|
|
Sentiment Analysis in Automotive Industry
Bezák, Adam ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
The main theme of this thesis is to familiarize with the basic methods of sentiment analysis on social networks. Thesis’s theme is aimed on the automotive industry, although this prinicipal can be used in any different examined branch. The basis of the practical part is to obtain data from the social networks, analyze them and then index them into ElasticSearch database. Another goal of the thesis is to visualize these data by means of a web portal. Created web portal provides various statistics of the leading automobile brands, an overview of new trends or the aspect visualization of the individual cars.
|
|
|
Smart Sensor Network with Using Mobile Devices
Tomčík, Milan ; Zbořil, František (referee) ; Samek, Jan (advisor)
This bachelor thesis deals with the use of mobile devices as sensors of various activities. Different types of mobile device sensors are used, in particular the gyroscope, accelerometer and magnetometer. The thesis tackles the possibility of utilization of mobile devices as part of the nodes in a sensor network, while employing mobile device and fusing data obtained from their sensors.
|
|
|
Road Detection for Autonomous Car
Komora, Matúš ; Veľas, Martin (referee) ; Španěl, Michal (advisor)
his thesis deals with detection of the road adjacent to an autonomous vehicle. The road is recognition is based on the Velodyne LiDAR laser radar data. An existing solution is used and extended by machine learning - a Support Vector Machine with online learning. The thesis evaluates the existing solution and the new one using a KITTI dataset. The reliability of the road recognition is then computed using F-measure.
|
|
|
Automatic assignment of diagnosis to medical reports
Lachata, Adrián ; Hana, Jiří (advisor) ; Vidová Hladká, Barbora (referee)
The goal of the thesis is to examine the percentage of automatically assigned diagnosis codes (ICD10) to Czech text medical reports. We used machine learning and text classification algorithms such as Naive Bayes and decision trees. Program WEKA was used for classification. Features selection and data preprocessing were made by our program, which was created exclusive for this purpose. The key features of the program are features selection based on IG or PMI, text lemmatization and stopwords generation by IDF. We took closer look at I10 diagnosis but the results were processed for H660, J00, K30 and Z001 as well. For the curiosity we include a comparison of automatic assignment I10 versus manuals assignment by doctors on a sample of hundred. Out data set was about one million medical reports.
|
|
|
Machine Learning for Google Android
Figura, Juraj ; Bojar, Ondřej (advisor) ; Dušek, Ondřej (referee)
The thesis discusses the topic of machine learning. It describes the theoretical base of the classification task and focuses on two algorithms--decision trees and Naive Bayes classifier. Using these algorithms we have implemented a library for the Android platform. The library provides the basic functionality for the classification task and it is designed with an emphasis on simplicity and efficiency, given that it is aimed for mobile devices. The functionality of the library has been tested on a large data set and its precision has been comparable to other implementations. An important part of the thesis is an application using our library. The application collects data about culture events and helps the user to filter some of them according to his or her personal preferences. As the data are obtained online from real servers, it is not only a sample demonstration, but a usable and potentially useful mobile application.
|
|
|
Classifier for semantic patterns of English verbs
Kríž, Vincent ; Holub, Martin (advisor) ; Bojar, Ondřej (referee)
The goal of the diploma thesis is to design, implement and evaluate classifiers for automatic classification of semantic patterns of English verbs according to a pattern lexicon that draws on the Corpus Pattern Analysis. We use a pilot collection of 30 sample English verbs as training and test data sets. We employ standard methods of machine learning. In our experiments we use decision trees, k-nearest neighbourghs (kNN), support vector machines (SVM) and Adaboost algorithms. Among other things we concentrate on feature design and selection. We experiment with both morpho-syntactic and semantic features. Our results show that the morpho-syntactic features are the most important for statistically-driven semantic disambiguation. Nevertheless, for some verbs the use of semantic features plays an important role.
|
|
|
Information Extraction from Loosely Structured Text
Minárik, Matej ; Bartík, Vladimír (referee) ; Burget, Radek (advisor)
Nowadays we are speaking about Web 2.0, which means the web of documents rather than the web of data. Documents are mostly unstructured, or just partially structured, but search engines need data in structured form in order to provide better search results. The process of extracting structured data from partially structured documents is the main goal of this work. In this work we are analyzing information extraction methods, namely classification methods, which need annotated training data, in order to create their inner model. We also analyze methods, which do not need training. These methods are initialized with a few data examples we are interested in extracting. We propose an extraction method in order to extract therapeutic indications and active substances from medical information sheets.
|
|
|
Bioinformatics Tool for Prediction of Protein Solubility
Hronský, Patrik ; Burgetová, Ivana (referee) ; Martínek, Tomáš (advisor)
This master's thesis addresses the solubility of recombinant proteins and its prediction. It describes the subject of protein synthesis, as well as the process of recombinant protein creation. Recombinant protein synthesis is of great importance for example to pharmacologic industry. This synthesis is not a simple task and it does not always produce viable proteins. Protein solubility is an important factor, determining the viability of the resulting proteins. It is of course favourable for companies, that take part in recombinant protein synthesis, to focus their effort and their resources on proteins, that will be viable in the end. In this regard, bioinformatics is of great help, as it is capable, with the help of machine learning, of predicting the solubility of proteins, for example based on their sequences. This thesis introduces the reader to the basic principles of machine learning and presents several machine learning methods, used in the field of protein solubility prediction. It deals with the definition of a dataset, which is later used to test selected predictors, as well as to train the ensemble predictor, which is the main focus of this thesis. It also focuses on several specific protein solubility predictors and explains the basic principles upon which they are built, as well as the results of their testing. In the end, it presents the ensemble predictor of protein solubility.
|
|
|
Classification Framework
Koroncziová, Dominika ; Otrusina, Lubomír (referee) ; Kouřil, Jan (advisor)
The goal of this work is the design and implementation of a machine learning software, based on the RapidMiner library. The finished application integrates the most commonly used algorithms and processes implemented in RapidMiner into an easily usable program. The application contains a simple command line interface, as well as a graphic interface to simplify selection of multiple parameters. The program also provides a tool to create standalone programs, that can be used for classification with a pre-trained model. On top of the original requirements the possibility to work with textual data from Wikipedia was also implemented, providing a tool for downloading and preprocessing of the data in order to use them as training input. This text focuses on the specifics of the algorithms and classifiers used and on their features and uses, and describes the design and implementation of the system. As part of this work, several tests were run in order to validate the efficiency and functionality of the program. The test results are included at the end of the thesis.
|
|
|
Computer analysis of medical image data
Krajčír, Róbert ; Šmirg, Ondřej (referee) ; Uher, Václav (advisor)
This work deals with medical image analysis, using variety of statisic and numeric methods implemented in Eclipse and Rapidminer environments in Java programming language. Sets of images (slices), which are used here, are the results of magnetic resonance brain examination of several subejcts. Segments in this 3D image are analyzed and some local features are computed, based on which data sets for use in training algorythms are generated. The ability of successful identification of healthy or unhealthy tissues is then practically tested using available data.
|
guest ::
