13 results on '"Daniel Kuchár"'
Search Results
2. Convolutional Networks Used to Classify Video and Audio Data
- Author
-
Daniel Kuchár, Marcel Nikmon, Roman Budjač, Dagmar Janáčová, and Peter Schreiber
- Subjects
0209 industrial biotechnology ,business.industry ,Computer science ,Deep learning ,Speech recognition ,020208 electrical & electronic engineering ,convolutional neural network ,deep learning ,02 engineering and technology ,Convolutional neural network ,020901 industrial engineering & automation ,audio-visual data ,classification ,0202 electrical engineering, electronic engineering, information engineering ,alexnet ,lcsh:TA401-492 ,lcsh:Materials of engineering and construction. Mechanics of materials ,Artificial intelligence ,business - Abstract
Deep learning is a kind of machine learning, and machine learning is a kind of artificial intelligence. Machine learning depicts groups of various technologies, and deep learning is one of them. The use of deep learning is an integral part of the current data classification practice in today’s world. This paper introduces the possibilities of classification using convolutional networks. Experiments focused on audio and video data show different approaches to data classification. Most experiments use the well-known pre-trained AlexNet network with various pre-processing types of input data. However, there are also comparisons of other neural network architectures, and we also show the results of training on small and larger datasets. The paper comprises description of eight different kinds of experiments. Several training sessions were conducted in each experiment with different aspects that were monitored. The focus was put on the effect of batch size on the accuracy of deep learning, including many other parameters that affect deep learning [1].
- Published
- 2019
3. Intersection as an Event- and Agent-Based System
- Author
-
Daniel Kuchár and Peter Schreiber
- Subjects
Source code ,Discretization ,Event (computing) ,Computer science ,media_common.quotation_subject ,Distributed computing ,Complex system ,Stateflow ,Intersection ,MATLAB ,computer ,media_common ,computer.programming_language ,Abstraction (linguistics) - Abstract
The paper presents the capabilities of Matlab/Simulink environment, namely the toolboxes Stateflow and SimEvents, of modelling the event- and agent-based systems in the shape of a symmetrical intersection at a micro-scale level. This simple but complex system deals with a random occurrence of the agents (the traffic participants), their own behaviour patterns, given road traffic regulations and a discretization of the intersection space model. The goal consists in proposing of a control algorithm, simulating of its function at a given model abstraction, and finally, generating a programming code for a PLC. With this kind of an approach, it is possible to work within one development environment with the systems which are impossible to be solved analytically and whose real testing is time and effort consuming.
- Published
- 2021
4. Comparison of UAV Landing Site Classifications with Deep Neural Networks
- Author
-
Peter Schreiber and Daniel Kuchár
- Subjects
Computer science ,business.industry ,Deep learning ,SIGNAL (programming language) ,Process (computing) ,Deep neural networks ,Context (language use) ,Computer vision ,Terrain ,Artificial intelligence ,Zoom ,business ,Running time - Abstract
The paper compares classification results of three deep neural networks: AlexNet, VGG16 and VGG19 for ten classes of a UAV landing site with respect to accuracy, memory requirements, and a typical running time. The overall results offer an insight into typical false friends among particular classes of landing site and a zooming technique for better understanding of a surrounding context in a landing situation. The algorithm presents just one of alternatives how to find out if the appropriate terrain is suitable for landing or not by means of an optical way. Nowadays, this kind of sensing is generally present on every single piece of UAV in the shape of a camera which could be easily adopted to the purpose of an automatic landing. All above, when an emergency of a loss of the controlling signal arises. The process of the training set preparation is described, too.
- Published
- 2021
5. Matlab Code Generation and Consumption
- Author
-
Martin Bartoň, Daniel Kuchár, Pavol Tanuska, and Peter Schreiber
- Subjects
Computer science ,Order (business) ,Virtual machine ,Programming language ,Code (cryptography) ,Process (computing) ,Independence (mathematical logic) ,Matlab code ,MATLAB ,computer.software_genre ,Programmer ,computer ,computer.programming_language - Abstract
During the complex application development, it is necessary to deploy various programming languages in order to utilize their strengths. The paper presents Matlab code generation for the purpose of signal filtering by means of .dll creation. Stress is put on the speed of a code execution and independence of a virtual machine (Matlab Runtime). Comfortable and quick code development in Matlab environment is able to unburden a programmer from a detailed study process of quite often complicated physical principle of the problematics and makes possible to deploy once developed and debugged code in a new environment, too. Two ways of a code generation are presented: automatic and manual. The automatic way was easy and represented an immediate use of the generated code but only in case of 64bit version. Contrary to this, the automatic generation of a 32bit version had its drawbacks. We proposed a manual universal way for overcoming all of these drawbacks irrespective to the 32bit or 64bit version. Moreover, the paper presents the side of the Matlab code consumers, too. All of the presented principles could serve for other purpose, not only for a signal filtering.
- Published
- 2020
6. Spin Axis Determination of Defunct GLONASS Satellites Using Photometry Observation
- Author
-
Jeeho Lee, Eunseo Park, Man-Soo Choi, Daniel Kucharski, Yu Yi, and Jong-Uk Park
- Subjects
spin axis ,glonass ,Astronomy ,QB1-991 - Abstract
GLONASS, a satellite navigation system developed in Russia since 1976, is defunct and orbits in an unstable attitude. The satellites in these problems are not managed and there is no precise information, which can increase the risk of collisions with other space objects. In this study, detailed attitude dynamic have to be analyzed through photometry data, which requires spin period and spin axis. The light curve data is obtained by observing through the photometer at the Graz station and the power spectrum is calculated to obtain the cycle of the satellite. The geometric relationship between observer and sun is analyzed for GLONASS-50 satellite. The box-wing model is applied to obtain the phase reflection of the satellite and obtain the Irradiation of the satellite through this information. In Light Curve and Irradiation, the spin axis is calculated for each peak points with the distance square minimum technique. The spin axis of the GLONASS-50 satellite is RA = 116°, Dec = 92°.
- Published
- 2021
- Full Text
- View/download PDF
7. Moderate- to high intensity aerobic and resistance exercise reduces peripheral blood regulatory cell populations in older adults with rheumatoid arthritis
- Author
-
Sofia E. M. Andersson, Elvira Lange, Daniel Kucharski, Sara Svedlund, Karin Önnheim, Maria Bergquist, Elisabet Josefsson, Janet M. Lord, Inga-Lill Mårtensson, Kaisa Mannerkorpi, and Inger Gjertsson
- Subjects
Rheumatoid arthritis ,Aging ,Exercise ,Treg cells ,T cells ,Breg cells ,Immunologic diseases. Allergy ,RC581-607 ,Geriatrics ,RC952-954.6 - Abstract
Abstract Objective Exercise can improve immune health and is beneficial for physical function in patients with rheumatoid arthritis (RA), but the immunological mechanisms are largely unknown. We evaluated the effect of moderate- to high intensity exercise with person-centred guidance on cells of the immune system, with focus on regulatory cell populations, in older adults with RA. Methods Older adults (≥65 years) with RA were randomized to either 20-weeks of moderate – to high intensity aerobic and resistance exercise (n = 24) or to an active control group performing home-based exercise of light intensity (n = 25). Aerobic capacity, muscle strength, DAS28 and CRP were evaluated. Blood samples were collected at baseline and after 20 weeks. The frequency of immune cells defined as adaptive regulatory populations, CD4 + Foxp3 + CD25 + CD127- T regulatory cells (Tregs) and CD19 + CD24hiCD38hi B regulatory cells (Bregs) as well as HLA-DR−/lowCD33 + CD11b + myeloid derived suppressor cells (MDSCs), were assessed using flow cytometry. Results After 20 weeks of moderate- to high intensity exercise, aerobic capacity and muscle strength were significantly improved but there were no significant changes in Disease Activity Score 28 (DAS28) or CRP. The frequency of Tregs and Bregs decreased significantly in the intervention group, but not in the active control group. The exercise intervention had no effect on MDSCs. The reduction in regulatory T cells in the intervention group was most pronounced in the female patients. Conclusion Moderate- to high intensity exercise in older adults with RA led to a decreased proportion of Tregs and Bregs, but that was not associated with increased disease activity or increased inflammation. Trial registration Improved Ability to Cope With Everyday Life Through a Person-centered Training Program in Elderly Patients With Rheumatoid Arthritis - PEP-walk Study, NCT02397798 . Registered at ClinicalTrials.gov March 19, 2015.
- Published
- 2020
- Full Text
- View/download PDF
8. Segmentation and Classification of Zn-Al-Mg-Sn SEM BSE Microstructure
- Author
-
Daniel Kuchar, Peter Gogola, Zuzana Gabalcova, Andrea Nemethova, and Martin Nemeth
- Subjects
SEM ,BSE ,microstructure ,classification ,Zn-Al-Mg-Sn alloy ,image processing ,Technology ,Engineering (General). Civil engineering (General) ,TA1-2040 ,Biology (General) ,QH301-705.5 ,Physics ,QC1-999 ,Chemistry ,QD1-999 - Abstract
The microstructure of materials is shaped not only by their chemical composition, but also by the thermomechanical processes used during the processing of a specific piece. The correct interpretation of the microstructure gives a rich source of information. This consists of several related steps, such as segmentation. Successful segmentation enables the qualitative as well as quantitative analysis of the individual microstructure components. The current paper deals with the segmentation and classification of four basic microstructure components of the Zn-Al-Mg-Sn alloy system. This is attempted with the help of several image processing techniques, where thresholding is the main one used. The investigated samples are the cast and annealed Zn-Al-Mg-Sn alloy bulks. The input data for this analysis are the SEM BSE images. These were taken for all alloys with a varying Sn content, covering a significant area of each investigated sample at different zoom levels. A semiautomatic algorithm running under Matlab is introduced. It addresses several tasks, such as preprocessing, noise filtering and decision methods. For the individual procedures, the time requirements for their execution are also indicated.
- Published
- 2023
- Full Text
- View/download PDF
9. The Importance of Economic Security in Shaping Cultural Behaviors Influenced by Progressive Globalization Processes
- Author
-
Daniel Kucharek
- Subjects
economic security ,culture ,migration ,safety ,Technology - Abstract
One of the most transparent manifestations of globalization processes currently occurring is the phenomenon of economic migration. It is associated with the movement of large masses of people from poor, economically underdeveloped regions often disturbed by armed conflicts to economically developed countries with already shaped prosperity. Migration processes pose many economic, social and cultural problems that discourage the population of wealthy countries from receiving incoming migrants. This article was organized in order to firstly consider the impact of economic migration on the phenomenon of changes in the population structure and thus cultural changes that might result from it. The next stage of the conducted analysis refers to the problem of commodification of artworks created within the area of culture. An important effect of the conducted research is to draw attention to the phenomenon of blurring differences, and, as a result, the emergence of widely accepted, supranational cultural patterns. Finally, the undertaken research identifies possible opportunities and threats for sustainable development of culture on an economically diverse world.
- Published
- 2020
- Full Text
- View/download PDF
10. Comparison of Mechanical and Barrier Properties of Al2O3/TiO2/ZrO2 Layers in Oxide–Hydroxyapatite Sandwich Composite Coatings Deposited by Sol–Gel Method on Ti6Al7Nb Alloy
- Author
-
Bożena Pietrzyk, Daniel Kucharski, Łukasz Kołodziejczyk, Sebastian Miszczak, and Mateusz Fijalkowski
- Subjects
hydroxyapatite ,oxide ,layered ,composite ,coating ,sol–gel ,barrier ,permeation ,Technology ,Electrical engineering. Electronics. Nuclear engineering ,TK1-9971 ,Engineering (General). Civil engineering (General) ,TA1-2040 ,Microscopy ,QH201-278.5 ,Descriptive and experimental mechanics ,QC120-168.85 - Abstract
In this study, coatings of different oxides (TiO2, Al2O3, ZrO2) and hydroxyapatite (HAp) as well as sandwich composite hydroxyapatite with an oxides sublayer (oxide+HAp) were deposited on Ti6Al7Nb alloy using the sol−gel dip-coating method. The coatings were characterized in terms of morphology (optical microscope), surface topography (AFM), thickness (ellipsometry), and crystal structure (XRD/GIXRD). The mechanical properties of the coatings—hardness, Young’s modulus, and adhesion to the substrate—were examined using nanoindentation and scratch tests. The barrier properties of the coatings against the migration of aluminum ions were examined by measuring their concentration after soaking in Hank’s balanced salt solution (HBSS) with the use of optical emission spectrometry of inductively coupled plasma (ICPOES). It was found that all the oxide and HAp coatings reduced the permeation of Al ions from the Ti6Al7Nb alloy substrate. The best features revealed an Al2O3 layer that had excellent barrier properties and the best adhesion to the substrate. Al2O3 as a sublayer significantly improved the properties of the sandwich composite HAp coating.
- Published
- 2020
- Full Text
- View/download PDF
11. Orbit Determination Using SLR Data for STSAT-2C:Short-arc Analysis
- Author
-
Young-Rok Kim, Eunseo Park, Daniel Kucharski, and Hyung-Chul Lim
- Subjects
orbit determination ,satellite laser ranging ,STSAT-2C ,GEODYN II ,sparse ,short-arc ,Astronomy ,QB1-991 - Abstract
In this study, we present the results of orbit determination (OD) using satellite laser ranging (SLR) data for the Science and Technology Satellite (STSAT)-2C by a short-arc analysis. For SLR data processing, the NASA/GSFC GEODYN II software with one year (2013/04 – 2014/04) of normal point observations is used. As there is only an extremely small quantity of SLR observations of STSAT-2C and they are sparsely distribution, the selection of the arc length and the estimation intervals for the atmospheric drag coefficients and the empirical acceleration parameters was made on an arc-to-arc basis. For orbit quality assessment, the post-fit residuals of each short-arc and orbit overlaps of arcs are investigated. The OD results show that the weighted root mean square post-fit residuals of short-arcs are less than 1 cm, and the average 1-day orbit overlaps are superior to 50/600/900 m for the radial/cross-track/along-track components. These results demonstrate that OD for STSAT-2C was successfully achieved with cm-level range precision. However its orbit quality did not reach the same level due to the availability of few and sparse measurement conditions. From a mission analysis viewpoint, obtaining the results of OD for STSAT-2C is significant for generating enhanced orbit predictions for more frequent tracking.
- Published
- 2015
- Full Text
- View/download PDF
12. Performance Analysis of the First Korean Satellite Laser Ranging System
- Author
-
Man-Soo Choi, Hyung-Chul Lim, Eun-Jung Choi, Eunseo Park, Sung-Yeol Yu, Seong-Cheol Bang, Tae-Keun Kim, Young-Rok Kim, Dong-Jin Kim, Kipyung Seong, Neung-Hyun Ka, Cer-Hee Choi, Joo-Yeon Hwang, Daniel Kucharski, In-Woo Han, Jakyoung Nah, Jung-Guen Jang, Bi-Ho Jang, and Sang-Jung Lee
- Subjects
SLR station ,satellite laser ranging ,single-shot ranging precision ,space geodesy ,Astronomy ,QB1-991 - Abstract
The first Korean satellite laser ranging (SLR) system, Daedeok SLR station (DAEK station) was developed by Korea Astronomy and Space Science Institute (KASI) in 2012, whose main objectives are space geodesy researches. In consequence, Korea became the 25th country that operates SLR system supplementing the international laser tracking network. The DAEK station is designed to be capable of 2 kHz laser ranging with precision of a few mm both in daytime and nighttime observation of satellites with laser retro-reflector array (LRA) up to the altitude of 25,000 km. In this study, characteristics and specifications of DAEK station are investigated and its data quality is evaluated and compared with International Laser Ranging Service (ILRS) stations in terms of single-shot ranging precision. The analysis results demonstrated that the DAEK station shows good ranging performance to a few mm precision. Currently, the DAEK station is under normal operations at KASI headquarters, however, it will be moved to Sejong city in 2014 to function as a fundamental station for space geodesy researches in combination with other space geodesy systems (GNSS, VLBI, DORIS, etc.).
- Published
- 2014
- Full Text
- View/download PDF
13. Stochastic Modelling as a Tool for Seismic Signals Segmentation
- Author
-
Daniel Kucharczyk, Agnieszka Wyłomańska, Jakub Obuchowski, Radosław Zimroz, and Maciej Madziarz
- Subjects
Physics ,QC1-999 - Abstract
In order to model nonstationary real-world processes one can find appropriate theoretical model with properties following the analyzed data. However in this case many trajectories of the analyzed process are required. Alternatively, one can extract parts of the signal that have homogenous structure via segmentation. The proper segmentation can lead to extraction of important features of analyzed phenomena that cannot be described without the segmentation. There is no one universal method that can be applied for all of the phenomena; thus novel methods should be invented for specific cases. They might address specific character of the signal in different domains (time, frequency, time-frequency, etc.). In this paper we propose two novel segmentation methods that take under consideration the stochastic properties of the analyzed signals in time domain. Our research is motivated by the analysis of vibration signals acquired in an underground mine. In such signals we observe seismic events which appear after the mining activity, like blasting, provoked relaxation of rock, and some unexpected events, like natural rock burst. The proposed segmentation procedures allow for extraction of such parts of the analyzed signals which are related to mentioned events.
- Published
- 2016
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.