The area of stem cell research is rapidly evolving. One of the recent achievements is the capture of naïve human embryonic stem cells through reprogramming of primed human embryonic stem cells. In this thesis, Gene Co-expression Networks are used to further our understanding of naïve and primed human embryonic (hESCs). We found that GCNs of naïve and primed hESCs exhibits distinct network topological structures. Rewiring analysis of naïve and primed hESC GCNs showed significant rewiring and change in networks structures and behaviors. This demonstrates that naïve and primed hESCs are distinct cellular states. In addition, KLF genes circuitry, NANOG, and SOX2 were more active in naïve GCNs and formed more edges with other genes. Those genes were significantly rewired in our GCNs. We found that KLF5 is major player in our naïve hESCs GCNs. In addition, NANOG and SOX2 interacted only in naïve hESCs GCNs..The observations in our GCNs concerning KLF circuitry activity and, NANOG and SOX2 interactions were consistent with published stem cell literature. This demonstrates the power of GCNs in unfolding cellular characteristics and understanding the underlying gene dynamics.

Technological advancements have opened up the possibility of digitizing the pathological landscape, enabling deep learning-based methods to analyze digitized tissue samples, i.e., whole slide images (WSIs). Attention has recently shifted toward modeling WSIs as graphs since graph representations can capture dynamic relationships. This thesis investigates different graph construction techniques in conjunction with graph-based deep learning to classify WSIs as breast cancer histological grade 1 versus histological grade 3. To that extent, multiple graph representation techniques and two graph convolutional networks, GCN and GraphSAGE, were utilized. Finally, by evaluating the proposed models on an external test set originating from a separate cohort, it is clear that both models have the capacity for binary histological grading, yielding AUC scores of 0.791 (95% CI 0.756 − 0.825) and 0.838 (95% CI 0.808 − 0.869) for the GCN and GraphSAGE models. Modeling WSIs as graphs is an exciting and emerging field; however, further work is needed to evaluate alternative graph representation techniques and graph convolutional networks. / Teknologiska framsteg har öppnat upp möjligheten att digitalisera det patologiska landskapet, och möjliggjort djupinlärningsbaserade metoder att analysera digitala vävnadsprover; whole slide images (WSIs). Uppmärksamhet har skiftats mot modellering av WSIs som grafer, då grafrepresentationer är dynamiska. Den här uppsatsen undersöker diverse tekniker för grafkonstruktion tillsammans med grafbaserad djupinlärning för att klassificera WSIs som histologisk gradering 1 kontra histologisk gradering 3. För detta ändamål användes flertalet olika grafrepresentationer samt två distinkta grafbaserade faltningsnätverk, GCN och GraphSAGE. Slutligen, genom att evaluera de föreslagna modellerna på ett externt test set, härstammande från en separat kohort, så är det tydligt att båda modellerna har kapacitet för binär histologisk gradering, med AUC-värden på 0.791 (95% CI 0.756 − 0.825) samt 0.838 (95% CI 0.808 − 0.869) för GCN och GraphSAGE. Att modellera WSIs som grafer är ett spännande och framväxande område. Det behövs emellertid mer forskning för att evaluera alternativa tekniker för grafrepresentationer samt grafbaserade faltningsnätverk.

Graphitische Karbonitride sind organische, kovalent gebundene, geschichtete und kristalline Halbleiter mit einer hohen thermischen und chemischen Stabilität. Diese Eigenschaften machen 2D Schichten der graphitischen Kristalle potentiell nützlich für das Ziel, Limitationen von organischen 0D Molekularen und 1D polymerischen Halbleitern zu überwinden. Trotz dieser interessanten Eigenschaften haben nur wenige Publikationen erfolgreich graphitische Karbonitride in optoelektronischen Bauteilen eingesetzt. Um die Vorteile dieser Materialien nutzbar zu machen, wurden bessere Synthesebedingungen gesucht. Die Verwendung von einem Iod-Eutektikum zeigt, dass Anionen mit einem größeren Radius als Bromid nicht für die Stabilisation von graphitischen Karbonitriden geeignet sind. Das Optimieren der Synthesebedingungen von Poly(triazin-imid)-LiBr resultiert in der Reduzierung von einem kohlenstoffreichen Zersetzungsprodukt bei vollständiger Kondensation. Das Untersuchen der elektronischen Struktur mit ab initio Berechnungen ergibt, dass der elektronische VB-CB-Übergang verboten ist. Dies resultiert daraus, dass die Zustände des obersten Valenzbandes nichtbindender Natur sind. Ein Band aus nichtbindenden Elektronen als oberstes Valenzband ist vor allem aus „lone-pair semiconductors“ aus der sechsten Hauptgruppe bekannt. In der Welt organischer Halbleiter wurde dieses Phänomen bisher nicht beobachtet. Die geringe makroskopische elektrische Leitfähigkeit der PTI-Filme wurde mit der Leitfähigkeit auf Nanoebene verglichen, woraus gefolgert werden kann, dass der Ladungsträgertransport durch den nanokristallinen Charakter an den Kristall-Kristall Übergängen gestört wird. Die elektronische Leitfähigkeit, Mobilität der Ladungsträger sowie die Ladungsträgerdichte wurden untersucht. Die Energie Niveaus legen nahe das Elektronentransport in der Präsenz von Sauerstoff möglich ist. Die erste Applikation eines kovalenten organischen Netzwerks in einer organischen lichtemittierenden Diode ist gezeigt worden. / Graphitic carbon nitrides are organic covalently-bonded, layered, and crystalline semiconductors with high thermal and oxidative stability. These properties make 2D layers of graphitic carbon nitrides potentially useful in overcoming the limitations of 0D molecular and 1D polymer semiconductors. Only few reports have shown them being employed in optoelectronic applications. With the goal to find better reaction conditions that enable higher product quality from the ionothermal synthesis the size effect of anions is studied by using an iodide eutectic instead of bromide or chloride eutectic. The highest crystalline condensation product obtained is melem, revealing that the large iodide anion is not capable of stabilizing a graphitic structure. Studying the synthesis conditions of poly(triazine imide) (PTI), the best characterized graphitic carbon nitride in literature, it is revealed that the brown discoloration of the product is due to a carbon rich side product. Reduction of reaction temperature and increase of reaction time allows omittance of carbonisation. Analyzing the electronic structure with ab initio calculations one finds that the lowest energy electronic transition in PTI is forbidden due to a non-bonding uppermost valence band. A uppermost non-bonding valence band is most reminiscent of lone-pair semiconductors and unknown in the world of organic semiconductors making PTI the first organic lone-pair semiconductor. The low electrical conductivity of PTI derivatives is compared to nanoscale conductivity values. The results indicate that macroscopic conductivity is hampered by the nano-crystalline character due to charge carrier trapping at crystal interfaces. The effective mobility is in the range of amorphous organic semiconductors with an unexpectedly high carrier density. The energy levels in PTI-LiBr potentially enable environmentally stable n-transport. The first successful Application of a covalent organic framework in a organic light emitting diode is presented.

This report is done in collaboration with WirelessCar for the master of science thesis at Halmstad University. Many different parameters influence fuel consumption. The objective of the report is to evaluate if Graph neural networks are a practical model to perform fuel consumption prediction on areas. The model uses a partitioning of geographical locations of trip observations to capture their spatial information. The project also proposes a method to capture the non-stationary behavior of vehicles by defining a vehicle node as a separate entity. The model then captures their different features in a dense layer neural network and utilizes message passing to capture context about neighboring nodes. The model is compared to a baseline neural network with a similar network architecture as the graph neural network. The data is partitioned to define an area with Kmeans and static gridnet partition with and without terrain details. This partition is used to structure a homogeneous graph that is underperforming. The practical drawbacks of the initial homogeneous graph are inspected and addressed to develop a heterogeneous graph that can outperform the neural network baseline.

Context. Aliasing artifacts are a present problem in both the game industryand the movie industry. With the GCN (Graphics Core Next) architectureused on both new generation of consoles; Xbox One and Playstation 4, aunified Anti-Aliasing solution can be constructed with high performance,temporal stable edges and satisfying visual fidelity. Objective. This thesis aims to implement several prototypes which willbe utilizing GCN architecture to solve aliasing artifacts such as temporalstability. Method. By doing performance measurements, a survey and an experimenton the constructed prototypes and current state of the art solutionsthis thesis will create both a benchmark between given state of the art solutionsfor the industry and at the same time evaluate the new solutions givenin this thesis. Result. With having potential of being the fastest Anti-Aliasing solutionin the field it does not only bring high performance, but also very temporalstable edges and satisfying visual quality. Conclusion. If not used as a standalone solution, the prototype can be decoupledfrom GCN specific features and be a very suitable complement forMulti Sample Anti-Aliasing which can not handle alpha clipped edges.

Machine learning plays a vital role in preventing financial losses within the banking industry, and still, a lot of state of the art and industry-standard approaches within the field neglect rejected customer information and the potential information that they hold to detect similar risk behavior.This thesis explores the possibility of including this information during training and utilizing transactional history through an LSTM to improve the detection of defaults.  The model is structured so an encoder is first trained with or without rejected customers. Virtual distances are then calculated in the embedding space between the accepted customers. These distances are used to create a graph where each node contains an LSTM network, and a GCN passes messages between connected nodes. The model is validated using two datasets, one public Taiwan dataset and one private Swedish one provided through the collaborative company. The Taiwan dataset used 8000 data points with a 50/50 split in labels. The Swedish dataset used 4644 with the same split.  Multiple metrics were used to validate the impact of the rejected customers and the impact of using time-series data instead of static features. For the encoder part, reconstruction error was used to measure the difference in performance. When creating the edges, the homogeny of the neighborhoods and if a node had a majority of the same labeled neighbors as itself were determining factors, and for the classifier, accuracy, f1-score, and confusion matrix were used to compare results. The results of the work show that the impact of rejected customers is minor when it comes to changes in predictive power. Regarding the effects of using time-series information instead of static features, we saw a comparative result to XGBoost on the Taiwan dataset and an improvement in the predictive power on the Swedish dataset. The results also show the importance of a well-defined virtual distance is critical to the classifier's performance.

In this masters thesis we focused on using machine learning methods for detecting money laundering in financial transaction networks, in order to demonstrate that it can be used as a complement or instead of the more commonly used rule based systems. The graph learning method graph convolutional networks (GCN) has been a hot topic in the field since they were shown to scale well with data size back in 2018. However the typical GCN models cannot use edge features, which is why this thesis combines the GCN model with a node and edge neural network (NENN) in order to solve this problem. This new method will be compared towards an already established machine learning method for financial transactions, namely the tree boosting method (XGBoost). Because of confidentiality concerns for financial transactions data, the machine learning algorithms will be tested on two carefully constructed synthetically generated data sets, which from agent based simulations resembles real financial data. The results showed the viability and superiority of the new implementation of the GCN model with it being a preferable method for connectivly structured data, meaning that a transaction or account is analyzed in the context of its financial environment. On the other hand the XGBoost method showed better results when examining transactions independently. Hence it was more accurately able to find fraudulent and non fraudulent patterns from the transactional features themselves. / I detta examensarbete fokuserar vi på användandet av maskininlärningsmetoder för att detektera penningtvätt i finansiella transaktionsnätverk, med målet att demonstrera att dess kan användas som ett komplement till eller i stället för de mer vanligt använda regelbaserade systemen. Grafinlärningsmetoden \textit{graph convolutional networks} (GCN) som har varit ett hett ämne inom området sedan metoden under 2018 visades fungera bra för stora datamängder. Däremot kan inte en vanlig GCN-modell använda kantinformation, vilket är varför denna avhandling kombinerar GCN-modellen med \textit{node and edge neural networks} (NENN) för att mer effektivt detektera penningtvätt. Denna nya metod kommer att jämföras med en redan etablerad maskininlärningsmetod för finansiella transaktioner, nämligen \textit{tree boosting} (XGBoost). På grund av sekretessanledningar för finansiella transaktionsdata var maskininlärningsalgoritmerna testade på två noggrant konstruerade syntetiskt genererade datamängder som från agentbaserade simuleringar liknar riktiga finansiella data. Resultaten visade på applikationsmöjligheter och överlägsenhet för den nya implementationen av GCN-modellen vilken är att föredra för relationsstrukturerade data, det vill säga när transaktioner och konton analyseras i kontexten av deras finansiella omgivning. Å andra sidan visar XGBoost bättre resultat på att examinera transaktioner individuellt eftersom denna metod mer precist kan identifiera bedrägliga och icke-bedrägliga mönster från de transnationella funktionerna.

With the arrival of 5G networks, telecommunication systems are becoming more intelligent, integrated, and broadly used. This thesis focuses on predicting the upcoming traffic to efficiently promote resource allocation, guarantee stability and reliability of the network. Since networks modeled as graphs potentially capture more information than tabular data, the construction of the graph and choice of the model are key to achieve a good prediction. In this thesis traffic prediction is based on a time-evolving graph, whose node and edges encode the structure and activity of the system. Edges are created by dynamic time-warping (DTW), geographical distance, and $k$-nearest neighbors. The node features contain different temporal information together with spatial information computed by methods from topological data analysis (TDA). To capture the temporal and spatial dependency of the graph several dynamic graph methods are compared. Throughout experiments, we could observe that the most successful model GConvGRU performs best for edges created by DTW and node features that include temporal information across multiple time steps. / Med ankomsten av 5G nätverk blir telekommunikationssystemen alltmer intelligenta, integrerade, och bredare använda. Denna uppsats fokuserar på att förutse den kommande nättrafiken, för att effektivt hantera resursallokering, garantera stabilitet och pålitlighet av nätverken. Eftersom nätverk som modelleras som grafer har potential att innehålla mer information än tabulär data, är skapandet av grafen och valet av metod viktigt för att uppnå en bra förutsägelse. I denna uppsats är trafikförutsägelsen baserad på grafer som ändras över tid, vars noder och länkar fångar strukturen och aktiviteten av systemet. Länkarna skapas genom dynamisk time warping (DTW), geografisk distans, och $k$-närmaste grannarna. Egenskaperna för noderna består av dynamisk och rumslig information som beräknats av metoder från topologisk dataanalys (TDA). För att inkludera såväl det dynamiska som det rumsliga beroendet av grafen, jämförs flera dynamiska grafmetoder. Genom experiment, kunde vi observera att den mest framgångsrika modellen GConvGRU presterade bäst för länkar skapade genom DTW och noder som innehåller dynamisk information över flera tidssteg.

Este trabalho propõe diretrizes de Gestão de Continuidade de Negócios (GCN) para a tecnologia de Ensino Presencial Mediado por Recursos Tecnológicos (EPMRT), que conta, para a realização de suas atividades acadêmicas, com um sistema complexo para transmissão de aulas e exige um grande esforço para o controle das suas operações e das respostas coordenadas diante de erros, falhas e defeitos, ou quaisquer incidentes que resultem na interrupção das suas atividades. A manutenção deste ambiente tecnológico está relacionada com a implantação de processos eficientes de gestão de risco e do ciclo de melhoria contínua em ambiente de TI com a adoção do ITIL® e através da construção das diretrizes de um Plano de Continuidade de Negócios (PCN), documentado por meio de elementos da UML, utilizando a Análise de Impacto nos Negócios (BIA), a Avaliação dos Riscos (RA) e os atributos de Dependabilidade para os elementos tecnológicos: disponibilidade, confiabilidade, segurança, confidencialidade, integridade e manutenibilidade. / This paper proposes guidelines for Business Continuity Management (BCM) that uses a technology called Education System Mediated Classroom Resources Technology (SPMRT), which needs, for the achievement of their academic activities, a complex system for transmission of lessons and requires a great effort to control their operations and coordinated fast responses in case of errors, faults, attacks and defects, or any incidents that result in the disruption of their activities. Maintaining this technological environment is related to the implementation of efficient processes of risk management and continuous improvement cycle in the IT environment with the adoption of ITIL® and through the construction of a Business Continuity Plan (BCP), documented by elements of the UML using the Business Impact Analysis (BIA), Risk Assessment (RA) and the attributes of Dependability: availability, reliability, security, confidentiality, integrity and maintainability.

Este trabalho propõe diretrizes de Gestão de Continuidade de Negócios (GCN) para a tecnologia de Ensino Presencial Mediado por Recursos Tecnológicos (EPMRT), que conta, para a realização de suas atividades acadêmicas, com um sistema complexo para transmissão de aulas e exige um grande esforço para o controle das suas operações e das respostas coordenadas diante de erros, falhas e defeitos, ou quaisquer incidentes que resultem na interrupção das suas atividades. A manutenção deste ambiente tecnológico está relacionada com a implantação de processos eficientes de gestão de risco e do ciclo de melhoria contínua em ambiente de TI com a adoção do ITIL® e através da construção das diretrizes de um Plano de Continuidade de Negócios (PCN), documentado por meio de elementos da UML, utilizando a Análise de Impacto nos Negócios (BIA), a Avaliação dos Riscos (RA) e os atributos de Dependabilidade para os elementos tecnológicos: disponibilidade, confiabilidade, segurança, confidencialidade, integridade e manutenibilidade. / This paper proposes guidelines for Business Continuity Management (BCM) that uses a technology called Education System Mediated Classroom Resources Technology (SPMRT), which needs, for the achievement of their academic activities, a complex system for transmission of lessons and requires a great effort to control their operations and coordinated fast responses in case of errors, faults, attacks and defects, or any incidents that result in the disruption of their activities. Maintaining this technological environment is related to the implementation of efficient processes of risk management and continuous improvement cycle in the IT environment with the adoption of ITIL® and through the construction of a Business Continuity Plan (BCP), documented by elements of the UML using the Business Impact Analysis (BIA), Risk Assessment (RA) and the attributes of Dependability: availability, reliability, security, confidentiality, integrity and maintainability.