<p>The detection of anomalies in real-world networks is applicable in different domains; the application includes, but is not limited to, credit card fraud detection, malware identification and classification, cancer detection from diagnostic reports, abnormal traffic detection, identification of fake media posts, and the like. Many ongoing and current researches are providing tools for analyzing labeled and unlabeled data; however, the challenges of finding anomalies and patterns in large-scale datasets still exist because of rapid changes in the threat landscape. </p><p>In this study, I implemented a novel and robust solution that combines data science and cybersecurity to solve complex network security problems. I used Long Short-Term Memory (LSTM) model, Louvain algorithm, and PageRank algorithm to identify and group anomalies in large-scale real-world networks. The network has billions of packets. The developed model used different visualization techniques to provide further insight into how the anomalies in the network are related. </p><p>Mean absolute error (MAE) and root mean square error (RMSE) was used to validate the anomaly detection models, the results obtained for both are 5.1813e-04 and 1e-03 respectively. The low loss from the training phase confirmed the low RMSE at loss: 5.1812e-04, mean absolute error: 5.1813e-04, validation loss: 3.9858e-04, validation mean absolute error: 3.9858e-04. The result from the community detection shows an overall modularity value of 0.914 which is proof of the existence of very strong communities among the anomalies. The largest sub-community of the anomalies connects 10.42% of the total nodes of the anomalies. </p><p>The broader aim and impact of this study was to provide sophisticated, AI-assisted countermeasures to cyber-threats in large-scale networks. To close the existing gaps created by the shortage of skilled and experienced cybersecurity specialists and analysts in the cybersecurity field, solutions based on out-of-the-box thinking are inevitable; this research was aimed at yielding one of such solutions. It was built to detect specific and collaborating threat actors in large networks and to help speed up how the activities of anomalies in any given large-scale network can be curtailed in time.</p><div><div><div> </div> </div> </div> <br>

Beschlossen 2015 im Gesetzesentwurf zur Digitalisierung der Energiewende (s. BMWi (2015a)) sollen verstärkt Smart Meter ausgerollt werden. Diese digitalen Stromzähler bestehen aus einem digitalen Zählwerk sowie einer Kommunikationseinheit, welche eine sichere und standardisierte Kommunikation ermöglichen soll. Die Smart Meter erfassen und veranschaulichen den aktuellen Verbrauch und können zusätzlich sogar simultan die momentane Erzeugung von Energie, z. B. durch eine Solaranlage, erfassen. Durch die ständige Erfassung des aktuellen Energieverbrauchs, verbunden mit der Übermittlungsfunktion an den EVU, kann dem Kunden unmittelbar sein aktueller Verbrauch aufgezeigt werden – eine wesentliche Grundlage für Transparenz im Verbrauch, Datenauswertungen und Startpunkt für Verbrauchsoptimierungen (vgl. BMWi (2015b); Fox (2010), S. 408). [... aus Punkt 1.2]

El Seguro Social de Salud, EsSalud, es un organismo público descentralizado que tiene como finalidad dar cobertura a los asegurados y sus derechohabientes, a través de otorgamiento de diferentes tipos de seguro a la población ante los riesgos humanos [1]. Esta institución brinda atención a un aproximado de 11 millones 493 mil peruanos asegurados, quienes representan un 35,7% de la población total [2], estos asegurados se encuentran concentrados en mayor proporción en edades de 0 a 14 años, de 25 a 44 años y 65 a más [3]. Según la memoria anual realizada en el 2019 por esta institución, muestra que se tiene un total de 28149 reclamos registrados en el sistema de información de Atención al Asegurado, que representa un 18,8 % del total de solicitudes de dicho sistema con un tiempo de conclusión de 25 días [4]. Asimismo, según el diario El Comercio, afirman que uno de los principales motivos de los reclamos se debe a la falta de acceso a los servicios de salud debido al tiempo de espera de atención para los asegurados [5]. EsSalud busca proponer estrategias para reducir estos reclamos y tiempos de espera, pero dichas investigaciones implican un mayor esfuerzo laboral y uso de recursos humanos. Los resultados de las pruebas no muestran ser muy efectivos dado que podría seguir presentando la disconformidad de los asegurados porque el tiempo de atención sigue siendo alto [6]. En este sentido, el presente trabajo consiste en proponer un método que permita contribuir a la mejora y optimización de la toma de decisiones por parte del equipo médico del Bloque de Cirugía sobre su proceso. Nuestro trabajo propone un método que permita formular y evaluar indicadores de Process Mining a través de preguntas relacionadas al funcionamiento de un proceso y permita comprender de manera sencilla las variables del proceso a través de técnicas de Data Visualization. El aporte se encuentra en la definición de variables dentro de las técnicas de Data Visualization. Este tiene el objetivo de permitir comprender en profundidad qué es lo que se va a representar gráficamente y, a la vez, sea de interés a los responsables del proceso de Bloque de Cirugía a nivel de negocio. Nuestra propuesta identifica cuellos de botella y violaciones de políticas de un proceso crítico en una organización de salud, ya que resulta complicado realizar mediciones y análisis para mejorar la calidad y transformación de los procesos en instituciones de atención en el sector salud. Para llevar a cabo el proyecto se tomará como referencia la información de la empresa AUNA. El método se ejecutó a través de escenarios operativos en el proceso quirúrgico de esta red de clínicas para responder preguntas típicas y frecuentes del proceso de Bloque de Cirugía. Se revisaron 1710 casos con un total de 15390 encuentros quirúrgicos. Asimismo, la aplicación del método permitió validar y mejorar el modelo de proceso documentado respecto a los registros de eventos de los sistemas de información del centro de salud. Se identificaron oportunidades de mejora para facilitar los registros de marcado y maximizar la calidad de los resultados para futuros proyectos de Minería de Procesos y Visualización de Datos. Finalmente, la aplicación del método permitió identificar cuellos de botella, variantes, violaciones y varianzas del proceso mediante el uso de indicadores de Minería de Procesos y de variables en Visualización de Datos para comprender el rendimiento actual del Bloque de Cirugía y, posteriormente, tomar decisiones y acciones de mejora en dicho proceso por parte del equipo médico. / The Social Health Insurance, EsSalud, is a decentralized public body whose purpose is to provide coverage to the insured and their beneficiaries, through the granting of different types of insurance to the population against human risks [1]. This institution provides care to an approximate 11 million 493 thousand insured Peruvians, who represent 35.7% of the total population [2], these insured persons are concentrated in a greater proportion in ages 0 to 14 years, from 25 to 44 years and 65 and over [3]. According to the annual report carried out in 2019 by this institution, it shows that there is a total of 28,149 claims registered in the Insured Service information system, which represents 18.8% of the total requests of said system with a time of 25-day conclusion [4]. Likewise, according to the newspaper El Comercio, they affirm that one of the main reasons for the complaints is due to the lack of access to health services due to the waiting time for the insured [5]. EsSalud seeks to propose strategies to reduce these claims and waiting times, but these investigations imply a greater work effort and use of human resources. The results of the tests do not show to be very effective since it could continue to present the dissatisfaction of the insured because the time of attention is still high [6]. In this sense, the present work consists in proposing a method that allows to contribute to the improvement and optimization of decision-making by the medical team of the Surgery Block regarding its process. / Tesis

Throughout the world, there is a great demand to map out the increasing environmental changes and life habitats on Earth. The vast majority of Earth Observations today, are collected using satellites. The Global Watch Center (GWC) initiative was started with the purpose of producing a global situational awareness of the premises for all life on Earth. By collecting, studying and analyzing vast amounts of data in an automatic, scalable and transparent way, the GWC aims are to work towards reaching the United Nations (UN) Sustainable Development Goals (SDG). The GWC vision is to make use of qualified accessible data together with leading organizations in order to lay the foundation of the important decisions that have the biggest potential to make an actual difference for the common awaited future. As a show-case for the initiative, the UN strategic department has recommended a specific use-case, involving mapping large accumulation of waste in areas greatly affected, which they believe will profit the initiative very much. This Master Thesis aim is, in an automatic and scalable way, to detect and classify dumpsites in Kampala, the capital of Uganda, by using available satellite imagery. The hopes are that showing technical feasibility and presenting interesting remarks will aid in spurring further interest in coming closer to a realization of the initiative. The technical approach is to use a lightweight version of Automatic Target Recognition. This is conventionally used in military applications but is here used, to detect and classify features of large accumulations of solid-waste by using techniques from the field of Image Analysis and Data Mining. Choice of data source, this study's area of interest as well as choice of methodology for Feature Extraction and choice of the Machine Learning algorithm Support Vector Machine will all be described and implemented. With a classification precision of 95 percent will technical results be presented, with the ambition to promote further work and contribute to the GWC initiative with valuable information for later realization.

Datavisualisering är en vanlig metod för att öka förståelsen av data genom att omvandla den från text till bild. Genom datavisualisering kan en gigantisk mängd data omvandlas till diagram och bilder som bidrar till att ge en användare en tydlig förståelse över vad denna data representerar. Det medlemsägda företaget Biometria verkar inom skogsnäring och har som uppgift att mäta skogsprodukter, så som trädstammar och stockar. Mätdatat lagras i skördspecifika XML-filer och görs tillgängligt för de som är involverade i skörden. Problemet är att dessa filer tenderar att bli extremt stora och svårtydda för någon som söker en överblick av en specifik skörd. Detta projekt har gått ut på att undersöka huruvida Biometrias data kan visualiseras och på så sätt förtydligas. Undersökningen resulterade i utvecklingen av en prototyp av en webbapplikation som tar emot en skördefil och visualiserar vissa mätdata från den. Den slutgiltiga prototypen bestod av en punktkarta som visar var stammarna fälldes, två cirkeldiagram som visar proportioner av trädarter samt sortiment av stockar, och ett stapeldiagram som visar max, minimi och medelvärden av stammarna och stockarnas diametrar. Resultatet var lyckat, eftersom de anställda på Biometria som resultatet presenterades för var överens om att visualiseringen bidrog till en mycket högre förståelse av den data som visualiserades. / Data visualization is a common method to increase the understanding of data by converting it from text to image. Through data visualization, a large amount of data can be transformed into diagrams and images that helps giving a user a clear understanding of what the data represents. The member-owned company Biometria operates in the forest industry and is tasked with measuring forest products, such as tree trunks and logs. The measurement data is stored in harvest-specific XML-files and are made available for those involved in the harvest. The problem is that these files tend to get extremely large and difficult to read for someone who wants an overview of a specific harvest. This project has aimed to investigate whether Biometria's data can be visualized and thus clarified. The study resulted in the development of a prototype of a web application that receives a harvest file and visualizes some measurement data from it. The final prototype consisted of a dot map showing where the trees were felled, two pie charts showing proportions of tree species and assortment of logs, and a bar chart showing the maximum, minimum and mean values of the trees and log diameters. The result was successful, since the employees at Biometria for whom the result was presented all agreed that the visualization contributed to a much higher understanding of the data that was visualized.

A Bicycle-sharing system (BSS) is a popular service scheme deployed in cities of different sizes around the world. Although docked bike systems are its most popular model used, it still experiences a number of weaknesses that could be optimized by investigating bike sharing network properties and evolution of obtained patterns.Efficiently keeping bicycle-sharing system as balanced as possible is the main problem and thus, predicting or minimizing the manual transportation of bikes across the city is the prime objective in order to save logistic costs for operating companies.The purpose of this thesis is two-fold; Firstly, it is to visualize bike flow using data exploration methods and statistical analysis to better understand mobility characteristics with respect to distance, duration, time of the day, spatial distribution, weather circumstances, and other attributes. Secondly, by obtaining flow visualizations, it is possible to focus on specific directed sub-graphs containing only those pairs of stations whose mutual flow difference is the most asymmetric. By doing so, we are able to use graph mining and machine learning techniques on these unbalanced stations.Identification of spatial structures and their structural change can be captured using Convolutional neural network (CNN) that takes adjacency matrix snapshots of unbalanced sub-graphs. A generated structure from the previous method is then used in the Long short-term memory artificial recurrent neural network (RNN LSTM) in order to find and predict its dynamic patterns.As a result, we are predicting bike flows for each node in the possible future sub-graph configuration, which in turn informs bicycle-sharing system owners in advance to plan accordingly. This combination of methods notifies them which prospective areas they should focus on more and how many bike relocation phases are to be expected. Methods are evaluated using Cross validation (CV), Root mean square error (RMSE) and Mean average error (MAE) metrics. Benefits are identified both for urban city planning and for bike sharing companies by saving time and minimizing their cost. / Lånecykel avser ett system för uthyrning eller utlåning av cyklar. Systemet används främst i större städer och bekostas huvudsakligen genom tecknande av ett abonnemang.Effektivt hålla cykel andelssystem som balanseras som möjligt huvud problemand därmed förutsäga eller minimera manuell transport av cyklar över staden isthe främsta mål för att spara logistikkostnaderna för drift companies.Syftet med denna avhandling är tvåfaldigt.För det första är det att visualisera cykelflödet med hjälp av datautforskningsmetoder och statistisk analys för att bättre förstå rörlighetskarakteristika med avseende på avstånd, varaktighet, tid på dagen, rumsfördelning, väderförhållanden och andra attribut.För det andra är det vid möjliga flödesvisualiseringar möjligt att fokusera på specifika riktade grafer som endast innehåller de par eller stationer vars ömsesidiga flödesskillnad är den mest asymmetriska.Genom att göra det kan vi anvnda grafmining och maskininlärningsteknik på dessa obalanserade stationer, och använda konjunktionsnurala nätverk (CNN) som tar adjacency matrix snapshots eller obalanserade subgrafer.En genererad struktur från den tidigare metoden används i det långa kortvariga minnet artificiella återkommande neurala nätverket (RNN LSTM) för att hitta och förutsäga dess dynamiska mönster.Som ett resultat förutsäger vi cykelflden för varje nod i den eventuella framtida underkonfigurationen, vilket i sin tur informerar cykeldelningsägare om att planera i enlighet med detta.Denna kombination av metoder meddelar dem vilka framtida områden som bör inriktas på mer och hur många cykelflyttningsfaser som kan förväntas.Metoder utvärderas med hjälp av cross validation (CV), Root mean square error (RMSE) och Mean average error (MAE) metrics.Fördelar identifieras både för stadsplanering och för cykeldelningsföretag genom att spara tid och minimera kostnaderna.

This thesis will provide knowledge on how to maintain a well developed flow of material while at the same time finding an optimal level of capacities for buffers. Simultaneously, aspects that allow for positive sustainability practices will be regarded.  Buffers have a considerable impact on the performance of a production system. However, the process of optimizing buffers remains a complex task, and is therefore in need of further research. Through a thorough data collection process, simulation modeling and Multi-objective Optimization, the authors will present evidence-based recommendations for managing buffers in an optimal manner. The case company currently has two buffer zones that are to be investigated if they could be improved by finding an optimal capacity level. The current flow of material consists of certain variations in the components that will be taken into consideration, some variations need further investigation in order to be representative and applicable to this study. By applying amongst other things, Lean concepts, Gemba walks, simulation modeling, interviews and knowledge within the specific field of buffer optimization, the authors were able to provide evidence-based recommendations. These recommendations both take into account optimal buffer capacities as well as brief sustainability and economical aspects. The authors have found that one buffer zone has the potential of being removed, which will contribute to positive environmental aspects. However, if this solution is to be applied, the need of planning and managing the distribution of components is required.  Another buffer zone has been investigated by applying the concept of Multi-objective Optimization, where the objectives are to maintain high throughput while minimizing the buffer capacities. The optimization procedure generated a decrease in buffer capacities in the zone by a total of 35%. This newly acquired space can either be used for other manufacturing processes, or be discontinued, which would decrease the energy consumption and positively affect the sustainability aspect.

[pt] A avaliação sistemática de uma Instituição de Ensino Superior (IES) fornece à sua administração um feedback valioso sobre vários aspectos da vida acadêmica, como a reputação da instituição e o desempenho individual do corpo docente. Em particular, as pesquisas com alunos são uma fonte de informação de primeira mão que ajuda a avaliar o desempenho do professor e a adequação do curso. Os objetivos principais desta tese são criar e avaliar modelos de análise de sentimento dos comentários dos alunos e estratégias para resumir os comentários dos alunos. A tese primeiro descreve duas abordagens para classificar a polaridade dos comentários dos alunos, ou seja, se eles são positivos, negativos ou neutros. A primeira abordagem depende de um dicionário criado manualmente que lista os termos que representam o sentimento a ser detectado nos comentários dos alunos. A segunda abordagem adota um modelo de representação de linguagem, que não depende de um dicionário criado manualmente, mas requer algum conjunto de teste anotado manualmente. Os resultados indicaram que a primeira abordagem superou uma ferramenta de linha de base e que a segunda abordagem obteve um desempenho muito bom, mesmo quando o conjunto de comentários anotados manualmente é pequeno. A tese então explora várias estratégias para resumir um conjunto de comentários com interpretações semelhantes. O desafio está em resumir um conjunto de pequenas frases, escritas por pessoas diferentes, que podem transmitir ideias repetidas. Como estratégias, a tese testou Market Basket Analysis, Topic Models, Text Similarity, TextRank e Entailment, adotando um método de inspeção humana para avaliar os resultados obtidos, uma vez que as métricas tradicionais de sumarização de textos se mostraram inadequadas. Os resultados sugerem que o agrupamento combinado com a estratégia baseada em centróide atinge os melhores resultados. / [en] The systematic evaluation of a Higher Education Institution (HEI) provides its administration with valuable feedback about several aspects of academic life, such as the reputation of the institution and the individual performance of teachers. In particular, student surveys are a first-hand source of information that help assess teacher performance and course adequacy. The primary goals of this thesis are to create and evaluate sentiment analysis models of students comments, and strategies to summarize students comments. The thesis first describes two approaches to classify the polarity of students comments, that is, whether they are positive, negative, or neutral. The first approach depends on a manually created dictionary that lists terms that represent the sentiment to be detected in the students comments. The second approach adopts a language representation model, which does not depend on a manually created dictionary, but requires some manually annotated test set. The results indicated that the first approach outperformed a baseline tool, and that the second approach achieved very good performance, even when the set of manually annotated comments is small. The thesis then explores several strategies to summarize a set of comments with similar interpretations. The challenge lies in summarizing a set of small sentences, written by different people, which may convey repeated ideas. As strategies, the thesis tested Market Basket Analysis, Topic Models, Text Similarity, TextRank, and Entailment, adopting a human inspection method to evaluate the results obtained, since traditional text summarization metrics proved inadequate. The results suggest that clustering combined with the centroid-based strategy achieves the best results.

This thesis aims to develop and evaluate a dashboard design that visualizes a stream of data from the different entities involved in autonomous warehouses, a subset of cyber-physical systems. I created this dashboard through User-Centered Design (UCD) methodologies based on two feedback iterations with the stakeholders employing semi-structured expert opinion interviews. This thesis also discusses the different stages involved in building this dashboard design, the design decisions, the technical aspects of the libraries used, and the feedback session towards the end of the project. It also presents the implemented dashboard as a proof of development efforts and explains its different functionalities. The project concludes with evaluating the dashboard through a semi-structured interview with the respective stakeholders and suggests features for further development. / Denna studie ämnar att utveckla och utvärdera en design för ett dashboard som visualiserar dataströmmar från olika enheter som kan hittas i autonoma lager. Detta dashboard har utvecklats genom att använda metoder inom användarcentrerad design, som baserades på två iterationer med intressenter som är experter inom området, där semistrukturerade intervjuer gjordes. Denna studie diskuterar också de olika steg som är involverade i att bygga designen av detta dashboard, de olika beslut som togs i designprocessen, de tekniska aspekterna av de bibliotek som används och resultatet från de sessioner som hölls för att få feedback i slutet av projektet. Studien presenterar också det dashboard som utvecklades samt förklarar dess funktionalitet. Slutsatser dras från de semistrukturerade intervjuerna med respektive intressent och föreslår framtida funktioner som skulle vara möjliga att implementera.

The Swedish Government has set a goal to reach net zero emissions of greenhouse gases by 2045, which together with the commissioning to the Swedish Housing Agency to prepare requirements for a climate declaration that shall reduce the climate impact from buildings, has enforce the AEC industry to provide solutions that help reach these targets. The introduction of the integration of BIM technologies, together with the LCA methodology has been suggested as a key solution to solve this problem. To achieve the results for this study, two main objectives were stablished. The first objective was to develop a BIM model in SMC able to produce automated climate calculations. The second objective was to perform interviews with relevant actors about this tool. The integration of those objectives helped to answer the research questions of this study. This study provides a way of performing automated climate calculations for construction projects using classification of materials in SMC and calculations in Excel. It also has the ability to perform data visualization of the carbon footprints of the complements in the 3D models of the project using the GWP of the chosen materials. It can be said that it is a great tool to introduce to decision-makers an easy way to identify the hotspots of carbon emissions and choose more sustainable alternatives. / Den Svenska Regeringen har fastställt ett mål att nå utsläppen av växthusgaser netto noll till 2045, som tillsammans med uppdraget till Boverket att förbereda krav på en klimatdeklaration som ska minska klimatpåverkan från byggnader har tvingat AEC-industrin att tillhandahålla lösningar som hjälper till att nå dessa mål. Införandet av integrationen av BIM-teknologier tillsammans med LCA-metoden har föreslagits som en nyckellösning för att lösa detta problem. För att uppnå resultaten för denna studie fastställdes två huvudmål. Det första målet var att utveckla en BIM-modell i SMC som kunde producera automatiserade klimatberäkningar. Det andra målet var att genomföra intervjuer med relevanta aktörer om detta verktyg. Integrationen av dessa mål hjälpte till att besvara forskningsfrågorna i denna studie. Denna studie ger ett sätt att utföra automatiserade klimatberäkningar för byggprojekt med klassificering av material i SMC och beräkningar i Excel. Det har också förmågan att utföra datavisualisering av kolavtryck av komplementen i projektets 3D-modeller med GWP för de valda materialen. Det kan sägas att det är ett bra verktyg att introducera för beslutsfattare ett enkelt sätt att identifiera de hotspots som koldioxidutsläpp och välja mer hållbara alternativ.