Le discours haineux est un problème sérieux sur les média sociaux. Dans ce mémoire, nous étudions le problème de détection automatique du langage haineux sur réseaux sociaux. Nous traitons ce problème comme un problème de classification de textes. La classification de textes a fait un grand progrès ces dernières années grâce aux techniques d’apprentissage profond. En particulier, les modèles utilisant un mécanisme d’attention tel que BERT se sont révélés capables de capturer les informations contextuelles contenues dans une phrase ou un texte. Cependant, leur capacité à saisir l’information globale sur le vocabulaire d’une langue dans une application spécifique est plus limitée. Récemment, un nouveau type de réseau de neurones, appelé Graph Convolutional Network (GCN), émerge. Il intègre les informations des voisins en manipulant un graphique global pour prendre en compte les informations globales, et il a obtenu de bons résultats dans de nombreuses tâches, y compris la classification de textes. Par conséquent, notre motivation dans ce mémoire est de concevoir une méthode qui peut combiner à la fois les avantages du modèle BERT, qui excelle en capturant des informations locales, et le modèle GCN, qui fournit les informations globale du langage. Néanmoins, le GCN traditionnel est un modèle d'apprentissage transductif, qui effectue une opération convolutionnelle sur un graphe composé d'éléments à traiter dans les tâches (c'est-à-dire un graphe de documents) et ne peut pas être appliqué à un nouveau document qui ne fait pas partie du graphe pendant l'entraînement. Dans ce mémoire, nous proposons d'abord un nouveau modèle GCN de vocabulaire (VGCN), qui transforme la convolution au niveau du document du modèle GCN traditionnel en convolution au niveau du mot en utilisant les co-occurrences de mots. En ce faisant, nous transformons le mode d'apprentissage transductif en mode inductif, qui peut être appliqué à un nouveau document. Ensuite, nous proposons le modèle Interactive-VGCN-BERT qui combine notre modèle VGCN avec BERT. Dans ce modèle, les informations locales captées par BERT sont combinées avec les informations globales captées par VGCN. De plus, les informations locales et les informations globales interagissent à travers différentes couches de BERT, ce qui leur permet d'influencer mutuellement et de construire ensemble une représentation finale pour la classification. Via ces interactions, les informations de langue globales peuvent aider à distinguer des mots ambigus ou à comprendre des expressions peu claires, améliorant ainsi les performances des tâches de classification de textes. Pour évaluer l'efficacité de notre modèle Interactive-VGCN-BERT, nous menons des expériences sur plusieurs ensembles de données de différents types -- non seulement sur le langage haineux, mais aussi sur la détection de grammaticalité et les commentaires sur les films. Les résultats expérimentaux montrent que le modèle Interactive-VGCN-BERT surpasse tous les autres modèles tels que Vanilla-VGCN-BERT, BERT, Bi-LSTM, MLP, GCN et ainsi de suite. En particulier, nous observons que VGCN peut effectivement fournir des informations utiles pour aider à comprendre un texte haiteux implicit quand il est intégré avec BERT, ce qui vérifie notre intuition au début de cette étude. / Hate speech is a serious problem on social media. In this thesis, we investigate the problem of automatic detection of hate speech on social media. We cast it as a text classification problem. With the development of deep learning, text classification has made great progress in recent years. In particular, models using attention mechanism such as BERT have shown great capability of capturing the local contextual information within a sentence or document. Although local connections between words in the sentence can be captured, their ability of capturing certain application-dependent global information and long-range semantic dependency is limited. Recently, a new type of neural network, called the Graph Convolutional Network (GCN), has attracted much attention. It provides an effective mechanism to take into account the global information via the convolutional operation on a global graph and has achieved good results in many tasks including text classification. In this thesis, we propose a method that can combine both advantages of BERT model, which is excellent at exploiting the local information from a text, and the GCN model, which provides the application-dependent global language information. However, the traditional GCN is a transductive learning model, which performs a convolutional operation on a graph composed of task entities (i.e. documents graph) and cannot be applied directly to a new document. In this thesis, we first propose a novel Vocabulary GCN model (VGCN), which transforms the document-level convolution of the traditional GCN model to word-level convolution using a word graph created from word co-occurrences. In this way, we change the training method of GCN, from the transductive learning mode to the inductive learning mode, that can be applied to new documents. Secondly, we propose an Interactive-VGCN-BERT model that combines our VGCN model with BERT. In this model, local information including dependencies between words in a sentence, can be captured by BERT, while the global information reflecting the relations between words in a language (e.g. related words) can be captured by VGCN. In addition, local information and global information can interact through different layers of BERT, allowing them to influence mutually and to build together a final representation for classification. In so doing, the global language information can help distinguish ambiguous words or understand unclear expressions, thereby improving the performance of text classification tasks. To evaluate the effectiveness of our Interactive-VGCN-BERT model, we conduct experiments on several datasets of different types -- hate language detection, as well as movie review and grammaticality, and compare them with several state-of-the-art baseline models. Experimental results show that our Interactive-VGCN-BERT outperforms all other models such as Vanilla-VGCN-BERT, BERT, Bi-LSTM, MLP, GCN, and so on. In particular, we have found that VGCN can indeed help understand a text when it is integrated with BERT, confirming our intuition to combine the two mechanisms.

Tato práce se zaměřuje na problém počítání vozidel v statickém obraze bez znalosti geometrických vlastností scény. V rámci řešení bylo implementováno a natrénováno 5 architektur konvolučních neuronových sítí. Také byl pořízen rozsáhlý dataset s 19 310 snímky pořízených z 12pohledů a zachycujících 7 různých scén. Použité konvoluční sítě mapují vstupní vzorek na mapu hustoty vozidel, ze které lze získat jejich počet a lokalizaci v kontextu vstupního snímku. Hlavním přínosem této práce je porovnání a aplikace dosavadních nejlepších řešení pro počítání objektů v obraze. Většina z těchto architektur byla navržena pro počítání lidí v obraze, proto musely být uzpůsobeny pro potřeby počítání vozidel v statickém obraze. Natrénované modely jsou vyhodnoceny GAME metrikou na TRANCOS datasetu a na velkém spojeném datasetu. Dosažené výsledky všech modelů jsou následně popsány a porovnány.

The threaded fastener is by far the most common method for securing components together and plays a significant role in determining the quality of a product. Atlas Copco offers industrial tools for tightening these fasteners, which are today suffering from errors in the applied torque. These errors have been found to behave in periodic patterns which indicate that the errors can be predicted and therefore compensated for. However, this is only possible by knowing the rotational position of the tool. Atlas Copco is interested in the possibility of acquiring this rotational position without installing sensors inside the tools. To address this challenge, the thesis explores the feasibility of estimating the rotational position by analysing the behaviour of the errors and finding periodicities in the data. The objective is to determine whether these periodicities can be used to accurately estimate the rotation of the torque errors of unknown data relative to errors of data where the rotational position is known. The tool analysed in this thesis exhibits a periodic pattern in the torque error with a period of 11 revolutions.  Two methods for estimating the rotational position were evaluated: a simple nearest neighbour method that uses mean squared error (MSE) as distance measure, and a more complex circular fully convolutional network (CFCN). The project involved data collection from a custom-built setup. However, the setup was not fully completed, and the models were therefore evaluated on a limited dataset. The results showed that the CFCN method was not able to identify the rotational position of the signal. The insufficient size of the data is discussed to be the cause for this. The nearest neighbour method, however, was able to estimate the rotational position correctly with 100% accuracy across 1000 iterations, even when looking at a fragment of a signal as small as 40%. Unfortunately, this method is computationally demanding and exhibits slow performance when applied to large datasets. Consequently, adjustments are required to enhance its practical applicability. In summary, the findings suggest that the nearest neighbour method is a promising approach for estimating the rotational position and could potentially contribute to improving the accuracy of tools. / Skruvförband är den vanligaste typen av förband för att sammanfoga komponenter och är avgörande för en produkts kvalitet. Atlas Copco tillverkar industriverktyg avsedda för sådana skruvförband, som dessvärre lider av små avvikelser i åtdragningsmomentet. Avvikelserna uppvisar ett konsekvent periodiskt mönster, vilket indikerar att de är förutsägbara och därför möjliga att kompenseras för. Det är dock endast möjligt genom att veta verktygets vinkelposition. Atlas Copco vill veta om det är möjligt att erhålla vinkelpositionen utan att installera sensorer i verktygen. Denna uppsats undersöker möjligheten att uppskatta vinkelpositionen genom att analysera beteendet hos avvikelserna i åtdragningsmomentet och identifiera periodiciteter i datan, samt undersöka om dessa periodiciteter kan utnyttjas för att uppskatta rotationen hos avvikelserna hos okänd data i förhållande till tidigare data. Det verktyget som används i detta projekt uppvisar en tydlig periodicitet med en period på 11 varv. Två metoder för att uppskatta vinkelpositionen utvärderades: en simpel nearest neighbour-metod som använder mean squared error (MSE) som mått för avstånd, och ett mer komplext circular fully convolutional network (CFCN). Projektet innefattade datainsamling från en egendesignad testrigg som tyvärr aldrig blev färdigställd, vilket medförde att utvärderingen av modellerna utfördes på ett begränsat dataset.  Resultatet indikerade att CFCN-metoden kräver en större datamängd för att kunna uppskatta rotationen hos den okända datan. Nearest neighbour-metoden lyckades uppskatta rotationen med 100% noggrannhet över 1000 iterationer, även när endast ett segment så litet som 40% av signalen utvärderades. Tyvärr lider denna metod av hög beräkningsbelastning och kräver förbättringar för att vara praktiskt tillämpbar. Sammantaget visade resultaten att nearest neighbour-metoden har potential att vara ett lovande tillvägagångssätt för att uppskatta vinkelpositionen och kan på så sätt bidra till förbättring av verktygens noggrannhet.

<p dir="ltr">Since graphs are natural representations for encoding relational data, the problem of graph matching is an emerging task and has attracted increasing attention, which could potentially impact various domains such as social network de-anonymization and computer vision. Our main interest is designing polynomial-time algorithms for seeded graph matching problems where a subset of pre-matched vertex-pairs (seeds) is revealed. </p><p dir="ltr">However, the existing work does not fully investigate the pivotal role of seeds and falls short of making the most use of the seeds. Notably, the majority of existing hand-crafted algorithms only focus on using ``witnesses'' in the 1-hop neighborhood. Although some advanced algorithms are proposed to use multi-hop witnesses, their theoretical analysis applies only to \ER random graphs and requires seeds to be all correct, which often do not hold in real applications. Furthermore, a parallel line of research, Graph Neural Network (GNN) approaches, typically employs a semi-supervised approach, which requires a large number of seeds and lacks the capacity to distill knowledge transferable to unseen graphs.</p><p dir="ltr">In my dissertation, I have taken two approaches to address these limitations. In the first approach, we study to design hand-crafted algorithms that can properly use multi-hop witnesses to match graphs. We first study graph matching using multi-hop neighborhoods when partially-correct seeds are provided. Specifically, consider two correlated graphs whose edges are sampled independently from a parent \ER graph $\mathcal{G}(n,p)$. A mapping between the vertices of the two graphs is provided as seeds, of which an unknown fraction is correct. We first analyze a simple algorithm that matches vertices based on the number of common seeds in the $1$-hop neighborhoods, and then further propose a new algorithm that uses seeds in the $D$-hop neighborhoods. We establish non-asymptotic performance guarantees of perfect matching for both $1$-hop and $2$-hop algorithms, showing that our new $2$-hop algorithm requires substantially fewer correct seeds than the $1$-hop algorithm when graphs are sparse. Moreover, by combining our new performance guarantees for the $1$-hop and $2$-hop algorithms, we attain the best-known results (in terms of the required fraction of correct seeds) across the entire range of graph sparsity and significantly improve the previous results. We then study the role of multi-hop neighborhoods in matching power-law graphs. Assume that two edge-correlated graphs are independently edge-sampled from a common parent graph with a power-law degree distribution. A set of correctly matched vertex-pairs is chosen at random and revealed as initial seeds. Our goal is to use the seeds to recover the remaining latent vertex correspondence between the two graphs. Departing from the existing approaches that focus on the use of high-degree seeds in $1$-hop neighborhoods, we develop an efficient algorithm that exploits the low-degree seeds in suitably-defined $D$-hop neighborhoods. Our result achieves an exponential reduction in the seed size requirement compared to the best previously known results.</p><p dir="ltr">In the second approach, we study GNNs for seeded graph matching. We propose a new supervised approach that can learn from a training set how to match unseen graphs with only a few seeds. Our SeedGNN architecture incorporates several novel designs, inspired by our theoretical studies of seeded graph matching: 1) it can learn to compute and use witness-like information from different hops, in a way that can be generalized to graphs of different sizes; 2) it can use easily-matched node-pairs as new seeds to improve the matching in subsequent layers. We evaluate SeedGNN on synthetic and real-world graphs and demonstrate significant performance improvements over both non-learning and learning algorithms in the existing literature. Furthermore, our experiments confirm that the knowledge learned by SeedGNN from training graphs can be generalized to test graphs of different sizes and categories.</p>

Given satellite images with accompanying pixel classifications and elevation data, we propose different solutions to object detection. The first method uses hierarchical clustering for segmentation and then employs different methods of classification. One of these classification methods used domain knowledge to classify objects while the other used Support Vector Machines. Additionally, a combination of three Support Vector Machines were used in a hierarchical structure which out-performed the regular Support Vector Machine method in most of the evaluation metrics. The second approach is more conventional with different types of Convolutional Neural Networks. A segmentation network was used as well as a few detection networks and different fusions between these. The Convolutional Neural Network approach proved to be the better of the two in terms of precision and recall but the clustering approach was not far behind. This work was done using a relatively small amount of data which potentially could have impacted the results of the Machine Learning models in a negative way.

No description available.

Cílem této diplomové práce je automatizace detekce vad ve vláknitých materiálech. Firma SILON se již přes padesát let zabývá výrobou jemné vaty z recyklovaných PET lahví. Tato vata se následně používá ve stavebnictví, automobilovém průmyslu, ale nejčastěji v dámských hygienických potřebách a dětských plenách. Cílem firmy je produkovat co nejkvalitnější výrobek a proto je každá dávka testována v laboratoři s několika přísnými kritérii. Jednám z testů je i množství vadných vláken, jako jsou zacuchané smotky vláken, nebo nevydloužená vlákna, která jsou tvrdá a snadno se lámou. Navrhovaný systém sestává ze snímací lavice fungující jako scanner, která nasnímá vzorek vláken, který byl vložen mezi dvě skleněné desky. Byla provedena série testů s různým osvětlením, která ověřovala vlastnosti Rhodaminu, který se používá právě na rozlišení defektů od ostatních vláken. Tyto defekty mají zpravidla jinou molekulární strukturu, na kterou se barvivo chytá lépe. Protože je Rhodamin fluorescenční barvivo, je možné ho například pod UV světlem snáze rozeznat. Tento postup je využíván při manuální detekci. Při snímání kamerou je možno si vypomoci filtrem na kameře, který odfiltruje excitační světlo a propustí pouze světlo vyzářené Rhodaminem. Součástí výroby skeneru byla i tvorba ovládacího programu. Byla vytvořena vlastní knihovna pro ovládání motoru a byla upravena knihovna pro kameru. Oba systém pak bylo možno ovládat pomocí jednotného GUI, které zajišťovalo pořizování snímku celé desky. Pomocí skeneru byla nasnímána řada snímků, které bylo třeba anotovat, aby bylo možné naučit počítač rozlišovat defekty. Anotace proběhla na pixelové úrovni; každý defekt byl označen v grafickém editoru ve speciální vrstvě. Pro rozlišování byla použita umělá neuronová síť, která funguje na principu konvolucí. Tento typ sítě je navíc plně konvoluční, takže výstupem sítě je obraz, který by měl označit na tom původním vadné pixely. Výsledky naučené sítě jsou v práci prezentovány a diskutovány. Síť byla schopna se naučit rozeznávat většinu defektů a spolehlivě je umí rozeznat a segmentovat. Potíže má v současné době s detekcí rozmazaných defektů na krajích zorného pole a s defekty, jejichž hranice není tolik zřetelná na vstupních obrazech. Nutno zmínit, že zákazník má zájem o kompletní řešení scanneru i s detekčním softwarem a vývoj tohoto zařízení bude pokračovat i po závěru této diplomové práce.

<p>The most important networks from different domains—such as Computing, Organization, Economic, Social, Academic, and Biology—are networks that change over time. For example, in an organization there are email and collaboration networks (e.g., different people or teams working on a document). Apart from the connectivity of the networks changing over time, they can contain attributes such as the topic of an email or message, contents of a document, or the interests of a person in an academic citation or a social network. Analyzing these dynamic networks can be critical in decision-making processes. For instance, in an organization, getting insight into how people from different teams collaborate, provides important information that can be used to optimize workflows.</p> <p><br></p> <p>Network generative models provide a way to study and analyze networks. For example, benchmarking model performance and generalization in tasks like node classification, can be done by evaluating models on synthetic networks generated with varying structure and attribute correlation. In this work, we begin by presenting our systemic study of the impact that graph structure and attribute auto-correlation on the task of node classification using collective inference. This is the first time such an extensive study has been done. We take advantage of a recently developed method that samples attributed networks—although static—with varying network structure jointly with correlated attributes. We find that the graph connectivity that contributes to the network auto-correlation (i.e., the local relationships of nodes) and density have the highest impact on the performance of collective inference methods.</p> <p><br></p> <p>Most of the literature to date has focused on static representations of networks, partially due to the difficulty of finding readily-available datasets of dynamic networks. Dynamic network generative models can bridge this gap by generating synthetic graphs similar to observed real-world networks. Given that motifs have been established as building blocks for the structure of real-world networks, modeling them can help to generate the graph structure seen and capture correlations in node connections and activity. Therefore, we continue with a study of motif evolution in <em>dynamic</em> temporal graphs. Our key insight is that motifs rarely change configurations in fast-changing dynamic networks (e.g. wedges intotriangles, and vice-versa), but rather keep reappearing at different times while keeping the same configuration. This finding motivates the generative process of our proposed models, using temporal motifs as building blocks, that generates dynamic graphs with links that appear and disappear over time.</p> <p><br></p> <p>Our first proposed model generates dynamic networks based on motif-activity and the roles that nodes play in a motif. For example, a wedge is sampled based on the likelihood of one node having the role of hub with the two other nodes being the spokes. Our model learns all parameters from observed data, with the goal of producing synthetic graphs with similar graph structure and node behavior. We find that using motifs and node roles helps our model generate the more complex structures and the temporal node behavior seen in real-world dynamic networks.</p> <p><br></p> <p>After observing that using motif node-roles helps to capture the changing local structure and behavior of nodes, we extend our work to also consider the attributes generated by nodes’ activities. We propose a second generative model for attributed dynamic networks that (i) captures network structure dynamics through temporal motifs, and (ii) extends the structural roles of nodes in motifs to roles that generate content embeddings. Our new proposed model is the first to generate synthetic dynamic networks and sample content embeddings based on motif node roles. To the best of our knowledge, it is the only attributed dynamic network model that can generate <em>new</em> content embeddings—not observed in the input graph, but still similar to that of the input graph. Our results show that modeling the network attributes with higher-order structures (e.g., motifs) improves the quality of the networks generated.</p> <p><br></p> <p>The generative models proposed address the difficulty of finding readily-available datasets of dynamic networks—attributed or not. This work will also allow others to: (i) generate networks that they can share without divulging individual’s private data, (ii) benchmark model performance, and (iii) explore model generalization on a broader range of conditions, among other uses. Finally, the evaluation measures proposed will elucidate models, allowing fellow researchers to push forward in these domains.</p>

Proteins are considered the primary actors in living organisms. Proteins mainly perform their functions by interacting with other proteins. Protein-protein interactions underpin various biological activities such as metabolic cycles, signal transduction, and immune response. PPI identification has been addressed by various experimental methods such as the yeast two-hybrid, mass spectrometry, and protein microarrays, to mention a few. However, due to the sheer number of proteins, experimental methods for finding interacting and non-interacting protein pairs are time-consuming and costly. Therefore a sequence-based framework called ProtInteract is developed to predict protein-protein interaction. ProtInteract comprises two components: first, a novel autoencoder architecture that encodes each protein's primary structure to a lower-dimensional vector while preserving its underlying sequential pattern by extracting uncorrelated attributes and more expressive descriptors. This leads to faster training of the second network, a deep convolutional neural network (CNN) that receives encoded proteins and predicts their interaction. Three different scenarios formulate the prediction task. In each scenario, the deep CNN predicts the class of a given encoded protein pair. Each class indicates different ranges of confidence scores corresponding to the probability of whether a predicted interaction occurs or not. The proposed framework features significantly low computational complexity and relatively fast response. The present study makes two significant contributions to the field of protein-protein interaction (PPI) prediction. Firstly, it addresses the computational challenges posed by the high dimensionality of protein datasets through the use of dimensionality reduction techniques, which extract highly informative sequence attributes. Secondly, the proposed framework, ProtInteract, utilises this information to identify the interaction characteristics of a protein based on its amino acid configuration. ProtInteract encodes the protein's primary structure into a lower-dimensional vector space, thereby reducing the computational complexity of PPI prediction. Our results provide evidence of the proposed framework's accuracy and efficiency in predicting protein-protein interactions.

Sound source separation is a popular and active research area, especially with modern machine learning techniques. In this thesis, the focus is on single-channel separation of two speakers into individual streams, and specifically considering the case where two speakers are also accompanied by background noise. There are different methods to separate speakers and in this thesis three different methods are evaluated: the Conv-TasNet, the DPTNet, and the FaSNetTAC.  The methods were used to train models to perform the sound source separation. These models were evaluated and validated through three experiments. Firstly, previous results for the chosen separation methods were reproduced. Secondly, appropriate models applicable for NFC's datasets and applications were created, to fulfill the aim of this thesis. Lastly, all models were evaluated on an independent dataset, similar to datasets from NFC. The results were evaluated using the metrics SI-SNRi and SDRi. This thesis provides recommended models and methods suitable for NFC applications, especially concluding that the Conv-TasNet and the DPTNet are reasonable choices.