modified methods of finding the mutually nearest points causes a great acceleration of the computational phase. Results of experiments show that the presented method does not significantly decrease the quality of classification.
Access status: Open Access ,
Network behavior-analysis systems with the use of learning set and decision rules based on distance
(Wydawnictwa AGH, 2010) Sierszeń, Artur; Sturgulewski, Łukasz; Dubel, Michał; Marciniak, Tomasz; Wójciński, Adam
Network Behavior Analysis is an ability to identify traffic patterns which do not occur during normal operation of a network. In other words, it is an attempt to identify irregularities in a network, an attempt which goes beyond simple settings concerning exceeding parameters for traffic of a given type. In the article the authors present a concept of using Pattern Recognition, i.e. a learning set and decision rules based on neighbor rule.
Access status: Open Access ,
Nowe metody selekcji cech i redukcji zbiorów odniesienia dla klasyfikatora typu 1-NN
(Wydawnictwa AGH, 2008) Kośla, Paweł; Raniszewski, Marcin
W artykule zostały przedstawione nowe metody minimalizacji zbioru odniesienia dla klasyfikatora 1-NN, czyli selekcja cech i redukcja zbioru odniesienia. Do selekcji cech zaproponowano metodę wykorzystującą badanie zależności miedzy cechami, a do redukcji zbioru odniesienia użyto sekwencyjnego algorytmu wykorzystującego podwójne sortowanie punktów. Rozstrzygnięto również, w jakiej kolejności procedury te powinny zostać zastosowane, analizując ich wpływ na jakość klasyfikacji i stopień redukcji danych. Zarówno nowe metody, jak i dobrze znane, takie jak procedura kolejnego dołączania cech, algorytm Gowdy-Krishny i algorytm RMHC zaproponowany przez Skalaka, zostały przetestowane na siedmiu zbiorach danych rzeczywistych i sztucznych.
Access status: Restricted ,
Opracowanie wizyjnego algorytmu wykrywania wad wyświetlaczy LCD i LED
(Data obrony: 2018-01-18) Pięta, Marek
Wydział Elektrotechniki, Automatyki, Informatyki i Inżynierii Biomedycznej
Access status: Restricted ,
Predykcja ruchu pieszych na podstawie obrazu wideo, danych statystycznych oraz wzorców behawioralnych
(Data obrony: 2018-01-24) Głód, Piotr
Wydział Elektrotechniki, Automatyki, Informatyki i Inżynierii Biomedycznej
Access status: Open Access ,
Próba wykorzystania sieci neuronowych w kompleksowej interpretacji danych elektromagnetycznych na przykładzie złoża Grabownica
(Wydawnictwa AGH, 2011) Mastej, Wojciech
The paper presents an attempt to apply the pattern recognition method using artificial neural networks in integrated interpretation of the magnetotelluric data AMT (Audio-frequency Magnetotellurics) and CSAMT (Controlled Source Audio-frequency Magnetotellurics), acquired from the Grabownica oil and gas deposit (longitudinal and transversal dipole in relation to measurement profile lines). Vertical belts of magnetotelluric cross-sections, each 50 m wide, obtained from interpolation grids, were the objects of classification. The structure of formally non-structural objects was partly imposed through division into: near-surface high-resistivity zone, to 200 m a.s.l., low-resistivity screens and week maxima - diffusion chimneys, from 200 to -100 m a.s.l., and the lowest, high-resistivity deposit zone. The usefulness of the method was proven by correct identification of real deposit zones based on data often coming from ambiguous and incompatible magnetotelluric cross-sections. In addition, two unknown deposit zones were discovered in NE part of cross-section G4 and SW part of cross-section G2.
Access status: Open Access ,
Recognition of aircraft noise in long-term environmental monitoring
(2010) Wszołek, Wiesław; Kłaczyński, Maciej
Continuous acoustical climate monitoring of a particular area raises problems related to large quantities of the recorded data, which often represents information unrelated to the study source. Manual verification of data is time-consuming and costly. Therefore, to develop effective methods for automatic identification of transport noise sources becomes an important task for the proper determination of noise levels. This paper presents a concept of method in automatic detection and classification of air transport noise sources in the acoustic environmental monitoring.
Access status: Open Access ,
Reduction of large reference sets with modified Chang's algorithm
(Wydawnictwa AGH, 2009) Sierszeń, Artur
The advantage of the Chang's algorithm is a considerable reduction of the reference set. Its drawback is relatively small speed. The modification proposed by the author of this article aims at accelerating computations by replacing a larger number of objects, not only a pair of them, with one object. For any object in the reference set, it is possible to determine all objects from the same class which are located at a shorter distance to it than any other object from a different class. This group of objects can be replaced by a single artificial object.
Access status: Restricted ,
Rozpoznawanie patologii oka z wykorzystaniem sieci neuronowych
(Data obrony: 2017-01-25) Zawada, Katarzyna
Wydział Elektrotechniki, Automatyki, Informatyki i Inżynierii Biomedycznej
Access status: Restricted ,
Rozpoznawanie wzorców danych jako sygnatury polarymetryczne przy pomocy sieci neuronowych
(Data obrony: 2013-07-04) Wojdanowski, Wojciech
Wydział Geologii, Geofizyki i Ochrony Środowiska
In this thesis a new method for polarimetric signatures recognition has been proposed. It uses selected tools from the set of artificial intelligence systems. Following chapters are explaining the discussed issue and the proposed solution. Data compression method of the explored data has been presented, which is based on Kohonen neural networks. It was shown using the ART-2 systems that polarimetric signatures can be divided on well defined set of classes. The last chapters also presents effectiveness of this method and its application in koherent pixels detection on polarimetric radar pictures.
Access status: Restricted ,
System rekomendacji treści WWW
(Data obrony: 2016-09-28) Porzycki, Krzysztof
Wydział Elektrotechniki, Automatyki, Informatyki i Inżynierii Biomedycznej
Access status: Restricted ,
System rozpoznawania i identyfikacji tablic rejestracyjnych pojazdów w aplikacji na system Android
(Data obrony: 2017-07-12) Niemiec, Michał
Wydział Elektrotechniki, Automatyki, Informatyki i Inżynierii Biomedycznej
Access status: Restricted ,
System wizyjny do wyszukiwania punktów bazowych na płytkach drukowanych
(Data obrony: 2017-01-17) Burcon, Mateusz
Wydział Elektrotechniki, Automatyki, Informatyki i Inżynierii Biomedycznej