|
STATISTICAL LANGUAGE MODELS BASED ON NEURAL NETWORKS
Mikolov, Tomáš ; Zweig, Geoffrey (referee) ; Hajič,, Jan (referee) ; Černocký, Jan (advisor)
Statistické jazykové modely jsou důležitou součástí mnoha úspěšných aplikací, mezi něž patří například automatické rozpoznávání řeči a strojový překlad (příkladem je známá aplikace Google Translate). Tradiční techniky pro odhad těchto modelů jsou založeny na tzv. N-gramech. Navzdory známým nedostatkům těchto technik a obrovskému úsilí výzkumných skupin napříč mnoha oblastmi (rozpoznávání řeči, automatický překlad, neuroscience, umělá inteligence, zpracování přirozeného jazyka, komprese dat, psychologie atd.), N-gramy v podstatě zůstaly nejúspěšnější technikou. Cílem této práce je prezentace několika architektur jazykových modelůzaložených na neuronových sítích. Ačkoliv jsou tyto modely výpočetně náročnější než N-gramové modely, s technikami vyvinutými v této práci je možné jejich efektivní použití v reálných aplikacích. Dosažené snížení počtu chyb při rozpoznávání řeči oproti nejlepším N-gramovým modelům dosahuje 20%. Model založený na rekurentní neurovové síti dosahuje nejlepších publikovaných výsledků na velmi známé datové sadě (Penn Treebank).
|
|
Image analysis in tribodiagnostics
Machalík, Stanislav ; Stodola,, Jiří (referee) ; Tillová,, Eva (referee) ; Zemčík, Pavel (advisor)
Image analysis of wear particles is a suitable support tool for detail analysis of engine, gear, hydraulic and industrial oils. It allows to obtain information not only of basic parameters of abrasion particles but also data that would be very difficult to obtain using classical ways of evaluation. Based on the analysis of morphological or image characteristics of particles, the progress of wearing the machine parts out can be followed and, as a result, possible breakdown of the engine can be prevented or the optimum period for changing the oil can be determined. The aim of this paper is to explore the possibilities of using the image analysis combined with the method of analytical ferrography and suggest a tool for automated particle classification. Current methods of wear particle analysis are derived from the evaluation that does not offer an exact idea of processes that take place between the friction surfaces in the engine system. The work is based upon the method of analytical ferrography which allows to evaluate the state of the machine. The benefit of use of classifiers defined in this wirk is the possibility of automated evaluation of analytical ferrography outputs; the use of them eliminates the crucial disadvantage of ferrographical analysis which is its dependence on the subjective evaluation done by the expert who performs the analysis. Classifiers are defined as a result of using the methods of machine learning. Based on an extensive database of particles that was created in the first part of the work, the classifiers were trained as a result, they make the evaluation of ferrographically separated abrasion particles from oils taken from lubricated systems possible. In the next stage, experiments were carried out and optimum classifier settings were determined based on the results of the experiments.
|
|
Physically-based Modeling and Simulation
Dvořák, Radim ; Racek, Stanislav (referee) ; Šujanský,, Milan (referee) ; Zbořil, František (advisor)
Disertační práce se zabývá modelováním znečištění ovzduší, jeho transportních a disperzních procesů ve spodní části atmosféry a zejména numerickými metodami, které slouží k řešení těchto modelů. Modelování znečištění ovzduší je velmi důležité pro předpověď kontaminace a pomáhá porozumět samotnému procesu a eliminaci následků. Hlavním tématem práce jsou metody pro řešení modelů popsaných parciálními diferenciálními rovnicemi, přesněji advekčně-difúzní rovnicí. Polovina práce je zaměřena na známou metodu přímek a je zde ukázáno, že tato metoda je vhodná k řešení určitých konkrétních problémů. Dále bylo navrženo a otestováno řešení paralelizace metody přímek, jež ukazuje, že metoda má velký potenciál pro akceleraci na současných grafických kartách a tím pádem i zvětšení přesnosti výpočtu. Druhá polovina práce se zabývá poměrně mladou metodou ELLAM a její aplikací pro řešení atmosférických advekčně-difúzních rovnic. Byla otestována konkrétní forma metody ELLAM společně s navrženými adaptacemi. Z výsledků je zřejmé, že v mnoha případech ELLAM překonává současné používané metody.
|
|
Point and Line Parameterizations Using Parallel Coordinates for Hough Transform
Juránková, Markéta ; Kälviäinen, Heikki (referee) ; Kittler, Josef (referee) ; Herout, Adam (advisor)
Tato dizertační práce se zaměřuje na použití paralelních souřadnic pro parametrizaci čar a bodů. Paralelní souřadný systém má souřadnicové osy vzájemně rovnoběžné. Bod ve dvourozměrném prostoru je v paralelních souřadnicích zobrazen jako přímka a přímka jako bod. Toho je možné využít pro Houghovu transformaci - metodu, při které body zájmu hlasují v prostoru parametrů pro danou hypotézu. Parametrizace pomocí paralelních souřadnic vyžaduje pouze rasterizaci úseček, a proto je velmi rychlá a přesná. V práci je tato parameterizace demonstrována na detekci maticových kódů a úběžníků.
|
|
Network Architecture and Interconnection of Embedded Systems
Trchalík, Roman ; Drábek, Vladimír (referee) ; Srovnal, Vilém (referee) ; Švéda, Miroslav (advisor)
The thesis focuses on the architecture of embedded systems. It summarizes the current state of accepted standards from IEEE 1451 family, which deals with creating an environment for the sensors and their involvement in various networks. These standards describe the open, network-independent communication architecture for a sensor-based system. One of the main outcomes of this work is the architectures presented as case studies, which can be used as design patters for embedded applications. They are demonstrated on ZigBee technology suitable mainly for small devices with very low power consumption. Based on these studies the new design of universal gateway was proposed. Its major advantage is that it allows interconnection of the endpoints based on different sensor network technologies. Additionally, the thesis deals with modifying the routing protocol of ZigBee network in order to reduce power consumption required to transmit one data packet.
|
|
Optimization of network flow monitoring
Žádník, Martin ; Lhotka,, Ladislav (referee) ; Matoušek, Radomil (referee) ; Sekanina, Lukáš (advisor)
The thesis deals with optimization of network flow monitoring. Flow-based network traffic processing, that is, processing packets based on some state information associated to the flows which the packets belong to, is a key enabler for a variety of network services and applications. The number of simultaneous flows increases with the growing number of new services and applications. It has become a challenge to keep a state per each flow in a network device processing high speed traffic. A flow table, a structure with flow states, must be stored in a memory hierarchy. The memory closest to the processing is known as a flow cache. Flow cache management plays an important role in terms of its effective utilization, which affects the performance of the whole system. This thesis focuses on an automated design of cache replacement policy optimized to a deployment on particular networks. A genetic algorithm is proposed to automate this process. The genetic algorithm generates and evaluates evolved replacement policies by a simulation on obtained traffic traces. The proposed algorithm is evaluated by designing replacement policies for two variations of the cache management problem. The first variation is an evolution of the replacement policy with an overall low number of state evictions from the flow cache. The second variation represents an evolution of the replacement policy with a low number of evictions belonging to large flows only. Optimized replacement policies for both variations are found while experimenting with various encoding of the replacement policy and genetic operators. The newly evolved replacement policies achieve better results than other tested policies. The evolved replacement policy lowers the overall amount of evictions by ten percent in comparison with the best compared policy. The evolved replacement policy focusing on large flows lowers the amount of their evictions two times. Moreover, no eviction occurs for most of the large flows (over 90%). The evolved replacement policy offers better resilience against flooding the flow cache with large amount of short flows which are typical side effects of scanning or distributed denial of service activities. An extension of the replacement policy is also proposed. The extension complements the replacement policy with an additional information extracted from packet headers. The results show further decrease in the number of evictions when the extension is used.
|
|
Effective using of potential of bilingual environment
HOVORKOVÁ, Eva
The dissertation thesis "How to use the potential of bilingual environment efficiently" endeavors to highlight bad as well as good practices in bilingual upbringing. Bilingualism represents at present a very topical issue. In connection with increasing globalization, the issue of learning of foreign languages is more and more emphasised. People living in mixed marriages have often no idea how to bring their children up. In many cases they take steps that lead to irreversible consequences. The theoretical part of the thesis gives a survey of bilingualism, the division and kinds of bilingualism and ways of its acquisiton. The theory is practically illustrated in the empirical part through various examples. 42 case studies have been carried out, which include characteristic and uncharacteristic respondents. The findings of the research are compared with the facts mentioned in the reference works. The aim of the dissertation thesis is to find out which educational methods should parents follow in bilingual education and which methods they should better avoid.
|
|
The prevention of pathological occurence of burnout syndrome (an example of employer)
BLAHOVÁ, Nela
This bachelor thesis deals with the issue of burnout syndrome which is currently a very discuss frequent problem. The rate of working stress will be investigated in selected groups of staff in company COOP družstvo HB. The purpose of my thesis is to compare which group of staff is threatened by burnout syndrome the most. The work is focused on the economical aspects which are reflected particularly in human capital. There will be applied the quantitative research, concretely questionaire research. Based on the results of questionaire research will be applied analytical method of the job evaluation, which is one of the main issues of human resources management. This application will be also recommendation for prevention for the company.
|
|
Faktory ovlivňující poptávku po osobních automobilech v ČR
ČURILLOVÁ, Michaela
The bachelor thesis investigates factors which influence the demand for passenger cars in the Czech Republic. The theoretical part of this work is focused on basic terms and determinants which are important for the demand. Further it describes particular statistical methods, which are used for the analysis. The practical part contains the introduction to the automotive industry and the description of specific attributes of the demand for passenger cars. This part analyses factors which may have an effect on the demand for passenger cars in the Czech Republic. The main factors and the dependence are explained by applying econometric methods. Analyzing reveals these important factors: number of registrations of passenger cars, consumer prices of new and used passenger cars, consumer prices of fuel, population and income.The conclusion contains the summary of impacts on the specific demand.
|
|
Application of Queueing Theory
VÁŇOVÁ, Eliška
The goal of this thesis was to understand Queueing Theory and use it for analysis of queueing system of hypermarket company PZV. Theoretical part is consists of basic iformations which is necessary to know for application of queueing theory. First chapter is about random variables, random event, random proces, stochastic and Poisson processes and Markov chains. Then was possible to describe queueing theory basic characteristics, parameters, analy-sis, classification and basic models. In the practical part was from the beginning analyze development of custo-mers going through cashier zone. On the base of analysis were customers divided into 4 groups. For these groups were counted characteristics and parameters, next was analyzed the system, but because data were too inaccurate, it was necessary to use different values for the groups and to count analysis for these values. The last step was to find number of cashiers to make system optimal. The result, it was 4 ca-shiers, was unfortunately not accurate. For better results it would be necessary to have more detail data.
|
guest ::
