One of the many challenges of machine learning are systems for automatic tagging of music, the complexity of this issue in particular. These systems can be practically used in the content analysis of music or the sorting of music libraries. This thesis deals with the design, training, testing, and evaluation of artificial neural network architectures for automatic tagging of music. In the beginning, attention is paid to the setting of the theoretical foundation of this field. In the practical part of this thesis, 8 architectures of neural networks are designed (4 fully convolutional and 4 convolutional recurrent). These architectures are then trained using the MagnaTagATune Dataset and mel spectrogram. After training, these architectures are tested and evaluated. The best results are achieved by the four-layer convolutional recurrent neural network (CRNN4) with the ROC-AUC = 0.9046 ± 0.0016. As the next step of the practical part of this thesis, a completely new Last.fm Dataset 2020 is created. This dataset uses Last.fm and Spotify API for data acquisition and contains 100 tags and 122877 tracks. The most successful architectures are then trained, tested, and evaluated on this new dataset. The best results on this dataset are achieved by the six-layer fully convolutional neural network (FCNN6) with the ROC-AUC = 0.8590 ± 0.0011. Finally, a simple application is introduced as a concluding point of this thesis. This application is designed for testing individual neural network architectures on a user-inserted audio file. Overall results of this thesis are similar to other papers on the same topic, but this thesis brings several new findings and innovations. In terms of innovations, a significant reduction in the complexity of individual neural network architectures is achieved while maintaining similar results.

This thesis aims at creation of new datasets for text recognition machine learning tasks and experiments with convolutional neural networks on these datasets. It describes architecture of convolutional nets, difficulties of recognizing text from photographs and contemporary works using these networks. Next, creation of annotation, using Tesseract OCR, for dataset comprised from photos of document pages, taken by mobile phones, named Mobile Page Photos. From this dataset two additional are created by cropping characters out of its photos formatted as Street View House Numbers dataset. Dataset Mobile Nice Page Photos Characters contains readable characters and Mobile Page Photos Characters adds hardly readable and unreadable ones. Three models of convolutional nets are created and used for text recognition experiments on these datasets, which are also used for estimation of annotation error.

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.

Over the last century, physiological signals have been broadly analyzed and processed not only to assess the function of the human physiology, but also to better diagnose illnesses or injuries and provide treatment options for patients. In particular, Electrocardiogram (ECG), blood pressure (BP) and impedance are among the most important biomedical signals processed and analyzed. The majority of studies that utilize these signals attempt to diagnose important irregularities such as arrhythmia or blood loss by processing one of these signals. However, the relationship between them is not yet fully studied using computational methods. Therefore, a system that extract and combine features from all physiological signals representative of states such as arrhythmia and loss of blood volume to predict the presence and the severity of such complications is of paramount importance for care givers. This will not only enhance diagnostic methods, but also enable physicians to make more accurate decisions; thereby the overall quality of care provided to patients will improve significantly. In the first part of the dissertation, analysis and processing of ECG signal to detect the most important waves i.e. P, QRS, and T, are described. A wavelet-based method is implemented to facilitate and enhance the detection process. The method not only provides high detection accuracy, but also efficient in regards to memory and execution time. In addition, the method is robust against noise and baseline drift, as supported by the results. The second part outlines a method that extract features from ECG signal in order to classify and predict the severity of arrhythmia. Arrhythmia can be life-threatening or benign. Several methods exist to detect abnormal heartbeats. However, a clear criterion to identify whether the detected arrhythmia is malignant or benign still an open problem. The method discussed in this dissertation will address a novel solution to this important issue. In the third part, a classification model that predicts the severity of loss of blood volume by incorporating multiple physiological signals is elaborated. The features are extracted in time and frequency domains after transforming the signals with Wavelet Transformation (WT). The results support the desirable reliability and accuracy of the system.

Now when information is abundant, practice of Data Journalism is quickly becoming a core technique of the 21st century newsrooms. The diploma thesis "Data Journalism aimed by Datablog IHNED.cz" is focused on introducing Data Journalism as a genre responding to the changes in the society and the technology development. The theoretical part concerns with the history of the subject, the workflow of Data Journalism in the newsrooms and the limitations; such as inappropriate business models, difficult process of collecting data or the lack of training. The main goal of the research is to map the work of the Czech data team in the IHNED.cz and compare the results with the work of teams in Australia. The research methods are combination of quantitative and qualitative analyses. The main source of information are interviews conducted with data journalists from the Czech Republic and Australia. On top of that the research gives deeper understanding of how the integration of data journalists in the newsrooms affect the way journalism can support the existence of media organizations and contribute to the public good. The last part offers predictions of the future of Data Journalism.

Network traffic exhibits a high level of variability over short periods of time. This variability impacts negatively on the performance (accuracy) of anomaly-based network Intrusion Detection Systems (IDS) that are built using predictive models in a batch-learning setup. This thesis investigates how adapting the discriminating threshold of model predictions, specifically to the evaluated traffic, improves the detection rates of these Intrusion Detection models. Specifically, this thesis studied the adaptability features of three well known Machine Learning algorithms: C5.0, Random Forest, and Support Vector Machine. The ability of these algorithms to adapt their prediction thresholds was assessed and analysed under different scenarios that simulated real world settings using the prospective sampling approach. A new dataset (STA2018) was generated for this thesis and used for the analysis. This thesis has demonstrated empirically the importance of threshold adaptation in improving the accuracy of detection models when training and evaluation (test) traffic have different statistical properties. Further investigation was undertaken to analyse the effects of feature selection and data balancing processes on a model's accuracy when evaluation traffic with different significant features were used. The effects of threshold adaptation on reducing the accuracy degradation of these models was statistically analysed. The results showed that, of the three compared algorithms, Random Forest was the most adaptable and had the highest detection rates. This thesis then extended the analysis to apply threshold adaptation on sampled traffic subsets, by using different sample sizes, sampling strategies and label error rates. This investigation showed the robustness of the Random Forest algorithm in identifying the best threshold. The Random Forest algorithm only needed a sample that was 0.05% of the original evaluation traffic to identify a discriminating threshold with an overall accuracy rate of nearly 90% of the optimal threshold.

Les collections de manuscrits sur feuilles de palmier sont devenues une partie intégrante de la culture et de la vie des peuples de l'Asie du Sud-Est. Avec l’augmentation des projets de numérisation des documents patrimoniaux à travers le monde, les collections de manuscrits sur feuilles de palmier ont finalement attiré l'attention des chercheurs en analyse d'images de documents (AID). Les travaux de recherche menés dans le cadre de cette thèse ont porté sur les manuscrits d'Indonésie, et en particulier sur les manuscrits de Bali. Nos travaux visent à proposer des méthodes d’analyse pour les manuscrits sur feuilles de palmier. En effet, ces collections offrent de nouveaux défis car elles utilisent, d’une part, un support spécifique : les feuilles de palmier, et d’autre part, un langage et un script qui n'ont jamais été analysés auparavant. Prenant en compte, le contexte et les conditions de stockage des collections de manuscrits sur feuilles de palmier à Bali, nos travaux ont pour objectif d’apporter une valeur ajoutée aux manuscrits numérisés en développant des outils pour analyser, translittérer et indexer le contenu des manuscrits sur feuilles de palmier. Ces systèmes rendront ces manuscrits plus accessibles, lisibles et compréhensibles à un public plus large ainsi que pour les chercheurs et les étudiants du monde entier. Cette thèse a permis de développer un système d’AID pour les images de documents sur feuilles de palmier, comprenant plusieurs tâches de traitement d'images : numérisation du document, construction de la vérité terrain, binarisation, segmentation des lignes de texte et des glyphes, la reconnaissance des glyphes et des mots, translittération et l’indexation de document. Nous avons ainsi créé le premier corpus et jeu de données de manuscrits balinais sur feuilles de palmier. Ce corpus est actuellement disponible pour les chercheurs en AID. Nous avons également développé un système de reconnaissance des glyphes et un système de translittération automatique des manuscrits balinais. Cette thèse propose un schéma complet de reconnaissance de glyphes spatialement catégorisé pour la translittération des manuscrits balinais sur feuilles de palmier. Le schéma proposé comprend six tâches : la segmentation de lignes de texte et de glyphes, un processus de classification de glyphes, la détection de la position spatiale pour la catégorisation des glyphes, une reconnaissance globale et catégorisée des glyphes, la sélection des glyphes et la translittération basée sur des règles phonologiques. La translittération automatique de l'écriture balinaise nécessite de mettre en œuvre des mécanismes de représentation des connaissances et des règles phonologiques. Nous proposons un système de translittération sans segmentation basée sur la méthode LSTM. Celui-ci a été testé sur des données réelles et synthétiques. Il comprend un schéma d'apprentissage à deux niveaux pouvant s’appliquer au niveau du mot et au niveau de la ligne de texte. / The collection of palm leaf manuscripts is an important part of Southeast Asian people’s culture and life. Following the increasing of the digitization projects of heritage documents around the world, the collection of palm leaf manuscripts in Southeast Asia finally attracted the attention of researchers in document image analysis (DIA). The research work conducted for this dissertation focused on the heritage documents of the collection of palm leaf manuscripts from Indonesia, especially the palm leaf manuscripts from Bali. This dissertation took part in exploring DIA researches for palm leaf manuscripts collection. This collection offers new challenges for DIA researches because it uses palm leaf as writing media and also with a language and script that have never been analyzed before. Motivated by the contextual situations and real conditions of the palm leaf manuscript collections in Bali, this research tried to bring added value to digitized palm leaf manuscripts by developing tools to analyze, to transliterate and to index the content of palm leaf manuscripts. These systems aim at making palm leaf manuscripts more accessible, readable and understandable to a wider audience and, to scholars and students all over the world. This research developed a DIA system for document images of palm leaf manuscripts, that includes several image processing tasks, beginning with digitization of the document, ground truth construction, binarization, text line and glyph segmentation, ending with glyph and word recognition, transliteration and document indexing and retrieval. In this research, we created the first corpus and dataset of the Balinese palm leaf manuscripts for the DIA research community. We also developed the glyph recognition system and the automatic transliteration system for the Balinese palm leaf manuscripts. This dissertation proposed a complete scheme of spatially categorized glyph recognition for the transliteration of Balinese palm leaf manuscripts. The proposed scheme consists of six tasks: the text line and glyph segmentation, the glyph ordering process, the detection of the spatial position for glyph category, the global and categorized glyph recognition, the option selection for glyph recognition and the transliteration with phonological rules-based machine. An implementation of knowledge representation and phonological rules for the automatic transliteration of Balinese script on palm leaf manuscript is proposed. The adaptation of a segmentation-free LSTM-based transliteration system with the generated synthetic dataset and the training schemes at two different levels (word level and text line level) is also proposed.

The continuous progression of urbanization has resulted in an increasing number of people living in cities or towns. In parallel, advancements in technologies, such as the Internet, telecommunications, and transportation, have allowed for better connectivity among people. This has engendered drastic changes in urban systems during the recent decades. From a social geographic perspective, the changes in urban systems are primarily characterized by intensive contacts among people and their interactions with the surrounding urban environment, which further leads to subsequent challenging problems such as traffic jams, environmental pollution, urban sprawl, etc. These problems have been reported to be heterogeneous and non-deterministic. Hence, to cope with them, massive amounts of geographic data are required to create new knowledge on urban systems. Due to the thriving of Volunteer Geographic Information (VGI) in recent years, this thesis presents knowledge on urban systems based on extensive VGI datasets from three sources: highway dataset from the OpenStreetMap (OSM) project, photo location dataset from the Flickr website, and GPS tracking datasets from volunteers, taxicabs, and air flights. The knowledge primarily relates to two issues of urban systems: the urban space and the corresponding human dynamics. In accordance, on one hand, urban space acts as a carrier for associated geographic activities and knowledge of it benefits our understanding of current social and economic problems in urban systems. On the other hand, human dynamics reflect human behavior in urban space, which leads to complex mobility or activity patterns. Its investigation allows a derivation of the underlying driving force that is very instructive to urban planning, traffic management, and infectious disease control. Therefore, to fully understand the two issues, this thesis conducts a thorough investigation from multiple aspects. The first issue is investigated from four aspects. First, at the city level, the controversial topic of city size regularity is investigated in terms of natural cities, and the conclusion is that Zipf’s law holds stably for all US cities. Second, at the sub-city level, the size distribution of spatial units within different cities in terms of the clusters formed by street nodes, photo locations, and taxi static points are explored, and the result shows a remarkable scaling property of these spatial units. Third, enlightened by the scaling property of the urban space at the city or sub-city level, this thesis devises a novel tool that can demarcate the cities into three categories: compact cities, normal cities, and sprawling cities. The tool is then applied to cities in both the US and three European countries. In the last, another representation of urban space is taken into account, namely the transportation network. The findings report that the US airport network displays the properties of scale-free, small-world, and disassortative mixing and that the individual natural airports show heterogeneous patterns that are probably subject to geographic constraints and socioeconomic factors. The second issue is examined from four perspectives. First, at the city level, the movement flow contributed by agents using two types of behavior is investigated through an agent-based simulation, and the result conjectures that the human mobility behavior is mainly shaped by the underlying street network. Second, at the country level, this thesis reports that the human travel length by air can be approximated well by an exponential distribution, and subsequent simulations indicate that human mobility behavior is largely constrained by the underlying airport network. Third, at the regional level, the length that humans travel by car is demonstrated to agree well with a power law with exponential cutoff distribution, and subsequent simulation further reproduces this levy flight characteristic. Based on the simulation, human mobility behavior is again revealed to be primarily shaped by the underlying hierarchical spatial structure. Finally, taxicab static points are adopted to explore human activity patterns, which can be characterized as the regularities in space and time, the heterogeneity and predictability in space. From a complex system perspective, this thesis presents the knowledge discovered in urban systems using massive volumes of geographic data. Together with new knowledge from empirical findings, the development of methods, and the design of theoretic models, this thesis also shares the research community with geographic data generated from extensive VGI datasets and the corresponding source codes. Moreover, this study is aligned with a paradigm shift in that it analyzes large-size datasets using high processing power as opposed to analyzing small-size datasets with low processing power. / <p>QC 20121113</p>

This thesis explores Chance-Constrained Programming (CCP) in the context of learning. It is shown that chance-constraint approaches lead to improved algorithms for three important learning problems — classification with specified error rates, large dataset classification and Ordinal Regression (OR). Using moments of training data, the CCPs are posed as Second Order Cone Programs (SOCPs). Novel iterative algorithms for solving the resulting SOCPs are also derived. Borrowing ideas from robust optimization theory, the proposed formulations are made robust to moment estimation errors. A maximum margin classifier with specified false positive and false negative rates is derived. The key idea is to employ chance-constraints for each class which imply that the actual misclassification rates do not exceed the specified. The formulation is applied to the case of biased classification. The problems of large dataset classification and ordinal regression are addressed by deriving formulations which employ chance-constraints for clusters in training data rather than constraints for each data point. Since the number of clusters can be substantially smaller than the number of data points, the resulting formulation size and number of inequalities are very small. Hence the formulations scale well to large datasets. The scalable classification and OR formulations are extended to feature spaces and the kernelized duals turn out to be instances of SOCPs with a single cone constraint. Exploiting this speciality, fast iterative solvers which outperform generic SOCP solvers, are proposed. Compared to state-of-the-art learners, the proposed algorithms achieve a speed up as high as 10000 times, when the specialized SOCP solvers are employed. The proposed formulations involve second order moments of data and hence are susceptible to moment estimation errors. A generic way of making the formulations robust to such estimation errors is illustrated. Two novel confidence sets for moments are derived and it is shown that when either of the confidence sets are employed, the robust formulations also yield SOCPs.

The aim of this work is to create a tool for automatic transcription of historical documents. The work is mainly focused on the recognition of texts from the period of modern times written using font Fraktur. The problem is solved with a newly designed recurrent convolutional neural networks and a Spatial Transformer Network. Part of the solution is also an implemented generator of artificial historical texts. Using this generator, an artificial data set is created on which the convolutional neural network for line recognition is trained. This network is then tested on real historical lines of text on which the network achieves up to 89.0 % of character accuracy. The contribution of this work is primarily the newly designed neural network for text line recognition and the implemented artificial text generator, with which it is possible to train the neural network to recognize real historical lines of text.