|
|
The Study of Serviceability of Highway network with Using of Telematics
Bruna, Jiří ; Hájek, Martin (referee) ; Jurová, Marie (advisor)
In the mean time there are only a few objective information available in a road accident . A electronically motor vehicle operational data recorder, that is main topic of my graduate work could record maximum of vehicle operational data (time, velocity, activity of brakes, activity of ABS, lights, blinkers, operational engine measures). This information could contribute to faster car crash investigation.
|
|
|
Sleep apnea detection
Hastík, Matěj ; Janoušek, Oto (referee) ; Ronzhina, Marina (advisor)
This master‘s thesis deals with a detailed description of sleep apnea and methods of detection of sleep apnea. The first part of the work is focused on the physiology of sleep, sleep apnea itself, its distribution, symptoms, risk factors and treatment. The next part of the work deals with polysomnographic examination and methods for analysis of polysomnographic data. The last part is devoted to the procedure design for detecting sleep apnea by using only one kind of signal and by using more kinds of signals, implementation of these proposals, their testing on real data, evaluating the detection performance and comparing the results with data available in the literature.
|
|
|
P wave detection in ECG signals
Bajgar, Jiří ; Kozumplík, Jiří (referee) ; Smital, Lukáš (advisor)
The aim of this diploma thesis is to introduce methods of detection of the QRS complex and the subsequent detection of P waves. The intention is to create a program by specified method in the software Matlab which will be able to implement this method. The thesis describes the basic and important methods of detection and subsequent algorithm to detect P waves. Solution of the algorithm is tested on real data. It also describes the automatic signal evaluation and the results of this automatic function.
|
|
|
Machine Vision Methods for Traffic Signs Recognition
Zátopek, Michal ; Richter, Miloslav (referee) ; Horák, Karel (advisor)
This diploma thesis is dealing with an issue of machine vision in the field of traffic signs recognition. The first part is devoted to machine vision in general traffic situations. Together with traffic applications there is paid attention to a possible autonomous vehicle and applications for the traffic signs recognition. The main part of this work is devoted to a description and an implementation of several methods for colour and pattern localisation of traffic signs in the scene and to identification algorithms. Apart from the implementation itself, these algorithms are submitted to several experiments for a valorisation of their success. The thesis also includes a gallery of images with traffic signs including a file with descriptive annotation for an automatic testing of algorithms.
|
|
|
Plagiarism detection of text documents
Lízal, Radek ; Vítek, Martin (referee) ; Smital, Lukáš (advisor)
This diploma thesis introduces the definition of plagiarism, distinguishes the types of plagiaries which often take place in praxis and the ways of determining the suspected texts. The means of detection are essential; therefore a whole chapter is dedicated to those. For the detection purposes, it is vital to pre-process the data to reduce the demand factor of the program. There is a preview of some programs which are already being used for the detection of plagiarism. The following chapter introduces some selected indications which have been implemented in the Matlab environment to create a detector of plagiaries in text documents. The created program is described in chapter eight. The applied indications and the detector response are described in a chapter called Indications testing. The testing proved the quality of these indications. The results together with pros and cons of the particular methods are discussed in the conclusion.
|
|
|
Analysis of Defects on PCB Using X-RAY
Mlýnek, Martin ; Vala, Radek (referee) ; Řihák, Pavel (advisor)
This thesis is focused on BGA packages and fault detection after rework using X – Ray. There is a description of BGA packages by carrier substrate, techniques of connecting on chip, from mounting packages to repair printed circuit boards (hereafter PCB). Thesis summarizes description of defects, which are created after rework process. There is also description of X – Ray as method for analyzing defects. X – PLANE method used to detect internal structure of BGA packages and it was confirmed by microsection and by software for reconstruction. Description of automatic and manual measurement is follow.
|
|
|
Detection and Correspondence of Image Features
Hasmanda, Martin ; Kohoutek, Michal (referee) ; Říha, Kamil (advisor)
The main goal of this bachelor‘s thesis was obtain basic knowledge about image processing. Especially was this work specialized on features detection in images captured from different perspectives and for finding correspondences between those images. Preliminary were to be described the basic principles for understanding computer vision such as perspective projection, description model of the camera and two views geometry. From methods of the detection was introduced best-known and most widely used of the detectors Harris corner detector. He is independent of images rotation and he is analyzed in detail. Further was described SIFT detector, that is independent of images scale. In this work further be described to several methods for finding correspondences of images features. First were to be described and derived two basic transformation matrixes that arrange to the association with features of two images. The first homography matrix describes transformation of two 2D views and fundamental matrix. Fundamental matrix obtains from two images full information of captured 3D scene and projection matrixes of cameras. For to primary definition correspondences were to be used to methods SSD and NCC. These methods match correspondences after similarities surroundings of features. These methods unfiled correct assignment features. Therefore uses stochastic RANSAC algorithm. The RANSAC algorithm was in detail described in this work in basic form and further modified on MLESAC algorithm. This algorithm can find better correspondences than RANSAC. In the end was described simple application for implementation introduced methods.
|
|
|
Statistical anomaly detection methods of data communication
Woidig, Eduard ; Mangová, Marie (referee) ; Slavíček, Karel (advisor)
This thesis serves as a theoretical basis for a practical solution to the issue of the use of statistical methods for detecting anomalies in data traffic. The basic focus of anomaly detection data traffic is on the data attacks. Therefore, the main focus is the analysis of data attacks. Within the solving are data attacks sorted by protocols that attackers exploit for their own activities. Each section describes the protocol itself, its usage and behavior. For each protocol is gradually solved description of the attacks, including the methodology leading to the attack and penalties on an already compromised system or station. For the most serious attacks are outlined procedures for the detection and the potential defenses against them. These findings are summarized in the theoretical analysis, which should serve as a starting point for the practical part, which will be the analysis of real data traffic. The practical part is divided into several sections. The first of these describes the procedures for obtaining and preparing the samples to allow them to carry out further analysis. Further described herein are created scripts that are used for obtaining needed data from the recorded samples. These data are were analyzed in detail, using statistical methods such as time series and descriptive statistics. Subsequently acquired properties and monitored behavior is verified using artificial and real attacks, which is the original clean operation modified. Using a new analysis of the modified traffics compared with the original samples and an evaluation of whether it has been some kind of anomaly detected. The results and tracking are collectively summarized and evaluated in a separate chapter with a description of possible further attacks, which were not directly part of the test analysis.
|
|
|
Image similarity measurement using points of interest
Jelínek, Ondřej ; Uher, Václav (referee) ; Burget, Radim (advisor)
This paper presents a new object detection method. The method is based on keypoints analysis and their parameters. Computed parameters are used for building a decision model using machine learning methods. The model is able to detect object in the picture based on input data and compares its similarity to the chosen example. The new method is described in detail, its accuracy is evaluated and this accuracy is compared to other existing detectors. The new method’s detection ability is by more than 40% better than detection ability of detectors like SURF. In order to understand the object detection this paper describes the process step by step including popular algorithms designed for specific roles in each step.
|
|
|
Modelling of elastic and inelastic collisions
Jurčík, Michal ; Burget, Radim (referee) ; Karásek, Jan (advisor)
Master's thesis deals with vehicles collisions within an environment of logistic distribution storehous. The aim is to avoid potential collisions that can occur between these vehicles. In the first chapter are detailed collisions of particles and elements impact for the law of conservation of energy and momentum. In further sections is carried out detailed research of elastic and inelastic collisions in an ideal environment, which are the theoretical basis for the simulation of the real environment. Collisions are supported by detailed calculations and added pictures. The second chapter deals with the development of double-layer application simulating elastic collisions in an ideal environment. In subchapters are descriptions of the classes and methods for computing prediction of collisions with examples of source code. The last section describes the software platform JavaFX and used animation classes that are required for visualization issues. The last chapter, which is the main goal of the work is done by the expansion of the existing design environment of storehouse and vehicles. Particular chapters then describe the cases of various types of collisions their detection and avoidance. There is an application designed to address this issue, with a description of the classes and methods. Used methods are supported with flowcharts for easier understanding.
|
guest ::
