|
|
Human Activity Recognition Using Smartphone
Novák, Andrej ; Červenák, Rastislav (referee) ; Burget, Radim (advisor)
The increase of mobile smartphones continues to grow and with it the demand for automation and use of the most offered aspects of the phone, whether in medicine (health care and surveillance) or in user applications (automatic recognition of position, etc.). As part of this work has been created the designs and implementation of the system for the recognition of human activity on the basis of data processing from sensors of smartphones, along with the determination of the optimal parameters, recovery success rate and comparison of individual evaluation. Other benefits include a draft format and displaying numerous training set consisting of real contributions and their manual evaluation. In addition to the main benefits, the software tool was created to allow the validation of the elements of the training set and acquisition of features from this set and software, that is able with the help of deep learning to train models and then test them.
|
|
|
Recognition of emotions in Czech texts
Červenec, Radek ; Smékal, Zdeněk (referee) ; Burget, Radim (advisor)
With advances in information and communication technologies over the past few years, the amount of information stored in the form of electronic text documents has been rapidly growing. Since the human abilities to effectively process and analyze large amounts of information are limited, there is an increasing demand for tools enabling to automatically analyze these documents and benefit from their emotional content. These kinds of systems have extensive applications. The purpose of this work is to design and implement a system for identifying expression of emotions in Czech texts. The proposed system is based mainly on machine learning methods and therefore design and creation of a training set is described as well. The training set is eventually utilized to create a model of classifier using the SVM. For the purpose of improving classification results, additional components were integrated into the system, such as lexical database, lemmatizer or derived keyword dictionary. The thesis also presents results of text documents classification into defined emotion classes and evaluates various approaches to categorization.
|
|
|
Scalable preprocessing of data using Hadoop tool
Marinič, Michal ; Šmirg, Ondřej (referee) ; Burget, Radim (advisor)
The thesis is concerned with scalable pre-processing of data using Hadoop tool which is used for processing of large volumes of data. In the first theoretical part it focuses on explaining of functioning and structure of the basic elements of Hadoop distributed file system and MapReduce methods for parallel processing. The latter practical part of the thesis describes the implementation of basic Hadoop cluster in pseudo-distributed mode for easy program-debugging, and also describes an implementation of Hadoop cluster in fully-distributed mode for simulation in practice.
|
|
| |
|
|
The Application of Evaluation Algorithm for the Rating of Suppliers of the Firm
Karásek, Jan ; Burget, Radim (referee) ; Dostál, Petr (advisor)
The aim of this diploma thesis is refer to the supplier evaluation and selection process in business sphere. On the business sphere is putted emphasis because securing of company sources are more and more important parts of strategic decision making. In this paper is analyzed supplier selection problem and are analyzed most common methods to determine the best supplier. The goal of this paper is proposal of own program solution of evaluation and supplier selection build on evolution methods, specifically evolution algorithms. The part of this thesis is map of theoretical possibilities of evolution algorithms and implementation of program for solving supplier selection problem.
|
|
|
People recognition using facial images
Lindovský, Michal ; Burget, Radim (referee) ; Rajnoha, Martin (advisor)
This bachelor thesis focuses on the person recognition between several millions of people in a few seconds. As a part of my thesis is comparison of two programs which are used for recognizing faces - OpenFace and Face Recognition. Computing times of localization and face encoding are compared. The accuracy of recognition in various tests is compared as well, such as blurred image, brightness changes, age of person or usage of sunglasses. Created web application is made for recognizing people in different databases. Is possible to add or remove databases of people in the application. The application allows to subsume people into database by gender automatically or manually. Face recognition can be speeded up by using multiple processor cores.
|
|
|
Image segmentation using deeplearning methods
Lukačovič, Martin ; Burget, Radim (referee) ; Mašek, Jan (advisor)
This thesis deals with the current methods of semantic segmentation using deep learning. Other approaches of neaural networks in the area of deep learning are also discussed. It contains historical solutions of neural networks, their development, and basic principle. Convolutional neural networks are nowadays the most preferable networks in solving tasks as detection, classification, and image segmentation. The functionality was verified on a freely available environment based on conditional random fields as recurrent neural networks and compered with the deep convolutional neural networks using conditional random fields as postprocess. The latter mentioned method has become the basis for training of new models on two different datasets. There are various enviroments used to implement neural networks using deep learning, which offer diverse perform possibilities. For demonstration purposes a Python application leveraging the BVLC\,/\,Caffe framework was created. The best achieved accuracy of a trained model for clothing segmentation is 50,74\,\% and 68,52\,\% for segmentation of VOC objects. The application aims to allow interaction with image segmentation based on trained models.
|
|
|
Automatic medical image segmentation using Level Set algorithm
Yerpeissov, Serik ; Burget, Radim (referee) ; Uher, Václav (advisor)
This thesis contains two main parts, theoretical and implementation. In the theoretical part, there are described the different segmentation methods. Mainly it is about description method Level Set. The aim of practical part is creation of java module for segmentation of medical data by using Level Set Methods. The work solves example of GUI for the display of results. The results should be tested
|
|
|
Stability of hierarchical aggregation system for internet television broadcasting
Olivka, Petr ; Komosný, Dan (referee) ; Burget, Radim (advisor)
This work is about Hierarchical agregation and it describes its parts in the rst part of this work. Next is described its parts, main features and properties in this rst part. Document describes the possibilities of realization. Second part describes an analysis of the stability problem. Realizes the detection of failures of the Feedback target stations by the implemented protocol. The protocol is programaticly realized in JAVA language and tested in the real enviroment. In this document it is described an function of bandwidth on the speed of failure detection. The issues of detection of failure on the feedback target manager machine are discussed in this document.
|
|
|
Tool for web content annotation
Najbr, Ondřej ; Povoda, Lukáš (referee) ; Burget, Radim (advisor)
This thesis is divided into three parts. The first part is focused on a description of the formulation of the extension for viewers Internet Explorer, Opera, Safari 5, Mozilla Firefox a Google Chrome, on summary of the facilities of development of the extension for these viewers and on structure of the extension factually for Google Chrome. The second part describes the installation of the extension for Chrome with method of the unpack extension and with method from the Internet shop Chrome. There is also described a detailed formulation of the extension for Chrome with examples of the code source, with possibility of the implementation and the commentary insert into websites. It further describes contribution of the extension and contribution of this thesis. The target of this thesis is to get acquainted with problems of the formulation of the extension of plugins for viewers Chrome or Firefox and to formulate an application, which it will be able to add the commentary to contents of the website.
|
guest ::
