handle: 11012/200792
In this paper, we present two pipelines in order to reduce the feature space for anomalydetection using the One Class SVM. As a first stage of both pipelines, we compare the performanceof three convolutional autoencoders. We use the PCA method together with t-SNE as the first pipelineand the reconstruction errors based method as the second. Both methods have potential for theanomaly detection, but the reconstruction error metrics prove to be more robust for this task. Weshow that the convolutional autoencoder architecture doesn’t have a significant effect for this task andwe prove the potential of our approach on the real world dataset.
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/200792&type=result"></script>');
-->
</script>
citations | 0 | |
popularity | Average | |
influence | Average | |
impulse | Average |
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/200792&type=result"></script>');
-->
</script>
handle: 11012/200770
We propose the model combining convolutional neural network with multiple instancelearning in order to localize the premature atrial contraction and premature ventricular contraction.The model is based on ResNet architecture modified for 1D signal processing. Model was trainedon China Physiological Signal Challenge 2018 database extended by manually labeled ground truthpositions of premature complexes. The presented method did not reach satisfying results in PAClocalization (with dice = 0.127 for avg-pooling implementation). On the other hand, results of localizationof PVCs were comparable with other published studies (with dice = 0.952 for avg-poolingimplementation).
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/200770&type=result"></script>');
-->
</script>
citations | 0 | |
popularity | Average | |
influence | Average | |
impulse | Average |
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/200770&type=result"></script>');
-->
</script>
handle: 11012/247738
This thesis focuses on utilizing image data of tree trunk damage to train a classifier for recognizing species of tree pests that caused this damage. The classifier is designed as a convolutional neural network. To successfully train the model, a preprocessing step - the sub-image generator - was employed before the classifier. This generator creates training data of suitable dimensions by cropping from the original data. The resulting data retains important details for network training. Two methods for generating training sub-images were proposed for the sub-image generator - the Grid division method and the Elliptic division method. Both of these methods can be successfully used to train the classifier for tree pest recognition based on image data of tree damage with comparable model accuracy. The Elliptic division method is more flexible and less time-consuming for preprocessing training data. Tato diplomová práce se věnuje využití obrazových dat poškození kmene stromu k natrénování klasifikátoru pro rozpoznávání druhů škůdců stromů, které toto poškození způsobili. Klasifikátor je navrhnut jako konvoluční neuronová síť. Pro úspěšné natrénování modelu byl klasifikátoru předřazen preprocesingový krok – sub-image generátor. Tento generátor vytváří tréninková data o vhodných rozměrech pomocí výřezů z původních dat. Takto vzniklá data zachovávají důležité detaily pro trénování sítě. Pro sub-image generátor byly navrženy dvě metody vytváření trénovacích pod-obrazů – Grid division method a Elliptic division method. Obě tyto metody lze úspěšně použít pro natrénování klasifikátoru škůdců stromů na základě obrazových dat poškození stromu se srovnatelnou přesností modelu. Metoda Elliptic division je flexibilnější a méně časově náročná na preprocesing trénovacích dat. A
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/247738&type=result"></script>');
-->
</script>
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/247738&type=result"></script>');
-->
</script>
handle: 11012/186685
SILON s.r.o is manufacturer of polyester fibres which get used in wide range of applications, many of them requiring highest quality material. Due to manufacturing processes, some fibres are not drawn properly and stay in the fiber as bundles, or brittle, thick threads. Proposed lab station should automate process of quality check of each batch. It consists of linescan camera scanner and computer with software for detection and analysis of defects.
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/186685&type=result"></script>');
-->
</script>
citations | 0 | |
popularity | Average | |
influence | Average | |
impulse | Average |
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/186685&type=result"></script>');
-->
</script>
handle: 11012/56493
Hlavním cílem této práce bylo navrhnout a vytvořit systém sledování osob s aplikací v oboru bezpečnosti nebo pro analýzu chování zákazníka v obchodě. Systém byl úspěšně implementován pomocí metod KLT trekování, AdaBoost klasifikátoru a datové asociace pomocí Markovských řetězců a metody Monte Carlo. Implementace umožňuje analýzu pohybu lidí ve vnitřních i vnějších prostorech. The main goal of this thesis is to develop multi-target tracking system for use in field of security surveillance or for customer behavior analysis. The system was successfully implemented using KLT tracking, AdaBoost classifier and Markov Chain Monte Carlo data association. It is able to perform analysis of motion of people in both outdoor and indoor environment. C
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/56493&type=result"></script>');
-->
</script>
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/56493&type=result"></script>');
-->
</script>
handle: 11012/138235
This work deals with the use of a convolutional neural network in the area of segmentation of images acquired with the use of a transmission electron microscope. Paper describes programming tool for image data augmentation, used neural network topology, and it also provides information about model training. This neural network topology delivered excellent results on provided data from the Thermo Fisher Scientific company, which will serve as a starting point for internal company research in image segmentation area.
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/138235&type=result"></script>');
-->
</script>
citations | 0 | |
popularity | Average | |
influence | Average | |
impulse | Average |
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/138235&type=result"></script>');
-->
</script>
handle: 11012/199322
This thesis aims to implement a method of detecting the horizon line in images using deep learning to prevent any constraints on input data. A training dataset is created by downloaded images from large metropolitan cities around the world using the Google Street View service. Several popular architectures for convolutional neural networks are chosen, and their performance is evaluated on existing benchmark datasets. Cieľom tejto práce je naimplementovať metódu detekovania horizontu vo fotografii pomocou hlbokého učenia, aby sa zabránilo obmedzeniam pre vstupné dáta. Trénovací dataset bol vytvorený sťahovaním obrázkov z miest z celého sveta pomocou služby Google Street View. Bolo vybratých niekoľko populárnych architektúr pre konvolučné neurónové siete a po natrénovaní boli vyhodnotené na existujúcich testovacích datasetoch. C
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/199322&type=result"></script>');
-->
</script>
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/199322&type=result"></script>');
-->
</script>
handle: 11012/248549
Convolutional Neural Networks (CNNs) have revolutionised computer vision field since their introduction. By replacing weights with convolution filters containing trainable weights, CNNs significantly reduced memory usage. However, this reduction came at the cost of increased computational resource requirements, as convolution operations are more computation intensive. Despite this, memory usage remains more energy-intensive than computation. This thesis explores whether it is possible to avoid loading weights from memory and instead functionally calculate them, thereby saving energy. To test this hypothesis, a novel weight compression algorithm was developed using Cartesian Genetic Programming. This algorithm searches for the most optimal weight compression function, aiming to enhance energy efficiency without compromising the functionality of the neural network. Experiments conducted on the LeNet-5 and MobileNetV2 architectures demonstrated that the algorithm could effectively reduce energy consumption while maintaining high model accuracy. The results showed that certain layers could benefit from weight computation, validating the potential for energy-efficient neural network implementations. Konvolučné neurónové siete (CNN) od svojho vynájdenia zrevolucionizovali spôsob, akým sa realizujú úlohy z odvetvia počítačového videnia. Vynález CNN viedol k zníženiu pamäťovej náročnosti, keďže váhy boli nahradené konvolučnými filtrami obsahujúcimi menej trénovateľných váh. Avšak, toto zníženie bolo dosiahnuté na úkor zvýšenia požiadaviek na výpočtový výkon, ktorý je naviazaný na výpočet konvolúcie. Táto práca skúma hypotézu, či je možné sa vyhnúť načítavaniu váh a miesto toho ich vypočítať, čím sa ušetrí energia. Na otestovanie tejto hypotézy bol vyvinutý nový algoritmus kompresie váh využívajúci Kartézske genetické programovanie. Tento algoritmus hľadá najoptimálnejšiu funkciu kompresie váh s cieľom zvýšiť energetickú účinnosť. Experimenty vykonané na architektúrach LeNet-5 a MobileNetV2 ukázali, že algoritmus dokáže efektívne znížiť spotrebu energie pri zachovaní vysokej presnosti modelu. Výsledky ukázali, že určité vrstvy je možné doplniť vypočítanými váhami, čo potvrdzuje potenciál pre energeticky efektívne neurónové siete. B
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/248549&type=result"></script>');
-->
</script>
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/248549&type=result"></script>');
-->
</script>
handle: 11012/212667
This thesis is devoted to the mitigation of multiple types of DoS attacks. Our aim was to create a custom apache module that is able to mitigate flood attacks as well as logical attacks. The module was created in C language using VS Code. After creating the module we ran multiple tests to gather data in order to be able to compare our module to already existing apache modules. Comparing the test result we concluded that our module is able to mitigate both types of attacks. The results of the tests are visualized using graphs in the appendix. Táto práca sa venuje mitigácii viacerých typov útokov DoS. Naším cieľom bolo vytvoriť vlastný modul apache, ktorý dokáže zmierniť útoky typu flood, ako aj logické útoky. Modul bol vytvorený v jazyku C pomocou programu VS Code. Po vytvorení modulu sme vykonali viacero testov na získanie údajov, aby sme mohli náš modul porovnať s už existujúcimi modulmi apache. Porovnaním výsledkov testov sme dospeli k záveru, že náš modul dokáže zmierniť oba typy útokov. Výsledky testov sú vizualizované pomocou grafov v prílohe. E
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/212667&type=result"></script>');
-->
</script>
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/212667&type=result"></script>');
-->
</script>
handle: 11012/209305
To protect the vineyards from starlings is very costly and ineffective with the available resources. In my work, I have designed a detection module which consist of four microphones, each one is directed to the cardinal point and based on the intensity of sound, the module will provide the information about the direction where the flock is located, in the vineyard that passes to the control module and scares the flocks. The detection module processes the signal in a Raspberry Pi 4 single board computer using an artificial neural network algorithm.
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/209305&type=result"></script>');
-->
</script>
citations | 0 | |
popularity | Average | |
influence | Average | |
impulse | Average |
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/209305&type=result"></script>');
-->
</script>
handle: 11012/200792
In this paper, we present two pipelines in order to reduce the feature space for anomalydetection using the One Class SVM. As a first stage of both pipelines, we compare the performanceof three convolutional autoencoders. We use the PCA method together with t-SNE as the first pipelineand the reconstruction errors based method as the second. Both methods have potential for theanomaly detection, but the reconstruction error metrics prove to be more robust for this task. Weshow that the convolutional autoencoder architecture doesn’t have a significant effect for this task andwe prove the potential of our approach on the real world dataset.
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/200792&type=result"></script>');
-->
</script>
citations | 0 | |
popularity | Average | |
influence | Average | |
impulse | Average |
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/200792&type=result"></script>');
-->
</script>
handle: 11012/200770
We propose the model combining convolutional neural network with multiple instancelearning in order to localize the premature atrial contraction and premature ventricular contraction.The model is based on ResNet architecture modified for 1D signal processing. Model was trainedon China Physiological Signal Challenge 2018 database extended by manually labeled ground truthpositions of premature complexes. The presented method did not reach satisfying results in PAClocalization (with dice = 0.127 for avg-pooling implementation). On the other hand, results of localizationof PVCs were comparable with other published studies (with dice = 0.952 for avg-poolingimplementation).
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/200770&type=result"></script>');
-->
</script>
citations | 0 | |
popularity | Average | |
influence | Average | |
impulse | Average |
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/200770&type=result"></script>');
-->
</script>
handle: 11012/247738
This thesis focuses on utilizing image data of tree trunk damage to train a classifier for recognizing species of tree pests that caused this damage. The classifier is designed as a convolutional neural network. To successfully train the model, a preprocessing step - the sub-image generator - was employed before the classifier. This generator creates training data of suitable dimensions by cropping from the original data. The resulting data retains important details for network training. Two methods for generating training sub-images were proposed for the sub-image generator - the Grid division method and the Elliptic division method. Both of these methods can be successfully used to train the classifier for tree pest recognition based on image data of tree damage with comparable model accuracy. The Elliptic division method is more flexible and less time-consuming for preprocessing training data. Tato diplomová práce se věnuje využití obrazových dat poškození kmene stromu k natrénování klasifikátoru pro rozpoznávání druhů škůdců stromů, které toto poškození způsobili. Klasifikátor je navrhnut jako konvoluční neuronová síť. Pro úspěšné natrénování modelu byl klasifikátoru předřazen preprocesingový krok – sub-image generátor. Tento generátor vytváří tréninková data o vhodných rozměrech pomocí výřezů z původních dat. Takto vzniklá data zachovávají důležité detaily pro trénování sítě. Pro sub-image generátor byly navrženy dvě metody vytváření trénovacích pod-obrazů – Grid division method a Elliptic division method. Obě tyto metody lze úspěšně použít pro natrénování klasifikátoru škůdců stromů na základě obrazových dat poškození stromu se srovnatelnou přesností modelu. Metoda Elliptic division je flexibilnější a méně časově náročná na preprocesing trénovacích dat. A
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/247738&type=result"></script>');
-->
</script>
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/247738&type=result"></script>');
-->
</script>
handle: 11012/186685
SILON s.r.o is manufacturer of polyester fibres which get used in wide range of applications, many of them requiring highest quality material. Due to manufacturing processes, some fibres are not drawn properly and stay in the fiber as bundles, or brittle, thick threads. Proposed lab station should automate process of quality check of each batch. It consists of linescan camera scanner and computer with software for detection and analysis of defects.
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/186685&type=result"></script>');
-->
</script>
citations | 0 | |
popularity | Average | |
influence | Average | |
impulse | Average |
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/186685&type=result"></script>');
-->
</script>
handle: 11012/56493
Hlavním cílem této práce bylo navrhnout a vytvořit systém sledování osob s aplikací v oboru bezpečnosti nebo pro analýzu chování zákazníka v obchodě. Systém byl úspěšně implementován pomocí metod KLT trekování, AdaBoost klasifikátoru a datové asociace pomocí Markovských řetězců a metody Monte Carlo. Implementace umožňuje analýzu pohybu lidí ve vnitřních i vnějších prostorech. The main goal of this thesis is to develop multi-target tracking system for use in field of security surveillance or for customer behavior analysis. The system was successfully implemented using KLT tracking, AdaBoost classifier and Markov Chain Monte Carlo data association. It is able to perform analysis of motion of people in both outdoor and indoor environment. C
<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=11012/56493&type=result"></script>');
-->
</script>