|
|
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.
|
|
|
Detection and Recognition of Dominant Face Features
Švábek, Hynek ; Láník, Aleš (referee) ; Chmelař, Petr (advisor)
This thesis deals with the increasingly developing field of biometric systems which is the identification of faces. The thesis deals with the possibilities of face localization in pictures and their normalization, which is necessary due to external influences and the influence of different scanning techniques. It describes various techniques of localization of dominant features of the face such as eyes, mouth or nose. Not least, it describes different approaches to the identification of faces. Furthermore a it deals with an implementation of the Dominant Face Features Recognition application, which demonstrates chosen methods for localization of the dominant features (Hough Transform for Circles, localization of mouth using the location of the eyes) and for identification of a face (Linear Discriminant Analysis, Kernel Discriminant Analysis). The last part of the thesis contains a summary of achieved results and a discussion.
|
|
|
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.
|
|
|
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.
|
|
| |
|
| |
|
|
Novel cancer biomarkers derived from quantitative phase imaging of biopsy cells
Plišková, Diana ; Týč, Matěj (referee) ; Kolářová, Jana (advisor)
The main objective of this work is the development of novel cancer biomarkers usable in personalized treatments. To understand why this issue is important, a brief description of cancer, including statistical results over the past years, is provided. The work also describes individual methods of light microscopy that can be used in cell analysis and subsequent image processing consisting of segmentation, tracking, feature extraction and classification. In this work, the main cell features, such as cell motility and shape, are presented. These features can be potential biomarkers in the treatment of cancer.
|
|
|
Heart beat classification
Potočňák, Tomáš ; Kozumplík, Jiří (referee) ; Ronzhina, Marina (advisor)
The aim of this work was to develop the method for classification of ECG beats into two classes, namely ischemic and non-ischemic beats. Heart beats (P-QRS-T cycles) selected from animals orthogonal ECGs were preprocessed and used as the input signals. Spectral features vectors (values of cross spectral coherency), principal component and HRV parameters were derived from the beats. The beats were classified using feedforward multilayer neural network designed in Matlab. Classification performance reached the value approx. from 87,2 to 100%. Presented results can be suitable in future studies aimed at automatic classification of ECG.
|
guest ::
