|
Acceleration of Object Detection Using Classifiers
Juránek, Roman ; Kälviäinen, Heikki (referee) ; Sojka, Eduard (referee) ; Zemčík, Pavel (advisor)
Detekce objektů v počítačovém vidění je složítá úloha. Velmi populární a rozšířená metoda pro detekci je využití statistických klasifikátorů a skenovacích oken. Pro učení kalsifikátorů se často používá algoritmus AdaBoost (nebo jeho modifikace), protože dosahuje vysoké úspěšnosti detekce, nízkého počtu chybných detekcí a je vhodný pro detekci v reálném čase. Implementaci detekce objektů je možné provést různými způsoby a lze využít vlastnosti konkrétní architektury, pro urychlení detekce. Pro akceleraci je možné využít grafické procesory, vícejádrové architektury, SIMD instrukce, nebo programovatelný hardware. Tato práce představuje metodu optimalizace, která vylepšuje výkon detekce objektů s ohledem na cenovou funkci zadanou uživatelem. Metoda rozděluje předem natrénovaný klasifikátor do několika různých implementací, tak aby celková cena klasifikace byla minimalizována. Metoda je verifikována na základním experimentu, kdy je klasifikátor rozdělen do předzpracovací jednotku v FPGA a do jednotky ve standardním PC.
|
|
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.
|
|
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.
|
|
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.
|
|
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.
|
|
Project management in selected company
POKORNÝ, Radek
This work deals with project management in chosen company. It has two parts. The first part is theoretical, which is focused to theoretical treatment of the subject. It explains what is the project, management of projects, organizations of projects, processes of project management, what is target of project, communication, control, changes and risks and more. In the practical part I focused to concrete company and project management and than I analyzed concrete project. Name of the mentioned company is OHL ŽS, a.s. It is company from Spain, which acts all over the world. In the Czech Republic has the base in Brno. This company has several divisions and every of them is focused to different professional architecture. I have chosen division of structural engineering. This division builds all kinds of buildings. It could be construction of new buildings or reconstruction. To analysis of chosen project I used various business documents, contracts with investor or suppliers, document which include billing, timetable. I especially used my experience with projects of this company, and I was part of this project. Name of this project is Reconstruction of cladding including replacement windows and insulation. During the analysis of project I found a couple major gaps. If we could avoid these gaps, we could increase profit. These graphs is especially in management. At the beginning there were appointed two temporary construction managers. They doesn't care about result project, because they knew that they will not be to the end of the project. These gaps are because there is missing motivation system. Project manager can´t affect results of employees. It doesn´t depend on performance of employees, they always has the same wages. For elimination of these gaps I proposed several suggestions for improvement. The first suggestion is modification and extension of motivation system. New motivation system include personal evaluation. This evaluation depends on performance of employee. The second part is bonus from over profit. The next suggestion is make a new working position. This position would take care about controlling and project documentation. During the building project, especially at the end is construction manager very busy. It depend of decision of construction 63 manager what kind of activity will have prefer. Project documentation and administration or controlling of building works. If they are doing everything correct and technology are respect. Suggested position would take care about invoices, real work, which is done, project documentation, controlling of budget. The third suggestion is purchase of small machinery such as chipping hammers and drills. At this time they rent all devices. Rent is higher than purchase price. The last suggestion is use credit to restoration of fleet. At this time they have obsolete fleet, because the bought all cars by cash. It is not conveniently.
|
|
Distribution management in a large company (warehouse)
MICHALOVÁ, Jana
Distribution management in a large company. This Master´s Thesis examines the company Fruko-Schulz, s. r. o. This company has been making spirits. The goal is to map out the information and material flows toward the warehouse and from the warehouse. Subsequently, to analyze the current state of the company. Based on the information propose measures for improvement. In own work is described in detail and enterprise activities in a company. After ideas are designed to change. These proposals relate to distribution to the end customer through the gastronomical exhibitions and fairs. Other proposals are aimed at end users in the Russian market. Ideas for packaging or new products are designed, but is backed that do not make sense. Company Fruko-Schulz, s. r. o. sas a long tradition and reputation. But that's not enough, the competition is great and it isalso at a high level. The idea to focus on the Russian market is very good and there is great potential.
|
|
Remote sensing as support tool for agricultural drought assessment
Hlavinka, Petr ; Semerádová, Daniela ; Balek, Jan ; Žalud, Z. ; Tadesse, T. ; Hayes, M. ; Wardlow, B. ; Trnka, Miroslav
Very important information about vegetation condition within wide areas (through continents and states) or for local areas in resolution from hundreds to tens of meters could be obtained from satellites within remote sensing. The temporal and spatial continuity is big advantage of this method. Namely so-called vegetation indices are often used for vegetation cover condition assessment. The aim of submitted study is to present possibility of using EVI2 (Enhanced Vegetation Index) for assessment of drought impact within vegetation. The results for selected years of the period 2000-2015 achieved using MODIS (Moderate Resolution Imaging Spectroradiometer) aboard Terra satellite are included. The data in weekly time step and for the whole Czech Republic are presented.
|
guest ::
