|
|
Odor analysis program for experimental electronic nose
Janošíková, Pavla ; Szendiuch, Ivan (referee) ; Adámek, Martin (advisor)
This work deals with processing data acquired from sensory device known as electronic nose. The work introduces readers to a few possible designes of electronic noses and to some of the best known analysis for odor recognition that are used in food industry. The work focus on a principal component analysis and a creation of program that process data from a simple electronic nose. The program not only receives data, but it even saves them and process them for better clarity of results. Using this program it is possible to create a new database and identify an unknown sample if its data are already stored in database. The part of this work is an experiment to see if the created program is able to recognize some odors better then a human nose.
|
|
|
Classification of heart beats from multilead ECG using principal component analysis
Vlček, Milan ; Vítek, Martin (referee) ; Ronzhina, Marina (advisor)
The resume of this master´s thesis is to introduce reader into principal component analysis (PCA), namely, the use of PCA for analysis of ECG. This method allows to reduce quantity of the data without loss of useful information. That is why PCA is widespread for preprocessing of the data for further classification, which this thesis also deals. Data available at the Department of Biomedical Engineering at the University of Technology in Brno were used in this work. All the methods were realized using Matlab.
|
|
|
Network Anomaly Detection Based on PCA
Krobot, Pavel ; Kováčik, Michal (referee) ; Bartoš, Václav (advisor)
This thesis deals with subject of network anomaly detection. The method, which will be described in this thesis, is based on principal component analysis. Within the scope of this thesis original design of this method was studied. Another two extensions of this basic method was studied too. Basic version and last extension was implemented with one little additional extension. This one was designed in this thesis. There were series of tests made above this implementation, which provided two findings. First, it shows that principal component analysis could be used for network anomaly detection. Second, even though the proposed method seems to be functional for network anomaly detection, it is still not perfect and additional research is needed to improve this method.
|
|
|
Creating a 3D Face Model Using Kinect Device
Nesvadba, Tomáš ; Malinka, Kamil (referee) ; Mráček, Štěpán (advisor)
The main aim of this bachelor's thesis is to suggest a method for increasing the resolution of 3D face models captured by Kinect. The document describes different methods of capturing 3D models and compares the Kinect sensor with more acurate scanners. The main part of this document is dedicated to statistic model based on the PCA and its usage in the project. The last section of the paper describes testing of various models and discuss the results and another options of aplication.
|
|
|
Speckle Tracking Echocardiography
Strecha, Juraj ; Drahanský, Martin (referee) ; Mráček, Štěpán (advisor)
he thesis deals with proposal of an algorithm and implementation of a program that tracks a motion of the heart muscle in the captured ultrasound video of the heart. The point position estimation is calculated by optical flow method. The Active Shape Model method is used to confirm the accuracy of point's position tracking. The user annotates desired structure of the heart arch first and the application displays new points which represent a new deformed heart shape.
|
|
|
Tool for Classification of Lifestyle Traits Based on Metagenomic Data from the Large Intestine
Kubica, Jan ; Hon, Jiří (referee) ; Smatana, Stanislav (advisor)
This thesis deals with analysis of human microbiome using metagenomic data from large intestine. The main focus is placed on bacteria composition in a sample on different taxonomic levels regarding the lifestyle traits of an individual. For this purpose, a tool for classification of several attributes was created. It considers attributes like diet type and eating habits (vegetarian, vegan, omnivore), gluten and lactose intolerance, body mass index, age or sex. From range of machine learning perspectives considering K Nearest Neighbours (kNN), Random Forest (RF) and Support Vector Machines (SVM) were used. Datasets for training and final evaluation of the classifier were taken from American Gut project. The thesis also focuses on particular problems with metagenomic datasets like its multidimensionality, sparsity, compositional character and class imbalance.
|
|
| |
|
|
Energy Harvesting Power Supply for MEMS Applications
Smilek, Jan ; Leuchter, Jan (referee) ; Ondrůšek, Čestmír (referee) ; Hadaš, Zdeněk (advisor)
Tato práce se zabývá vývojem nezávislého elektrického zdroje pro moderní nízkopříkonové elektrické aplikace. Protože tradiční řešení napájení drobných spotřebičů s využitím baterií či akumulátorů snižuje uživatelský komfort kvůli potřebě pravidelné údržby, navrhovaný zdroj využívá principu energy harvesting. Tento princip spočívá v získávání energie přímo z okolního prostředí napájené aplikace a její přeměně na energii elektrickou, která je dále využita pro na-pájení moderních MEMS (mikroelektromechanických) zařízení. Potenciální aplikací vyvíjeného zdroje je především moderní nositelná elektronika a biomedicínské senzory. Tato oblast využití ovšem klade zvýšené nároky na parametry generátoru, který musí zajistit dostatečný generovaný výkon z energie, dostupné v okolí lidského těla, a to při zachování prakticky využitelné velikosti a hmotnosti. Po stanovení předběžných požadavků a provedení analýz vhodnosti dostupných zdrojů energie ke konverzi byla k využití vybrána kinetická energie lidských aktivit. Byla provedena série měření zrychlení na lidském těle, především v místě předpokládaného umístění generátoru, aby bylo možno analyzovat a generalizovat hodnoty energie dostupné ke konverzi v daném umístění. V návaznosti na tato měření a analýzy byl vyvinut inovativní kinetický energy harvester, který byl následně vyroben jako funkční vzorek. Tento vzorek byl pak testován v reálných podmínkách pro verifikaci simulačního modelu a vyhodnocení reálné použitelnosti takového zařízení. Kromě samotného vývoje generátoru je v práci popsán i originální způsob zvýšení generovaného výkonu pro kinetické energy harvestery a jsou prezentována statistická data a modely pro predikci využitelnosti kinetických harvesterů pro získávání energie z lidské aktivity.
|
|
|
Human Face Recognition
Burián, Pavel ; Ševcovic, Jiří (referee) ; Herout, Adam (advisor)
The bachelor thesis deals with the problematic of the human face recognition in an image. It describes the face detection principles, methods used in recognition problematic and existing face data sets. Thesis is aimed on analysis, comparison and testing of the eigenface, fisherface and KDDA (Kernel Direct Discriminant Analysis) algorithms.
|
|
|
Face Identification
Macenauer, Oto ; Drozd, Michal (referee) ; Chmelař, Petr (advisor)
This document introduces the reader to area of face recognition. Miscellaneous methods are mentioned and categorized to be able to understand the process of face recognition. Main focus of this document is on issues of current face recognition and possibilities do solve these inconveniences in order to be able to massively spread face recognition. The second part of this work is focused on implementation of selected methods, which are Linear Discriminant Analysis and Principal Component Analysis. Those methods are compared to each other and results are given at the end of work.
|
guest ::
