Przeglądaj {{ collection }} wg Autor "Puchała, Dariusz"

Teraz wyświetlane 1 - 6 z 6

Image filtering with past parametrized biorthogonal transforms implemented on a new GUI research aid system
(Wydawnictwo Politechniki Łódzkiej, 2013) Puchała, Dariusz; Stasiak, Bartłomiej; Stokfiszewski, Kamil; Yatsymirskyy, Mykhaylo
In this paper the authors show that fast parametrized biorthogonal transforms (FPBT) are well suited for adaptive generalized Wiener image ﬁltering. Research results are obtained with a use of a new graphical user interface system for implementing various fast adaptive techniques, designed, implemented and published by the authors as a part of a project Innovative Economy Programme 2007-2013 „Platforma Informatyczna TEWI”.
Integrating Anomaly Detection for Enhanced Data Protection in Cloud-Based Applications
(Wydawnictwo Politechniki Łódzkiej, 2023) Czerkas, Konrad; Drozd, Michał; Duraj, Agnieszka; Lichy, Krzysztof; Lipiński, Piotr; Morawski, Michał; Napieralski, Piotr; Puchała, Dariusz; Kwapisz, Marcin; Warcholiński, Adrian; Karbowańczyk, Michał; Wosiak, Piotr
In this research, anomaly detection techniques and artificial neural networks were employed to address the issue of attacks on cluster computing systems. The study investigated the detection of Distributed Denial of Service (DDoS) and Partition attacks by monitoring metrics such as network latency, data transfer rate, and number of connections. Additionally, outlier detection algorithms, namely Local Outlier Factor (LOF) and COF, as well as ARIMA and SHESD models were tested for anomaly detection. Two types of neural network architectures, multi-layer perceptron (MLP) and recursive LSTM networks, were used to detect attacks by classifying events as “attack” or “no attack”. The study underscores the importance of implementing proactive security measures to protect cluster computing systems from cyber threats.
Local Energy Redistribution Units for Space Dimensionality Reduction in Data Classification
(Wydawnictwo Politechniki Łódzkiej, 2023) Puchała, Dariusz
In this paper, we present locally trained 2-input to 2-output neurons called Local Energy Redistribution Units (LERUs), which enable to transfer most of the input data energy to the selected output, and when organized into properly designed networks, allow for the energy accumulation in lower-indexed elements of output vectors. This property can be used to reduce the dimensionality of the input data space, resulting in a reduction in the number of weights and disk space needed to store neural network models. We test the effectiveness of the proposed approach experimentally in the task of data classification using the well-known MNIST dataset.
Low-complexity approximation of 8-point discrete cosine transform for image compression
(Wydawnictwo Politechniki Łódzkiej, 2012) Puchała, Dariusz; Stokfiszewski, Kamil
In this paper the authors propose a new low-complexity approximation of 8-point discrete cosine transform (DCT) that requires 18 additions and two bit-shift operations. It is shown that the proposed transform outperforms significantly the known transform of the same computational complexity when applied to a JPEG compression stream in practical cases of encoding and decoding of still images. As such, the proposed transform can be effectively used in any practical applications where significant limitations exist regarding the computational capabilities coding and / or decoding devices, i.e. mobile devices or industrial imaging devices.
Szybkie algorytmy adaptacyjne przekształceń trygonometrycznych
(Wydawnictwo Politechnika Łódzka, 2016) Puchała, Dariusz; Red. nauk. Wydziału Fizyki Technicznej, Informatyki i Matematyki Stosowanej: Poniszewska-Marańda, Aneta; Pietruszka, Maria; Lipiński, Piotr
Na treść niniejszej monografii składa się opis szybkich algorytmów adaptacyjnych dla numerycznego obliczania przekształcenia Fouriera w postaci całkowej. Jako kwadratury całkowania numerycznego wykorzystano znane dyskretne przekształcenia trygonometryczne w postaci dyskretnego przekształcenia Fouriera oraz dyskretnych przekształceń kosinusowych i sinusowych drugiego i czwartego rodzaju. Przedstawione szybkie algorytmy adaptacyjne dają możliwość obliczania zadanego pasma widma sygnału zgodnie z kryterium: dokładność- cz as realizacji obliczeń . W ramach monografii rozważa się jednocześnie przypadki sygnałów jedno- i dwuwymiarowych. Proponowane podejście może jednak zostać z powodzeniem rozszerzone na większą licz bę wymiarów.
TEWI 2021 (Technology, Education, Knowledge, Innovation)
(Lodz University of Technology Press, 2021) Wojciechowski, Adam (Ed.); Napieralski, Piotr (Ed.); Lipiński, Piotr (Ed.); Lodz University of Technology. Faculty of Technical Physics, Information Technology and Applied Mathematics Institute of Information Technology.; Byczkowska-Lipińska, Liliana; Napieralska-Juszczak, Ewa; Duraj, Agnieszka; Guskos, Andreas; Poniszewska-Marańda, Aneta; Puchała, Dariusz; Mielczarek, Jakub; Wosiak, Agnieszka
The monograph TEWI 2021 is a direct response to the demand of the industry, which looks for research projects partners. On the one hand, the material submitted for this monograph will give opportunity for the academic community to present their competencies in the thematic areas of research they conduct. On the other hand, the industry will stimulate the research development of academic staff by outlining current and future areas in the field of modern technologies. The aim of this monograph is to popularize research areas in: 1. technology (information technologies), 2. education (new methods and IT solutions implemented in education), 3. knowledge (practical applications of physics and mathematics in technical sciences), 4. innovation (transfer of new ideas between science and business). [...]