Large collections of historical document images have been collected by companies and government institutions for decades. More recently, these collections have been made available to a larger public via the Internet. However, to make accessing them truly useful, the contained images need to be made readable and searchable. One step in that direction is document image binarization, the separation of text foreground from page background. This separation makes the text shown in the document images easier to process by humans and other image processing algorithms alike. While reasonably well working binarization algorithms exist, it is not sufficient to just being able to perform the separation of foreground and background well. This separation also has to be achieved in an efficient manner, in terms of execution time, but also in terms of training data used by machine learning based methods. This is necessary to make binarization not only theoretically possible, but also practically viable. In this thesis, we explore different ways to achieve efficient binarization in terms of execution time by improving the implementation and the algorithm of a state-of-the-art binarization method. We find that parameter prediction, as well as mapping the algorithm onto the graphics processing unit (GPU) help to improve its execution performance. Furthermore, we propose a binarization algorithm based on recurrent neural networks and evaluate the choice of its design parameters with respect to their impact on execution time and binarization quality. Here, we identify a trade-off between binarization quality and execution performance based on the algorithm’s footprint size and show that dynamically weighted training loss tends to improve the binarization quality. Lastly, we address the problem of training data efficiency by evaluating the use of interactive machine learning for reducing the required amount of training data for our recurrent neural network based method. We show that user feedback can help to achieve better binarization quality with less training data and that visualized uncertainty helps to guide users to give more relevant feedback. / Scalable resource-efficient systems for big data analytics

O contexto tecnológico percebido em vários setores da sociedade brasileira impulsiona a sua utilização em sala de aula que, por sua vez, não deve estar desconectada dessa realidade. Neste cenário, os materiais digitais no formato de multimídia interativa são reconhecidos como uma possibilidade educativa. Importantes avaliações reconhecem as dificuldades nas habilidades de leitura e escrita de alunos do Ensino Fundamental, como a Prova Brasil e o Indicador de Analfabetismo Funcional (INAF). O referencial teórico desta tese está ancorado na Teoria Cognitiva de Aprendizagem Multimídia, do inglês Cognitive Theory Multimedia Learning (CTML), principalmente nos princípios de interatividade e multimídia propostos por Richard Mayer, publicados em 2001 e 2011 e que constituem relevante orientação para projetos de Objetos de Aprendizagem Multimídia Interativos (OAMI) eficazes. Além disso, esta tese adota as taxonomias de Schwier e Misanchuk de 1993 e de Sims de 1997 e 2000, sobre interatividade em educação. Trata-se de uma pesquisa qualitativa e quantitativa, cujo objetivo é comprovar se e como os diferentes modelos de Objetos de Aprendizagem Multimídia Interativos possibilitam o aprimoramento da capacidade de leitura e escrita dos alunos nos anos iniciais do Ensino Fundamental. Os experimentos foram realizados com alunos do quinto ano do Ensino Fundamental de uma escola pública da periferia de Santa Maria - RS, durante as aulas em sala de Informática entre 2011 e 2013. Para testar as hipóteses deste estudo, foram realizadas diferentes etapas que incluem: estudo exploratório, estudo piloto, segundo estudo e o questionário sobre os objetos de aprendizagem multimídia, o qual foi aplicado em 2011 e 2013. Os dados levantados no estudo piloto de 2011 serviram como base para a proposição do segundo estudo em 2013 que definiu diferentes condições experimentais, com os tipos e níveis de interatividade, as mídias a serem utilizadas e as habilidades referentes ao conteúdo abordado nas multimídias. Inicialmente testou-se a normalidade dos dados, empregando-se o teste de Kolmogorov-Smirnov e constatou-se que os dados não seguiam uma distribuição normal (p < 0,05). A partir desse resultado, optou-se pela realização de testes não paramétricos para a comparação entre os valores dos acertos e dos erros, das Multimídias do Grupo Teste e do Grupo Controle. As respostas dos questionários (2011 e 2013) foram analisadas (Teste Qui-quadrado). As análises estatísticas conjuntas indicam algumas versões de multimídia com resultados significativos e, através dos questionários, foi possível detectar algumas variáveis que provavelmente influenciaram positivamente no desempenho dos alunos, chegando-se à conclusão de que os modelos de Objetos de Aprendizagem Multimídia Interativos utilizados nos experimentos e a sequência / The technological context perceived in various sectors of Brazilian society drives its use in the classroom, which in turn should not be disconnected from this reality. In this scenario, the digital materials in an interactive multimedia format are recognized as an educational opportunity. Important assessments as Prova Brasil (Brazil Test) and the Functional Illiteracy Indicator (INAF - Indicador de Analfabetismo Funcional), acknowledge the reading and writing skills difficulties of elementary school students. The theoretical framework of this thesis is anchored in the Cognitive Theory of Multimedia Learning (CTML), mainly on the interactivity and multimedia principles proposed by Richard Mayer, published in 2001 and 2011 and which are relevant guidance to effective projects of Interactive Multimedia Learning Objects. Moreover, this thesis adopts the interactivity education taxonomies proposed by Schwier and Misanchuk 1993 and Sims 1997 and 2000. This is a qualitative and quantitative research, whose goal is to prove whether and how the different models of Interactive Multimedia Learning Objects enable the improvement of reading and writing ability of students in the early years of elementary school. The experiments were conducted with students of the fifth grade of elementary school in a public school at the outskirts of Santa Maria – RS, during classes in Computer room between 2011 and 2013. In order to test the hypotheses of this study, different steps were performed including the following: exploratory study, pilot study, a second study and the multimedia learning objects questionnaire, which was applied in 2011 and 2013. The data collected during the 2011 pilot study, were the basis for the proposition of the second study performed in 2013 which defined the different experimental conditions with the types and levels of interactivity, media to be used and the skills related to the content addressed in multimedia. Initially, data normality was tested using the Kolmogorov - Smirnov test and it was confirmed data did not follow a normal distribution (p<0.05). From this result, it was decided to perform non-parametric tests to compare the values of the successes and the mistakes between the Multimedia Test Group and Control Group. The surveys (2011 and 2013) answers were analyzed (chi–square test). Join statistical analyses indicate some versions of multimedia with significant results and through the questionnaires; it was possible to detect some variables that probably influenced positively on students’ performance. This supports the conclusion that the models of Interactive Multimedia Learning Objects and the didactic sequence used in the experiments enabled the researched people to improve their ability to read and write.

O contexto tecnológico percebido em vários setores da sociedade brasileira impulsiona a sua utilização em sala de aula que, por sua vez, não deve estar desconectada dessa realidade. Neste cenário, os materiais digitais no formato de multimídia interativa são reconhecidos como uma possibilidade educativa. Importantes avaliações reconhecem as dificuldades nas habilidades de leitura e escrita de alunos do Ensino Fundamental, como a Prova Brasil e o Indicador de Analfabetismo Funcional (INAF). O referencial teórico desta tese está ancorado na Teoria Cognitiva de Aprendizagem Multimídia, do inglês Cognitive Theory Multimedia Learning (CTML), principalmente nos princípios de interatividade e multimídia propostos por Richard Mayer, publicados em 2001 e 2011 e que constituem relevante orientação para projetos de Objetos de Aprendizagem Multimídia Interativos (OAMI) eficazes. Além disso, esta tese adota as taxonomias de Schwier e Misanchuk de 1993 e de Sims de 1997 e 2000, sobre interatividade em educação. Trata-se de uma pesquisa qualitativa e quantitativa, cujo objetivo é comprovar se e como os diferentes modelos de Objetos de Aprendizagem Multimídia Interativos possibilitam o aprimoramento da capacidade de leitura e escrita dos alunos nos anos iniciais do Ensino Fundamental. Os experimentos foram realizados com alunos do quinto ano do Ensino Fundamental de uma escola pública da periferia de Santa Maria - RS, durante as aulas em sala de Informática entre 2011 e 2013. Para testar as hipóteses deste estudo, foram realizadas diferentes etapas que incluem: estudo exploratório, estudo piloto, segundo estudo e o questionário sobre os objetos de aprendizagem multimídia, o qual foi aplicado em 2011 e 2013. Os dados levantados no estudo piloto de 2011 serviram como base para a proposição do segundo estudo em 2013 que definiu diferentes condições experimentais, com os tipos e níveis de interatividade, as mídias a serem utilizadas e as habilidades referentes ao conteúdo abordado nas multimídias. Inicialmente testou-se a normalidade dos dados, empregando-se o teste de Kolmogorov-Smirnov e constatou-se que os dados não seguiam uma distribuição normal (p < 0,05). A partir desse resultado, optou-se pela realização de testes não paramétricos para a comparação entre os valores dos acertos e dos erros, das Multimídias do Grupo Teste e do Grupo Controle. As respostas dos questionários (2011 e 2013) foram analisadas (Teste Qui-quadrado). As análises estatísticas conjuntas indicam algumas versões de multimídia com resultados significativos e, através dos questionários, foi possível detectar algumas variáveis que provavelmente influenciaram positivamente no desempenho dos alunos, chegando-se à conclusão de que os modelos de Objetos de Aprendizagem Multimídia Interativos utilizados nos experimentos e a sequência / The technological context perceived in various sectors of Brazilian society drives its use in the classroom, which in turn should not be disconnected from this reality. In this scenario, the digital materials in an interactive multimedia format are recognized as an educational opportunity. Important assessments as Prova Brasil (Brazil Test) and the Functional Illiteracy Indicator (INAF - Indicador de Analfabetismo Funcional), acknowledge the reading and writing skills difficulties of elementary school students. The theoretical framework of this thesis is anchored in the Cognitive Theory of Multimedia Learning (CTML), mainly on the interactivity and multimedia principles proposed by Richard Mayer, published in 2001 and 2011 and which are relevant guidance to effective projects of Interactive Multimedia Learning Objects. Moreover, this thesis adopts the interactivity education taxonomies proposed by Schwier and Misanchuk 1993 and Sims 1997 and 2000. This is a qualitative and quantitative research, whose goal is to prove whether and how the different models of Interactive Multimedia Learning Objects enable the improvement of reading and writing ability of students in the early years of elementary school. The experiments were conducted with students of the fifth grade of elementary school in a public school at the outskirts of Santa Maria – RS, during classes in Computer room between 2011 and 2013. In order to test the hypotheses of this study, different steps were performed including the following: exploratory study, pilot study, a second study and the multimedia learning objects questionnaire, which was applied in 2011 and 2013. The data collected during the 2011 pilot study, were the basis for the proposition of the second study performed in 2013 which defined the different experimental conditions with the types and levels of interactivity, media to be used and the skills related to the content addressed in multimedia. Initially, data normality was tested using the Kolmogorov - Smirnov test and it was confirmed data did not follow a normal distribution (p<0.05). From this result, it was decided to perform non-parametric tests to compare the values of the successes and the mistakes between the Multimedia Test Group and Control Group. The surveys (2011 and 2013) answers were analyzed (chi–square test). Join statistical analyses indicate some versions of multimedia with significant results and through the questionnaires; it was possible to detect some variables that probably influenced positively on students’ performance. This supports the conclusion that the models of Interactive Multimedia Learning Objects and the didactic sequence used in the experiments enabled the researched people to improve their ability to read and write.

O contexto tecnológico percebido em vários setores da sociedade brasileira impulsiona a sua utilização em sala de aula que, por sua vez, não deve estar desconectada dessa realidade. Neste cenário, os materiais digitais no formato de multimídia interativa são reconhecidos como uma possibilidade educativa. Importantes avaliações reconhecem as dificuldades nas habilidades de leitura e escrita de alunos do Ensino Fundamental, como a Prova Brasil e o Indicador de Analfabetismo Funcional (INAF). O referencial teórico desta tese está ancorado na Teoria Cognitiva de Aprendizagem Multimídia, do inglês Cognitive Theory Multimedia Learning (CTML), principalmente nos princípios de interatividade e multimídia propostos por Richard Mayer, publicados em 2001 e 2011 e que constituem relevante orientação para projetos de Objetos de Aprendizagem Multimídia Interativos (OAMI) eficazes. Além disso, esta tese adota as taxonomias de Schwier e Misanchuk de 1993 e de Sims de 1997 e 2000, sobre interatividade em educação. Trata-se de uma pesquisa qualitativa e quantitativa, cujo objetivo é comprovar se e como os diferentes modelos de Objetos de Aprendizagem Multimídia Interativos possibilitam o aprimoramento da capacidade de leitura e escrita dos alunos nos anos iniciais do Ensino Fundamental. Os experimentos foram realizados com alunos do quinto ano do Ensino Fundamental de uma escola pública da periferia de Santa Maria - RS, durante as aulas em sala de Informática entre 2011 e 2013. Para testar as hipóteses deste estudo, foram realizadas diferentes etapas que incluem: estudo exploratório, estudo piloto, segundo estudo e o questionário sobre os objetos de aprendizagem multimídia, o qual foi aplicado em 2011 e 2013. Os dados levantados no estudo piloto de 2011 serviram como base para a proposição do segundo estudo em 2013 que definiu diferentes condições experimentais, com os tipos e níveis de interatividade, as mídias a serem utilizadas e as habilidades referentes ao conteúdo abordado nas multimídias. Inicialmente testou-se a normalidade dos dados, empregando-se o teste de Kolmogorov-Smirnov e constatou-se que os dados não seguiam uma distribuição normal (p < 0,05). A partir desse resultado, optou-se pela realização de testes não paramétricos para a comparação entre os valores dos acertos e dos erros, das Multimídias do Grupo Teste e do Grupo Controle. As respostas dos questionários (2011 e 2013) foram analisadas (Teste Qui-quadrado). As análises estatísticas conjuntas indicam algumas versões de multimídia com resultados significativos e, através dos questionários, foi possível detectar algumas variáveis que provavelmente influenciaram positivamente no desempenho dos alunos, chegando-se à conclusão de que os modelos de Objetos de Aprendizagem Multimídia Interativos utilizados nos experimentos e a sequência / The technological context perceived in various sectors of Brazilian society drives its use in the classroom, which in turn should not be disconnected from this reality. In this scenario, the digital materials in an interactive multimedia format are recognized as an educational opportunity. Important assessments as Prova Brasil (Brazil Test) and the Functional Illiteracy Indicator (INAF - Indicador de Analfabetismo Funcional), acknowledge the reading and writing skills difficulties of elementary school students. The theoretical framework of this thesis is anchored in the Cognitive Theory of Multimedia Learning (CTML), mainly on the interactivity and multimedia principles proposed by Richard Mayer, published in 2001 and 2011 and which are relevant guidance to effective projects of Interactive Multimedia Learning Objects. Moreover, this thesis adopts the interactivity education taxonomies proposed by Schwier and Misanchuk 1993 and Sims 1997 and 2000. This is a qualitative and quantitative research, whose goal is to prove whether and how the different models of Interactive Multimedia Learning Objects enable the improvement of reading and writing ability of students in the early years of elementary school. The experiments were conducted with students of the fifth grade of elementary school in a public school at the outskirts of Santa Maria – RS, during classes in Computer room between 2011 and 2013. In order to test the hypotheses of this study, different steps were performed including the following: exploratory study, pilot study, a second study and the multimedia learning objects questionnaire, which was applied in 2011 and 2013. The data collected during the 2011 pilot study, were the basis for the proposition of the second study performed in 2013 which defined the different experimental conditions with the types and levels of interactivity, media to be used and the skills related to the content addressed in multimedia. Initially, data normality was tested using the Kolmogorov - Smirnov test and it was confirmed data did not follow a normal distribution (p<0.05). From this result, it was decided to perform non-parametric tests to compare the values of the successes and the mistakes between the Multimedia Test Group and Control Group. The surveys (2011 and 2013) answers were analyzed (chi–square test). Join statistical analyses indicate some versions of multimedia with significant results and through the questionnaires; it was possible to detect some variables that probably influenced positively on students’ performance. This supports the conclusion that the models of Interactive Multimedia Learning Objects and the didactic sequence used in the experiments enabled the researched people to improve their ability to read and write.

<div>Real-time social media data can provide useful information on evolving events and situations. In addition, various domain users are increasingly leveraging real-time social media data to gain rapid situational awareness. Informed by discussions with first responders and government officials, we focus on two major barriers limiting the widespread adoption of social media for situational awareness: the lack of geotagged data and the deluge of irrelevant information during events. Geotags are naturally useful, as they indicate the location of origin and provide geographic context. Only a small portion of social media is geotagged, however, limiting its practical use for situational awareness. The deluge of irrelevant data provides equal difficulties, impeding the effective identification of semantically relevant information. Existing methods for short text relevance classification fail to incorporate users' knowledge into the classification process. Therefore, classifiers cannot be interactively retrained for specific events or user-dependent needs in real-time, limiting situational awareness. In this work, we first adapt, improve, and evaluate a state-of-the-art deep learning model for city-level geolocation prediction, and integrate it with a visual analytics system tailored for real-time situational awareness. We then present a novel interactive learning framework in which users rapidly identify relevant data by iteratively correcting the relevance classification of tweets in real-time. We integrate our framework with the extended Social Media Analytics and Reporting Toolkit (SMART) 2.0 system, allowing the use of our interactive learning framework within a visual analytics system adapted for real-time situational awareness.</div>

Senaste tidens debatt om de ständigt sjunkande matematikkunskaperna hos svenska elever i kombination med den lärarbrist som vuxit fram i den svenska skolan har skapat ett utrymme för diskussion kring och behov av alternativa lärandeformer. Idag utnyttjar ungdomar internet i allt större utsträckning och det är troligtvis där som nya plattformar för lärande har störst potential att lyckas. Den här studien är inriktad på interaktivt e-lärande. Det övergripande syftet med studien är att förbättra förutsättningarna för elevers studier i matematik då de använder en interaktiv e-lärandetjänst. För att åstadkomma detta identifierades tre viktiga aspekter i syfte att mäta hur den digitala studiemiljön i den interaktiva e-lärandetjänsten upplevs. Efter detta togs en metod fram och användes för att förbättra den digitala studiemiljön utifrån de tre aspekterna. Rapporten beskriver hur en interaktiv e-lärandetjänst kan vidareutvecklas genom utvärdering och implementering av ny programvara. Den tjänst som har utvecklats är den svenska interaktiva e-lärandetjänsten Mattecoach på nätet. Utifrån resultaten som erhölls från utvärderingen togs förbättringsförslag fram och implementerades varpå en ny utvärdering följde. I den här studien lyckades vi hitta ett antal förbättringspunkter vilka vi sedemera implementerade en större del av. Resultatet från studien indikerar att dessa förbättringar bidrog till en bättre studiemiljö samt att ett gångbart sätt att utveckla en interaktiv elärandetjänst är att undersöka olika aspekter (tidsaspekt, coachningsaspekt, programvaruaspekt) med syfte att utvärdera tjänsten, och därefter utveckla tjänsten genom att förbättra dessa aspekter med utgångspunkt i teorier om lärande och användares önskemål. / Recent debate about the ever decreasing mathematics skills of Swedish students combined with the shortage of mathematics teachers in the Swedish school system have created the need for alternative forms of learning. Today the number of young people who use the internet is at an all time high and it is probably on the internet that new platforms for learning have the greatest potential to succeed. This study focuses on interactive e-learning. The overall objective of the study presented in this thesis is to improve the conditions for students studying mathematics using an interactive e-learning service. To accomplish this, three important aspects were identified in order to measure how the digital learning environment of the interactive e-learning service is experienced. After that, a method is developed in order to improve the digital learning environment, based on the three aspects. The report describes how an interactive e-learning service can be further improved through assessment and implementation of new software. The service that has been assessed and improved is the Swedish interactive e-learning service Mattecoach på nätet. Based on results obtained from surveys and interviews, potential ways to improve the service were found and parts of those improvements were implemented. In order to assess the improvements made, a second evaluation was conducted. In this study, we managed to find a number of improvement points of which we later on implemented a big part of. The result from the study indicates that these improvements contributed to a better study environment and that a viable way to develop an interactive elearning service is to examine different aspects (time aspect, coaching aspect, software aspect) with the aim to evaluate the service, and then develop the service by improving these aspects based on theories of learning and users preferences.

Every day, machine learning (ML) and artificial intelligence (AI) embeds itself further into domestic and industrial technologies. Interaction de- signers have historically struggled to engage directly with the subject, facing a shortage of appropriate methods and abstractions. There is a need to find ways though which interaction design practitioners might integrate ML into their work, in order to democratize and diversify the field. This thesis proposes a mode of inquiry that considers the inter- active qualities of what machine learning does, as opposed the tech- nical specifications of what machine learning is. A shift in focus from the technicality of ML to the artifacts it creates allows the interaction designer to situate its existing skill set, affording it to engage with ma- chine learning as a design material. A Research-through-Design pro- cess explores different methodological adaptions, evaluated through user feedback and an-in depth case analysis. An elaborated design experiment, Multiverse, examines the novel, non-anthropomorphic aesthetic qualities of generative literature. It prototypes interactions with bidirectional literature and studies how these transform the reader into a cybertextual “user-reader”. The thesis ends with a discussion on the implications of machine written literature and proposes a number of future investigations into the research space unfolded through the prototype.

In the domain of cyber security, machine learning promises advanced threat detection. However, the volume of available unlabeled data poses challenges for efficient data management. This study investigates the potential for active learning, a subset of interactive machine learning, to reduce the effort required for manual data labelling. Through different query strategies, the most informative unlabeled data points were selected for manual labelling. The performance of different query strategies was assessed by testing a transformer model’s ability to accurately distinguish tweets mentioning names of advanced persistent threats. The findings suggest that the K-means diversity-based query strategy outperformed both the uncertainty-based approach and the random data point selection, when the amount of labelled training data was limited. This study also evaluated the cost-effective active learning approach, which incorporates high-confidence data points into the training dataset. However, this was shown to be the least effective strategy. Lastly, the study acknowledges that the computational time taken for each query strategy varies significantly between strategies. Hence, an optimal query strategy selection requires a balanced consideration of F-score performance taken together with time efficiency. / Maskininlärning skulle kunna användas för avancerad hotdetektion i cyberdomänen. Dock utgör behovet av träningsdata tillsammans med den stora tillgången till oannoterad data en utmaning. Detta arbete undersöker huruvida aktiv inlärning, en delmängd av interaktiv maskininlärning, kan minska behovet av annoterad data. Genom olika frågestrategier valdes de mest informativa datapunkterna ut för mänsklig annotering. Resultaten för de olika frågestrategierna utvärderades sedan genom att testa en maskininlärningsmodells förmåga att korrekt urskilja tweets som innehåller namn på cyberhotsaktörer. Resultaten tyder på att när mängden annoterad data var begränsad, presterade den diversifieringsbaserade strategin K-means bättre än både den osäkerhetsbaserade frågestrategin och strategin som väljer ut datapunkter slumpmässigt. Denna studie utvärderade också kostnadseffektiv aktiv inlärning som lägger till datapunkter som modellen redan är relativt säker på till träningsdatamängden. Denna metod visade sig dock vara den minst effektiva strategin. Slutligen visar arbetet att beräkningstiden som krävs för varje frågestrategi varierar avsevärt. För att utse den mest optimala frågestrategin krävs därför ett övervägande av både prestanda och tidsåtgång.

Left heart disease often results in left heart failure and right ventricular dysfunction which is challenging to diagnose with traditional diagnostic approaches. To address this a novel empirical 4-point right ventricular dysfunction score was created at Sahlgrenska University Hospital to overcome the limitations of single variables for diagnosing right ventricular dysfunction. In this study, we used machine learning, more specifically XGBoost coupled with interactive machine learning to develop four different models for predicting death or receiving a left ventricular assist device in patients with left heart disease (n=486). Features were selected from the dataset using recursive feature elimination with the default number of features. The initial model with 29 features, called the baseline model served as the foundation of the three additional models, each adjusted based on feedback from a clinician. The first step of feedback included removing features due to high correlation, creating a modified model with 12 features, the second step was to use 12 well-known characteristics of left and right ventricular dysfunction creating an empirical model, and adjusting the prediction threshold from 50% to 60%. The third step was to reduce the number of features to 5 based on empirical grounds. The models were compared to the right ventricular dysfunction score using the metrics area under the curve, f1 score, positive likelihood ratio, and negative likelihood ratio. The predictive efficacy of the machine learning models was superior compared to the right ventricular dysfunction score. The results also indicated that the models did neither improve nor deteriorate when reducing the number of features. However, insufficient accuracy indicates that none of the machine learning models are clinically viable. These results show the potential of machine learning in enhancing prognostic stratification in patients with left heart disease although further refinement is necessary for clinical use. / Vänstersidig hjärtsjukdom resulterar ofta i vänstersidig hjärtsvikt och högerkammarsvikt vilket är utmanade att diagnostisera med traditionella diagnostiska metoder. För att komma undan med begränsningen med enskilda variabler för att diagnostisera högerkammarsvikt skapades ett 4 poängs högerkammarsvikt score vid Sahlgrenska Universitetssjukhuset. I denna studie användes en XGBoost-algoritm kombinerat med interaktiv maskininlärning för att utveckla fyra olika prediktions modeller för att förutsäga dödlighet eller risken att få en mekanisk hjärtpump för vänster kammare hos patienter med vänster hjärtsvikt (n=486). Variabler valdes från datamängden med hjälp av rekursiv funktionseliminering med ett standardantal variabler. Den initiala modellen med 29 variabler kallades baslinjemodellen och fungerade som grunden för de tre ytterligare modellerna som justerades baserat på klinikerns feedback. Det först steget inkluderade att ta bort variabler med inbördes hög korrelation och vi skapade en modifierad modell med 12 variabler. I det andra steget i den empiriska modellen använde vi 12 kända egenskaperna vid vänsterkammar- och högerkammarsvikt och för båda justerades tröskelvärdet för prediktion från 50% till 60%. I ett tredje steg skapade vi en förenklad modell med 5 variabler ut ifrån klinisk grund. Modellerna jämfördes med höger hjärtsvikts 4 poängskalan med hjälp av mätvariablerna area under kurvan, f1-poäng, positivt sannolikhets ratio och negativt sannolikhets ratio. Detta avslöjade att maskininlärnings modellerna hade bättre prediktiv förmåga än 4-poängs högerkammarsvikt score. Dessutom visade resultatet att modellerna inte försämrades eller förbättrades när variabler valdes bort eller när nya modeller skapades på klinisk grund. Dock hade maskininlärnings modellerna otillräcklig noggrannhet för klinisk användning.

The aim of this thesis is to analyse and provide a summary of the existing knowledge and teachers' attitudes regarding the usage and sources of interactive electronic learning materials in primary schools. Furthermore, the thesis compares the theory with real-life experience. The theoretical part introduces the current sources and possibilities of the use of interactive electronic learning materials in primary schools. Moreover, it defines the interactive electronic learning materials and the implementation of modern technologies in education. The research part analyses the opinions of the teachers and the challenges they perceive in the incorporation of interactive electronic learning materials into their teaching. Furthermore, it supports the theory with the practical application of interactive electronic learning materials in various primary school subjects. The concluding part confronts the theoretical knowledge with the practical experience. At the same time, it introduces some of the author's examples of activities using interactive electronic learning materials which can be used during elementary school classes.