|
|
The GPU Based Acceleration of Neural Networks
Šimíček, Ondřej ; Jaroš, Jiří (referee) ; Petrlík, Jiří (advisor)
The thesis deals with the acceleration of backpropagation neural networks using graphics chips. To solve this problem it was used the OpenCL technology that allows work with graphics chips from different manufacturers. The main goal was to accelerate the time-consuming learning process and classification process. The acceleration was achieved by training a large amount of neural networks simultaneously. The speed gain was used to find the best settings and topology of neural network for a given task using genetic algorithm.
|
|
|
Scene Analysis Based on the 2D Images
Hejtmánek, Martin ; Drahanský, Martin (referee) ; Orság, Filip (advisor)
This thesis deals with an object surface analysis in a simple scene represented by two-dimensional raster image. It summarizes the most common methods used within this branch of information technology and explains both their advantages and drawbacks. It introduces the design of an surface profile analysis algorithm based on the lighting analysis using knowledge and experiences from previous work. It contains a detailed description of the implemented algorithm and discusses the experimental results. It also brings up options for the possible enhancement of the projected algorithm.
|
|
|
Features for the analysis and classification of cells in holographic microscope images
Navrátilová, Markéta ; Kolář, Radim (referee) ; Vičar, Tomáš (advisor)
This thesis deals with features used for analysis and classification of cell images captured by holographic microscope. Distinctive features are described together with tools for their classification. Features are extracted on provided segmented cells with use of Matlab programming environment. Based on extracted features the cells are classified by SVM classificator. With use of clustering methods and dimensionality reduction different cell types are analyzed. Reliabity of each feature is tested.
|
|
|
Content Based Photo Search
Valenta, Martin ; Mlích, Jozef (referee) ; Španěl, Michal (advisor)
This work deals with methods appropriate to content based photo search, design and implementation of subsequent applications for searching buildings. Purpose of the application is to create an interactive guide to the city using a combination of Web and client technologies (mobile, desktop). There are subscribed in detail the steps of recognition. A key points of the image are extracted by SURF. A visual dictionary is calculated with k-means algorithm. The dictionary is weighted by TF- IDF. To describe the image data is used a Bag of Words method. The text also mentions the new trends in this area and summarizes the application design and implementation results achieved.
|
|
|
Aspects of airspace evaluation
Závodník, Ondřej ; Kujal, Tomáš (referee) ; Brhelová, Dana (advisor)
Diplomová práce se zabývá jednak popisem stavu letecké dopravy a to zejména co se týče její bezpečnosti, plynulosti, propustnosti a kapacity. Výše uvedené je poté zhodnoceno v části věnující se aspektům nebezpečnosti vzdušného prostoru v jednotlivých fázích letu.
|
|
|
Classification on unbalanced data
Hlosta, Martin ; Popelínský, Lubomír (referee) ; Štěpánková,, Olga (referee) ; Zendulka, Jaroslav (advisor)
Tématem této disertační práce je klasifikace daty s nevyváženými daty. Jedná se o oblast strojového, jejímž cílem je řešit problémy, které plynou z toho, že jedna ze tříd je v datech zastoupena výrazně méně než třída druhá. Minoritní třída má často větší význam a tradiční metody upřednostňující majoritní třídu nedosahují dobrých výsledků na třídě minoritní. Dvě aplikační domény motivovaly výzkum a vedly na identifikaci dvou specifických, dosud neřešených problémů. V první z nich vedlo omezení kladené na minimální požadovanou přesnost na minoritní třídě v počítačové bezpečnosti na formulaci úlohy klasifikace s omezením. Navrhl jsem metodu, která kombinuje upravenou verzi logistické regrese a stochastické algoritmy, které vždy vylepšily výsledky logistické regrese.Druhou je doména analýzy učení (Learning Analytics), která motivovala definici problému predikce splnění cíle, jenž má specifikovaný termín splnění. Byl představen koncept sebe-učení (Self-Learning), kdy trénování modelu probíhá díky jedincům, kteří tento cíl splní předčasně. Díky malému počtu jedinců splňujících úlohu na začátku je problém silně nevyvážený, ale nevyváženost klesá směrem k termínu splnění. Na problému identifikace rizikových studentů distanční univerzity bylo ukázáno, že (1) takový koncept dává lepší výsledky než specifikovaná základna (baseline), (2) a že metody pro vypořádání se s nevyvážeností, které neberou v potaz informaci o doméně, nevedly k velkým zlepšením. Evaluace ukázala, že metody založené na znalosti domény v rozšířené verzi pro Self-Learning vylepšily klasifikaci více než běžné metody pro vypořádání se s nevyvážeností a že znalost příčiny nevyváženosti může vést k lepším výsledkům.
|
|
|
Reduction of Computation Cost in libSVM Using String Kernel Functions
Kubernát, Tomáš ; Sehnalová, Pavla (referee) ; Michlovský, Zbyněk (advisor)
The goal of this thesis was to implement four string functions into the library libSVM . Then apply series of tests with variable parameters values affecting the individual string functions using the library and string functions. Using the results of experiments the speed and success of clasification of my implementation of string functions in library libSVM was compared with the implementation of string functions in program kernels . In this thesis there are also described procedures of all tests along with measured data and their graphical representation.
|
|
|
Segmentation of ribs in thoracic CT scans
Kašík, Ondřej ; Kolář, Radim (referee) ; Jakubíček, Roman (advisor)
This thesis deals with design and implementation of an algorithm for segmentation of ribs from thoracic CT data. For the segmentation method of rib centerlines detection is chosen. The first step of this approach is to extract the centerlines of all the bones located in the scan. These centerlines are divided into short primitives, which are subsequently classified into couple of categories, depending on whether they represent the centerline of the rib. Subsequently, the centrelines of ribs are used as the seed points of the region growing algorithm in three-dimensional space, which realizes the final segmentation of the ribs. Within the work, a database of 10 CT scans was manually annotated, which was subsequently used to validate a performance of the proposed segmentation approach. The achieved success rate of primitive classification is 96,7 %, the success rate of rib segmentation (Dice coefficient) is 86,8 %.
|
|
| |
|
|
Artificial Intelligence in Bang! Game
Kolář, Vít ; Lodrová, Dana (referee) ; Orság, Filip (advisor)
The goal of this master's thesis is to create an artificial intelligence for the Bang! game. There is a full description of the Bang! game, it's entire rules, player's using strategy principles and game analysis from UI point of view included. The thesis also resumes methods of the artificial intelligence and summarizes basic information about the domain of game theory. Next part describes way of the implementation in C++ language and it's proceeding with use of Bayes classification and decision trees based on expert systems. Last part represent analysis of altogether positive results and the conclusion with possible further extensions.
|
guest ::
