This work describes actual state of open-source browsers on the Android platform and compares their features. It describes webpage classification problem and methods how to detect porn websites. It also shows a design of a system for blocking and detection of webpages with adult content and its implementation. For pornography detection there were used text based methods but also methods based on detection in images from web page with deep learning. Implemented solution was tested with experiments and described. The last chapter contains summarization of this work and proposal of improvements.

This master's thesis deals with the design and implementation of an algorithm for high-speed network packet filtering. The main goal was to provide hardware architecture, which would support large rule sets and could be used in 100 Gbps networks. The system has been designed with respect to the implementation on an FPGA card and time-space complexity trade-off. Properties of the system have been evaluated using various available rule sets. Due to the highly optimized and deep pipelined architecture it was possible to reach high working frequency (above 220 MHz) together with considerable memory reduction (on average about 72% for compared algorithms). It is also possible to efficiently store up to five thousands of filtering rules on an FPGA with only 8% of on-chip memory utilization. The architecture allows high-speed network packet filtering at wire-speed of 100 Gbps.

The theme of the work is sentiment analysis, especially in terms of informatics (marginally from a linguistic point of view). The linguistic part discusses the term sentiment and language methods for its analysis, e.g. lemmatization, POS tagging, using the list of stopwords etc. More attention is paid to the structure of the sentiment analyzer which is based on some of the machine learning methods (support vector machines, Naive Bayes and maximum entropy classification). On the basis of the theoretical background, a functional analyzer is projected and implemented. The experiments are focused mainly on comparing the classification methods and on the benefits of using the individual preprocessing methods. The success rate of the constructed classifier reaches up to 84 % in the cross-validation.

This project is dedicated to the problem of vehicle classification using inductive loop sensors. We created the dataset that contains more than 11000 labeled inductive loop signatures collected at different times and from different parts of the world. Multiple classification methods and their optimizations were employed to the vehicle classification. Final model that combines K-nearest neighbors and logistic regression achieves 94\% accuracy on classification scheme with 9 classes. The vehicle classifier was implemented in C++.

This work explores machine learning as a tool for medical images' classification. A literary research is contained concerning both classical and modern approaches to image segmentation. The main purpose of this work is to design and implement an extension for the 3D Slicer platform. The extension uses machine learning to classify images using set parameters. The extension is tested on tomographic images obtained by nuclear magnetic resonance and observes the accuracy of the classification and usability in practice.

The thesis is focused on automatic classification of polysomnographic signals based on various parameters in time and frequency domain. The parameters are acquired from 30 seconds long segments of EEG, EMG and EOG signals recorded during different sleep stages. The parameters used for automatic classification of sleep stages are selected according to statistical analysis. Classification is performed using the SVM method and evaluation of the success of the classification is done using sensitivity, specificity and percentage success. Classification method was implemented using Matlab.

This master’s thesis is about automatic digital modulation recognition using artificial neural networks. The paper briefly describes the issue and existing algorithms for solving the problem of modulation recognition. It was found that the best results are achieved when using the feature-recognition methods and artificial neural networks. The digital modulations that were chosen for recognition are described theoretically and they are ASK, FSK, BPSK, QPSK and 16QAM. These modulations are most commonly used today. Later was briefly described theory of neural networks. In another part was given to the characteristic features of modulation for modulation recognition using artificial neural networks. The penultimate part describes the parameters for signal simulation in Matlab, how to create the key features in Matlab and results after experimental simulation. The last part contains neural network optimization experiments.

The aim of this work is sexual dimorphism quantification of greater sciatic notch profile using 2D geometric morphometrics methods. The curvature was digitized by two different methods - manually with contact digitizer MicroScribe G2 and automatically with software Morphome3cs. Results from each method were comparised and advatages and disadvantages of boths methods were discussed. Target sample of 114 adult specimens of known sex was analyzed. This collection comes from Maxwell Museum of Anthropology, The University of New Mexico, Albuquerque and contains 57 male and 57 female hip bones. For the method verification the test smaple contains 112 adult specimens of known sex was used. This collection comes from Universidad Nacional Autonóma de México (UNAM). This collection contains 56 male and 56 female hip bones. The procrustes analysis, principal components analysis, thin plate spine and discriminant function analysis were used for analysis. We could make a detail description of morphologic differences in greater sciatic notch shape of men and women because of shape visualisation and difference of both group was confirmed by discriminant function analysis. Sex assesment achieves accuracy 92,11% - 98,25% in dependence on used methods and number of semilandmarks.

Hyperspectral data for classification of vegetation of alpine treeless in the Krkonoše Mts. ABSTRACT The Master Thesis is a part of the HyMountEcos project, which deals with a complex evaluation of mountain's ecosystems in the Giant Mountains National Park using the hyperspectral data. The area of interest is alpine treeless in the Giant Mountains National Park. The main goal of this thesis was to create detailed methodology for classification of vegetation cover using hyperspectral data from AISA DUAL and APEX sensors, to find a classification method, which would improve the accuracy of the results compared to those found in the literature, and to compare the accuracy reached with these two types of the data. Many different classification algorithms (Spectral Angle Mapper, Linear Spectral Unmixing, Support Vector Machine, MESMA a Neural Net) were applied and the classification results were statistically evaluated and compared in the next part of the work. The classification method Neural Net was found as the most accurate one, as it gives the most accurate results for APEX data (the overall accuracy 96 %, Kappa coefficient 0,95) as well as for AISA DUAL data (the overall accuracy 90 %, Kappa coefficient 0,88). The resulting accuracy of the classification (the overall one and also for some classes) reached...

No description available.