|
|
Electromagnetic analysis
Kolofík, Josef ; Reichert, Pavel (referee) ; Martinásek, Zdeněk (advisor)
This thesis deals with electromagnetic analysis and applications of electromagnetic side channel. The first and second part describes the basics of cryptography, function of cryptographic module and side-channel attacks. The third part discusses the electromagnetic analysis, construction of probe, a description of the laboratory workplace, the electromagnetic emission of PIC16F84A, AES and preparation for laboratory measurements. The fourth part describes specific laboratory measurements and extracting the useful signal. In the fifth part of the thesis presents the results of processing the measured values, the outputs generated by scripts and found the link between measured curves and AES encryption key. In the sixth part of the thesis are analyzed the basics of defense against side channel attack.
|
|
|
The use of artificial intelligence in the capital markets to reduce the risks of trading
Orság, Štěpán ; Budík, Jan (referee) ; Dostál, Petr (advisor)
This thesis deals with the prediction of trading at financial markets and by using the prediction is trying to reduce the risks of entering at the market. The prediction has been work out by using of artificial intelligence. The artificial intelligence is in this thesis represented by neural networks witch model and predict market behavior. The thesis contains a description of the financial markets, exchange trading and its analysis, and artificial intelligence methods. The main part of this thesis is a model for prediction of prices of a particular instrument. This model was developed in MATLAB and should serve as a support for making business decisions. Its aim is to predict the direction and magnitude of movement the price level for the next trading day. The output of this model is processed using the platform MetaTrader 4. At the end are evaluated possible gains from this solution.
|
|
|
The use of artificial intelligence in cryptography
Lavický, Vojtěch ; Rosenberg, Martin (referee) ; Babnič, Patrik (advisor)
Goal of this thesis is to get familiar with problematics of neural networks and commonly used security protocols in cryptography. Theoretical part of the thesis is about neural networks theory and chooses best suitable type of neural network to use in cryptographic model. In practical part, a new type of security protocol is created, using chosen neural network.
|
|
|
Artificial Intelligence
Ragas, Luděk ; Žouželková Bartošová, Marie (referee) ; Sedláček, Pavel (advisor)
Cílem této bakalářské práce je poskytnout náhled do rozsáhlého oboru umělé inteligence. Téze nejprve poskytuje definici umělé inteligence a krátký přehled její historie. Poté práce stručně popisuje technologie umělé inteligence, jako jsou neuronové sítě, expertní systémy a genetické algoritmy. Na závěr téze popisuje vliv umělé inteligence na společnost a její pozici v ní.
|
|
|
Parameter Identification for Elastic-plastic Material Models from Experimental Data
Jeník, Ivan ; Šebek, František (referee) ; Kubík, Petr (advisor)
This master's thesis deals with the identification of the material flow curve from record of tensile test of smooth cylindrical specimen. First, necessary theory background is presented. Basic terms of incremental theory of plasticity, tensile test procedure and processing its outputs are described. Furthermore, possibilities of mathematical expression of the elastic-plastic material constitutive law, thus mathematical expression of the material flow curve itself. Mechanism of ductile damage of material is explained briefly as well. Overview of recent methods of the flow curve identification is given, focused on cases, when the stress distribution in a specimen is not uniaxial. That is either kind of analytic correction of basic formulas derived for uniaxial stress state, or application of mathematical optimization techniques combined with numerical simulation of the tensile test. Also unusual method of neural network is mentioned. For 8 given materials, the flow curve identification was performed using different methods. Namely by analytic correction, optimization, sequential identification and neural network. Algorithms of the last two methods were modified. Based on assessment of obtained results, application field and adjusting the parameters of single algorithms was recommended. It showed up, that an effective way to the accurate and credible results is the combination of different methods during flow curve identification procedure.
|
|
| |
|
|
Use of HRV analysis for automatic detection of ischemia in animal isolated heart
Vykoupil, Pavel ; Vítek, Martin (referee) ; Ronzhina, Marina (advisor)
This paper deals with HRV analysis, creating segments for this analysis, calculating HRV parameters and their classification for automatic detection of ischemia. First part of the work is dedicated to theoretical describtion of heart anatomy, ECG reading, its processing and methods of HRV analysis. Next part of this work outline the principle of creating segments used for calculation of HRV parameters. Last part of the work indtroduces classification of said parameters with the help of multilayered neural networks and finding their best possible setup based on least classification error and computing time achieved. Calculation of HRV parameters and classification was realized using software Matlab.
|
|
|
Automated Design Methodology for Approximate Low Power Circuits
Mrázek, Vojtěch ; Bosio, Alberto (referee) ; Fišer, Petr (referee) ; Sekanina, Lukáš (advisor)
Rozšiřování moderních vestavěných a mobilních systémů napájených bateriemi zvyšuje požadavky na návrh těchto systémů s ohledem na příkon. Přestože moderní návrhové techniky optimalizují příkon, elektrická spotřeba těchto obvodů stále roste díky jejich složitosti. Nicméně existuje celá řada aplikací, kde nepotřebujeme získat úplně přesný výstup. Díky tomu se objevuje technika zvaná aproximativní (přibližné) počítání, která umožňuje za cenu zanesení malé chyby do výpočtu významně redukovat příkon obvodů. V práci se zaměřujeme na použití evolučních algoritmů v této oblasti. Ačkoliv již tyto algoritmy byly úspěšně použity v syntéze přesných i aproximativních obvodů, objevují se problémy škálovatelnosti - schopnosti aproximovat složité obvody. Cílem této disertační práce je ukázat, že aproximační logická syntéza založená na genetickém programování umožňuje dosáhnout vynikajícího kompromisu mezi spotřebou a chybou. Byla provedena analýza čtyř různých aplikacích na třech úrovních popisu. Pomocí kartézského genetického programování s modifikovanou reprezentací jsme snížili spotřebu malých obvodů popsaných na úrovni tranzistorů použitelných například v technologické knihovně. Dále jsme zavedli novou metodu pro aproximaci aritmetických obvodů, jako jsou sčítačky a násobičky, popsaných na úrovni hradel. S využitím metod formální verifikace navíc celý návrhový proces umožňuje garantovat stanovenou chybu aproximace. Tyto obvody byly využity pro významné snížení příkonu v neuronových sítích pro rozpoznávání obrázků a v diskrétní kosinově transformaci v HEVC kodéru. Pomocí nové chybové metriky nezávislé na rozložení vstupních dat jsme navrhli komplexní aproximativní mediánové filtry vhodné pro zpracování signálů. Disertační práce reprezentuje ucelenou metodiku pro návrh aproximativních obvodů na různých úrovních popisu, která navíc garantuje nepřekročení zadané chyby aproximace.
|
|
|
Methods of deep learning in image processing tasks
Polášková, Lenka ; Marcoň, Petr (referee) ; Mikulka, Jan (advisor)
The clue of learning to recognize objects using neural network lies in imitation of animal neural network's behavior. In spite the details of how brain works is not known yet, the teams consisting of scientists from various medical or technical professions are trying to search for them. Thanks to giants like Geoffrey Hinton science made a big progress in this domain. The convolutional networks which are based on animal model of optical system can be advantageously used for image segmentation and therefore they ware chosen for segmentation of tumor and edema from images of magnetic resonance. The models of artificial neural networks used in this work had achieved the 41\% of success in edema segmentation and 79\% in segmentation of tumor from brain issue.
|
|
|
Parallel Training of Neural Networks for Speech Recognition
Veselý, Karel ; Fousek, Petr (referee) ; Burget, Lukáš (advisor)
This thesis deals with different parallelizations of training procedure for artificial neural networks. The networks are trained as phoneme-state acoustic descriptors for speech recognition. Two effective parallelization strategies were implemented and compared. The first strategy is data parallelization, where the training is split into several POSIX threads. The second strategy is node parallelization, which uses CUDA framework for general purpose computing on modern graphic cards. The first strategy showed a 4x speed-up, while using the second strategy we observed nearly 10x speed-up. The Stochastic Gradient Descent algorithm with error backpropagation was used for the training. After a short introduction, the second chapter of this thesis shows the motivation and introduces the neural networks into the context of speech recognition. The third chapter is theoretical, the anatomy of a neural network and the used training method are discussed. The following chapters are focused on the design and implementation of the project, while the phases of the iterative development are described. The last extensive chapter describes the setup of the testing system and reports the experimental results. Finally, the obtained results are concluded and the possible extensions of the project are proposed.
|
guest ::
