This master's thesis deals with the problems of anomalies detection in data from clinical trials and medical registries. The purpose of this work is to perform literary research about quality of data in clinical trials and to design a personal algorithm for detection of anomalous records based on machine learning methods in real clinical data from current or completed clinical trials or medical registries. In the practical part is described the implemented algorithm of detection, consists of several parts: import of data from information system, preprocessing and transformation of imported data records with variables of different data types into numerical vectors, using well known statistical methods for detection outliers and evaluation of the quality and accuracy of the algorithm. The result of creating the algorithm is vector of parameters containing anomalies, which has to make the work of data manager easier. This algorithm is designed for extension the palette of information system functions (CLADE-IS) on automatic monitoring the quality of data by detecting anomalous records.

The biometric techniques are well known and widespread nowadays. In this context biometry means automated person recognition using anatomic features. This work uses the iris as the anatomic feature. Iris recognition is taken as the most promising technique of all because of its non-invasiveness and low error rate. The inventor of iris recognition is John G. Daugman. His work underlies almost all current public works of this technology. This final thesis is concerned with biometry based on iris images. The principles of biometric methods based on iris images are described in the first part. The first practical part of this work is aimed at the proposal and realization of two methods which localize the iris inner boundary. The third part presents the proposal and realization of iris image processing in order to classifying persons. The last chapter is focus on evaluation of experimental results and there are also compared our results with several well-known methods.

Help documents are important in an organization to use the technology applications licensed from a vendor. Customers and internal employees frequently use and interact with the help documents section to use the applications and know about the new features and developments in them. Help documents consist of various knowledge base materials, question and answer documents and help content. In day- to-day life, customers go through these documents to set up, install or use the product. Recommending similar documents to the customers can increase customer engagement in the product and can also help them proceed without any hurdles. The main aim of this study is to build a recommendation system by exploring different machine-learning techniques to recommend the most relevant and similar help document to the user. To achieve this, in this study a hybrid-based recommendation system for help documents is proposed where the documents are recommended based on similarity of the content using content-based filtering and similarity between the users using collaborative filtering. Finally, the recommendations from content-based filtering and collaborative filtering are combined and ranked to form a comprehensive list of recommendations. The proposed approach is evaluated by the internal employees of the company and by external users. Our experimental results demonstrate that the proposed approach is feasible and provides an effective way to recommend help documents.

This thesis deals with mining of relevant information from documents and automatic splitting of multiple documents merged together. Moreover, it describes the design and implementation of software for data mining from documents and for automatic splitting of multiple documents. Methods for acquiring textual data from scanned documents, named entity recognition, document clustering, their supportive algorithms and metrics for automatic splitting of documents are described in this thesis. Furthermore, an algorithm of implemented software is explained and tools and techniques used by this software are described. Lastly, the success rate of the implemented software is evaluated. In conclusion, possible extensions and further development of this thesis are discussed at the end.

Android is the second most targeted operating system for malware authors and to counter the development of Android malware, more knowledge about their behavior is needed. There are mainly two approaches to analyze Android malware, namely static and dynamic analysis. Recently in 2017, a study and well labeled dataset, named AMD (Android Malware Dataset), consisting of over 24,000 malware samples was released. It is divided into 135 varieties based on similar malicious behavior, retrieved through static analysis of the file classes.dex in the APK of each malware, whereas the labeled features were determined by manual inspection of three samples in each variety. However, static analysis is known to be weak against obfuscation techniques, such as repackaging or dynamic loading, which can be exploited to avoid the analysis. In this study the second approach is utilized and all malware in the dataset are analyzed at run-time in order to monitor their dynamic behavior. However, analyzing malware at run-time has known weaknesses as well, as it can be avoided through, for instance, anti-emulator techniques. Therefore, the study aimed to explore the available sandbox environments for dynamic analysis, study the effectiveness of fingerprinting Android malware using one of the tools and investigate whether static features from AMD and the dynamic analysis correlate. For instance, by an attempt to classify the samples based on similar dynamic features and calculating the Pearson Correlation Coefficient (r) for all combinations of features from AMD and the dynamic analysis. The comparison of tools for dynamic analysis, showed a need of development, as most popular tools has been released for a long time and the common factor is a lack of continuous maintenance. As a result, the choice of sandbox environment for this study ended up as Droidbox, because of aspects like ease of use/install and easily adaptable for large scale analysis. Based on the dynamic features extracted with Droidbox, it could be shown that Android malware are more similar to the varieties which they belong to. The best metric for classifying samples to varieties, out of four investigated metrics, turned out to be Cosine Similarity, which received an accuracy of 83.6% for the entire dataset. The high accuracy indicated a correlation between the dynamic features and static features which the varieties are based on. Furthermore, the Pearson Correlation Coefficient confirmed that the manually extracted features, used to describe the varieties, and the dynamic features are correlated to some extent, which could be partially confirmed by a manual inspection in the end of the study.

The rapid growth of text based information on the World Wide Web and various applications making use of this data motivates the need for efficient and effective methods to identify and separate the “main content” from the additional content items, such as navigation menus, advertisements, design elements or legal disclaimers. Firstly, in this thesis, we study, develop, and evaluate R2L, DANA, DANAg, and AdDANAg, a family of novel algorithms for extracting the main content of web documents. The main concept behind R2L, which also provided the initial idea and motivation for the other three algorithms, is to use well particularities of Right-to-Left languages for obtaining the main content of web pages. As the English character set and the Right-to-Left character set are encoded in different intervals of the Unicode character set, we can efficiently distinguish the Right-to-Left characters from the English ones in an HTML file. This enables the R2L approach to recognize areas of the HTML file with a high density of Right-to-Left characters and a low density of characters from the English character set. Having recognized these areas, R2L can successfully separate only the Right-to-Left characters. The first extension of the R2L, DANA, improves effectiveness of the baseline algorithm by employing an HTML parser in a post processing phase of R2L for extracting the main content from areas with a high density of Right-to-Left characters. DANAg is the second extension of the R2L and generalizes the idea of R2L to render it language independent. AdDANAg, the third extension of R2L, integrates a new preprocessing step to normalize the hyperlink tags. The presented approaches are analyzed under the aspects of efficiency and effectiveness. We compare them to several established main content extraction algorithms and show that we extend the state-of-the-art in terms of both, efficiency and effectiveness. Secondly, automatically extracting the headline of web articles has many applications. We develop and evaluate a content-based and language-independent approach, TitleFinder, for unsupervised extraction of the headline of web articles. The proposed method achieves high performance in terms of effectiveness and efficiency and outperforms approaches operating on structural and visual features. / Das rasante Wachstum von textbasierten Informationen im World Wide Web und die Vielfalt der Anwendungen, die diese Daten nutzen, macht es notwendig, effiziente und effektive Methoden zu entwickeln, die den Hauptinhalt identifizieren und von den zusätzlichen Inhaltsobjekten wie z.B. Navigations-Menüs, Anzeigen, Design-Elementen oder Haftungsausschlüssen trennen. Zunächst untersuchen, entwickeln und evaluieren wir in dieser Arbeit R2L, DANA, DANAg und AdDANAg, eine Familie von neuartigen Algorithmen zum Extrahieren des Inhalts von Web-Dokumenten. Das grundlegende Konzept hinter R2L, das auch zur Entwicklung der drei weiteren Algorithmen führte, nutzt die Besonderheiten der Rechts-nach-links-Sprachen aus, um den Hauptinhalt von Webseiten zu extrahieren. Da der lateinische Zeichensatz und die Rechts-nach-links-Zeichensätze durch verschiedene Abschnitte des Unicode-Zeichensatzes kodiert werden, lassen sich die Rechts-nach-links-Zeichen leicht von den lateinischen Zeichen in einer HTML-Datei unterscheiden. Das erlaubt dem R2L-Ansatz, Bereiche mit einer hohen Dichte von Rechts-nach-links-Zeichen und wenigen lateinischen Zeichen aus einer HTML-Datei zu erkennen. Aus diesen Bereichen kann dann R2L die Rechts-nach-links-Zeichen extrahieren. Die erste Erweiterung, DANA, verbessert die Wirksamkeit des Baseline-Algorithmus durch die Verwendung eines HTML-Parsers in der Nachbearbeitungsphase des R2L-Algorithmus, um den Inhalt aus Bereichen mit einer hohen Dichte von Rechts-nach-links-Zeichen zu extrahieren. DANAg erweitert den Ansatz des R2L-Algorithmus, so dass eine Sprachunabhängigkeit erreicht wird. Die dritte Erweiterung, AdDANAg, integriert eine neue Vorverarbeitungsschritte, um u.a. die Weblinks zu normalisieren. Die vorgestellten Ansätze werden in Bezug auf Effizienz und Effektivität analysiert. Im Vergleich mit mehreren etablierten Hauptinhalt-Extraktions-Algorithmen zeigen wir, dass sie in diesen Punkten überlegen sind. Darüber hinaus findet die Extraktion der Überschriften aus Web-Artikeln vielfältige Anwendungen. Hierzu entwickeln wir mit TitleFinder einen sich nur auf den Textinhalt beziehenden und sprachabhängigen Ansatz. Das vorgestellte Verfahren ist in Bezug auf Effektivität und Effizienz besser als bekannte Ansätze, die auf strukturellen und visuellen Eigenschaften der HTML-Datei beruhen.

The aim of the thesis was to design, implement and evaluate the results of automatic tests for the JavaScript Restrictor project, which is being developed as a web browser extension. The tests are divided into three levels - unit, integration, and system. The Unit Tests verify the behavior of individual features, the Integration Tests verify the correct wrapping of browser API endpoints, and the System Tests check that the extension does not suppress the desired functionality of web pages. The System Tests are implemented for parallel execution in a distributed environment which has succeeded in achieving an almost directly proportional reduction in time with respect to the number of the tested nodes. The benefit of this work is detection of previously unknown errors in the JavaScript Restrictor extension and provision of the necessary information that allowed to fix some of the detected bugs.

The rapid growth of text based information on the World Wide Web and various applications making use of this data motivates the need for efficient and effective methods to identify and separate the “main content” from the additional content items, such as navigation menus, advertisements, design elements or legal disclaimers. Firstly, in this thesis, we study, develop, and evaluate R2L, DANA, DANAg, and AdDANAg, a family of novel algorithms for extracting the main content of web documents. The main concept behind R2L, which also provided the initial idea and motivation for the other three algorithms, is to use well particularities of Right-to-Left languages for obtaining the main content of web pages. As the English character set and the Right-to-Left character set are encoded in different intervals of the Unicode character set, we can efficiently distinguish the Right-to-Left characters from the English ones in an HTML file. This enables the R2L approach to recognize areas of the HTML file with a high density of Right-to-Left characters and a low density of characters from the English character set. Having recognized these areas, R2L can successfully separate only the Right-to-Left characters. The first extension of the R2L, DANA, improves effectiveness of the baseline algorithm by employing an HTML parser in a post processing phase of R2L for extracting the main content from areas with a high density of Right-to-Left characters. DANAg is the second extension of the R2L and generalizes the idea of R2L to render it language independent. AdDANAg, the third extension of R2L, integrates a new preprocessing step to normalize the hyperlink tags. The presented approaches are analyzed under the aspects of efficiency and effectiveness. We compare them to several established main content extraction algorithms and show that we extend the state-of-the-art in terms of both, efficiency and effectiveness. Secondly, automatically extracting the headline of web articles has many applications. We develop and evaluate a content-based and language-independent approach, TitleFinder, for unsupervised extraction of the headline of web articles. The proposed method achieves high performance in terms of effectiveness and efficiency and outperforms approaches operating on structural and visual features. / Das rasante Wachstum von textbasierten Informationen im World Wide Web und die Vielfalt der Anwendungen, die diese Daten nutzen, macht es notwendig, effiziente und effektive Methoden zu entwickeln, die den Hauptinhalt identifizieren und von den zusätzlichen Inhaltsobjekten wie z.B. Navigations-Menüs, Anzeigen, Design-Elementen oder Haftungsausschlüssen trennen. Zunächst untersuchen, entwickeln und evaluieren wir in dieser Arbeit R2L, DANA, DANAg und AdDANAg, eine Familie von neuartigen Algorithmen zum Extrahieren des Inhalts von Web-Dokumenten. Das grundlegende Konzept hinter R2L, das auch zur Entwicklung der drei weiteren Algorithmen führte, nutzt die Besonderheiten der Rechts-nach-links-Sprachen aus, um den Hauptinhalt von Webseiten zu extrahieren. Da der lateinische Zeichensatz und die Rechts-nach-links-Zeichensätze durch verschiedene Abschnitte des Unicode-Zeichensatzes kodiert werden, lassen sich die Rechts-nach-links-Zeichen leicht von den lateinischen Zeichen in einer HTML-Datei unterscheiden. Das erlaubt dem R2L-Ansatz, Bereiche mit einer hohen Dichte von Rechts-nach-links-Zeichen und wenigen lateinischen Zeichen aus einer HTML-Datei zu erkennen. Aus diesen Bereichen kann dann R2L die Rechts-nach-links-Zeichen extrahieren. Die erste Erweiterung, DANA, verbessert die Wirksamkeit des Baseline-Algorithmus durch die Verwendung eines HTML-Parsers in der Nachbearbeitungsphase des R2L-Algorithmus, um den Inhalt aus Bereichen mit einer hohen Dichte von Rechts-nach-links-Zeichen zu extrahieren. DANAg erweitert den Ansatz des R2L-Algorithmus, so dass eine Sprachunabhängigkeit erreicht wird. Die dritte Erweiterung, AdDANAg, integriert eine neue Vorverarbeitungsschritte, um u.a. die Weblinks zu normalisieren. Die vorgestellten Ansätze werden in Bezug auf Effizienz und Effektivität analysiert. Im Vergleich mit mehreren etablierten Hauptinhalt-Extraktions-Algorithmen zeigen wir, dass sie in diesen Punkten überlegen sind. Darüber hinaus findet die Extraktion der Überschriften aus Web-Artikeln vielfältige Anwendungen. Hierzu entwickeln wir mit TitleFinder einen sich nur auf den Textinhalt beziehenden und sprachabhängigen Ansatz. Das vorgestellte Verfahren ist in Bezug auf Effektivität und Effizienz besser als bekannte Ansätze, die auf strukturellen und visuellen Eigenschaften der HTML-Datei beruhen.