|
|
Interactive 3D CT Data Segmentation Based on Deep Learning
Trávníčková, Kateřina ; Hradiš, Michal (referee) ; Kodym, Oldřich (advisor)
This thesis deals with CT data segmentation using convolutional neural nets and describes the problem of training with limited training sets. User interaction is suggested as means of improving segmentation quality for the models trained on small training sets and the possibility of using transfer learning is also considered. All of the chosen methods help improve the segmentation quality in comparison with the baseline method, which is the use of automatic data specific segmentation model. The segmentation has improved by tens of percents in Dice score when trained with very small datasets. These methods can be used, for example, to simplify the creation of a new segmentation dataset.
|
|
|
Dynamic Programming in Biosignal Processing
Procházka, Petr ; Kolářová, Jana (referee) ; Klimek, Martin (advisor)
Bachelor thesis describes the dynamic time warping method (DTW), which is used for extrasystoles detection in ECG signales. Several methods for extracting a reference cycle are described in this paper. These methods are applied either to whole heart cycles or just to QRS complexes. Afterwards these methods are compared with results of cluster analysis.
|
|
|
Data Mining with Python
Šenovský, Jakub ; Bartík, Vladimír (referee) ; Zendulka, Jaroslav (advisor)
The main goal of this thesis was to get acquainted with the phases of data mining, with the support of the programming languages Python and R in the field of data mining and demonstration of their use in two case studies. The comparison of these languages in the field of data mining is also included. The data preprocessing phase and the mining algorithms for classification, prediction and clustering are described here. There are illustrated the most significant libraries for Python and R. In the first case study, work with time series was demonstrated using the ARIMA model and Neural Networks with precision verification using a Mean Square Error. In the second case study, the results of football matches are classificated using the K - Nearest Neighbors, Bayes Classifier, Random Forest and Logical Regression. The precision of the classification is displayed using Accuracy Score and Confusion Matrix. The work is concluded with the evaluation of the achived results and suggestions for the future improvement of the individual models.
|
|
|
Automatic Photography Categorization
Matuszek, Martin ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
This thesis deal with choosing methods, design and implementation of application, which is able of automatic categorization photos based on its content into predetermined groups. Main steps of categorization are described in greater detail. Finding and description of interesting points in image is implemented using SURF, creation of visual dictionary by k-means, mapping on the words through kd-tree structure. Own evaluation is made for categorization. It is described, how the selected steps were implemented with OpenCV and Qt libraries. And the results of runs of application with different settings are shown. And efforts to improve outcome, when the application can categorize right, but success is variable.
|
|
|
Clustering of Protein Sequences Based on Primary Structure of Proteins
Jurásek, Petr ; Stryka, Lukáš (referee) ; Burgetová, Ivana (advisor)
This master's thesis consider clustering of protein sequences based on primary structure of proteins. Studies the protein sequences from they primary structure. Describes methods for similarities in the amino acid sequences of proteins, cluster analysis and clustering algorithms. This thesis presents concept of distance function based on similarity of protein sequences and implements clustering algorithms ANGES, k-means, k-medoids in Python programming language.
|
|
|
Automatic Photography Categorization
Veľas, Martin ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
This thesis deals with content based automatic photo categorization. The aim of the work is to create an application, which is would be able to achieve sufficient precision and computation speed of categorization. Basic solution involves detection of interesting points, extraction of feature vectors, creation of visual codebook by clustering, using k-means algorithm and representing visual codebook by k-dimensional tree. Photography is represented by bag of words - histogram of presence of visual words in a particular photo. Support vector machines (SVM) was used in role of classifier. Afterwards the basic solution is enhanced by dividing picture into cells, which are processed separately, computing color correlograms for advanced image description, extraction of feature vectors in opponent color space and soft assignment of visual words to extracted feature vectors. The end of this thesis concerns to experiments of of above mentioned techniques and evaluation of the results of image categorization on their usage.
|
|
|
Success Rate Measure Methods in Data Mining
Trunkát, Jan ; Zelený, Jan (referee) ; Bartík, Vladimír (advisor)
The Bachelor thesis is aimed at success rate measure methods in data mining in the area of clustering. It introduces the basic concepts, features of data mining and especially the cluster analysis. This work includes program, which implements methods of measuring success. In conclusion, they are given results of clustering success.
|
|
|
Knowledge Discovery in Multimedia Databases
Jurčák, Petr ; Řezníček, Ivo (referee) ; Chmelař, Petr (advisor)
This master's thesis is dedicated to theme of knowledge discovery in Multimedia Databases, especially basic methods of classification and prediction used for data mining. The other part described about extraction of low level features from video data and images and summarizes information about content-based search in multimedia content and indexing this type of data. Final part is dedicated to implementation Gaussian mixtures model for classification and compare the final result with other method SVM.
|
|
|
Datamining in MS SQL Using Incremental Algorithms
David, Lukáš ; Bartík, Vladimír (referee) ; Šebek, Michal (advisor)
This work deals with issues in data streams mining which nowadays is a very dynamic area in information technology. The thesis describes the general principles of data mining. There are also the principles of data mining in the data streams. Special attention is given to the implemented algorithm CluStream. In the practical part the data stream processing solution was designed and implemented by the MSSQL technology using the above algorithm. The functionality of the algorithm was verified using own data stream generator.
|
|
|
Web page segmentation utilizing clustering techniques
Zelený, Jan ; Šimko, Marián (referee) ; Kliegr, Tomáš (referee) ; Zendulka, Jaroslav (advisor)
Získávání informací a jiné techniky dolování dat z webových stránek získávají na důležitosti s tím, jak se rozvíjí webové technologie a jak roste množství informací uložených na webu, jakožto jediném nosiči těchto informací. Spolu s tímto množství informací také ale roste množství obsahu, který není v kontextu prezentovaných informací ničím důležitý. To je jedním z důvodů, proč je důležité se intenzivně věnovat předzpracování informací uložených na webu. Segmentační algoritmy jsou jedním z možných způsobů předzpracování. Tato práce se věnuje využití shlukovacích technik pro zefektivnění existujících, ale i nalezení zcela nových algoritmů použitelných pro segmentaci webových stránek.
|
guest ::
