In this new digital age, efficiency, quality and competition are all increasing rapidly as companies leverage the Industrial Internet of Things (IIoT). However, while industrial innovation moves at a faster and faster pace, educational institutions have lagged in the development of the curriculum and environment needed to support further development of the IIoT. To fully realize the potential of the IIoT in the manufacturing sector educational institutions must support the technological training and education rigor demanded to instill the skills and thought leadership to move the industry forward. The purpose of this research is to provide an IIoT core system in an educational factory environment. This system will assist in teaching basic principles of IIoT in the factory while simultaneously allowing for students to envision the manufacturing journey of any facility by implementing principles of IIoT. This will be accomplished by providing all the following capabilities together in a single data system: unified connectivity, role-based data display, real-time issue identification, data analytics, and augmented reality.

Im Rahmen dieser Dissertation wird sich mit der Einbettung komplexer Datenanalyseprozesse in serviceorientierten Umgebungen beschäftigt. Diese Betrachtung beginnt mit einem konkreten Anwendungsgebiet, indem derartige Analyseprozesse eine entscheidende Rolle bei der Wissenserschließung spielen und ohne deren Hilfe kein Fortschritt erzielt werden kann. Im zweiten Teil werden konkrete komplexe Datenanalyseprozesse entwickelt, die den Ausgangspunkt für die Erörterung der Einbettung in eine serviceorientierte Umgebung bilden. Auf diese Einbettung wird schlussendlich im dritten Teil der Dissertation eingegangen und entsprechende Erweiterungen an den Technologien der bekanntesten Realisierungsform präsentiert. In der Evaluierung wird gezeigt, dass diese neue Form wesentlich besser geeignet ist für komplexe Datenanalyseprozesse als die bisherige Variante.

Background: Digital technologies are increasingly transforming traditional businesses, and their pervasive impact is leading to a radical restructuring of entire industries. While the significance of generating competitive advantages for businesses utilizing big data analytics is recognized, there is still a lack of consensus of big data analytics influencing strategic decision-making in organisations. As big data and big data analytics become increasingly common, understanding the factors influencing decision-making quality becomes of paramount importance for businesses. Purpose: This thesis investigates how big data and big data analytics affect the operational strategic decision-making processes in enterprises through the theoretical lens of the strategy-as-practice framework. Method: The study follows an abductive research approach by testing a theory (i.e., strategy-aspractice) through the use of a qualitative research design. A single case study of IKEA was conducted to generate the primary data for this thesis. Sampling is carried out internally at IKEA by first identifying the heads of the different departments within the data analysis and from there applying the snowball sampling technique, to increase the number of interviewees and to ensure the collection of enough data for coding. Findings: The findings show that big data analytics has a decisive influence on practitioners. At IKEA, data analysts have become an integral part of the operational strategic decision-making processes and discussions are driven by data and rigor rather than by gut and intuition. In terms of practices, it became apparent that big data analytics has led to a more performance-oriented use of strategic tools and enabling IKEA to make strategic decisions in real-time, which not only increases agility but also mitigates the risk of wrong decisions.

I takt med digitaliseringen blir datadrivet beslutsfattande det nya normala i många branscher. Konkurrensfördelarna är allmänt kända eftersom det hjälper företag att utvecklas. Denna fallstudie syftar till att belysa de möjligheter som datadriven optimering bidrar med för skidorter när det kommer till att förbättra tjänster och anpassa skidanläggningar för framtiden. Huvudfokuset är att studera rörelsemönster hos skidåkare med hjälp av processutvinningsverktyg och andra metoder för visualisering. Detta har lett till följande forskningsfrågor: Vilken information går att utvinna ur data från liftsystem? Hur skulle denna typ av information kunna skapa värde i en organisation? Tidigare studier inom detta forskningsområde visar på stora möjligheter med användning av datautvinning och uppmanar till fortsatt forskning. Studien bidrar till forskningen genom att studera specifika åldersgrupper vilket tidigare inte genomförts. Studien visar att det finns skillnader i rörelsemönster hos olika åldersgrupper av skidåkare, vilket i sin tur visar på potentiella optimeringsområden hos skidanläggningarna. Utöver att belysa potentiella förbättringsområden med hjälp av datadrivna beslut visar studien även på en markant förändring hos typen av skidåkare som besöker svenska skidorter 2021, vilket troligtvis berodde på att Alperna höll stängt under skidsäsongen. I framtiden kan studien spela en viktig roll för forskning gällande hur Covid-19 påverkade svenska skidorter. / Given the digitalization, data-driven decision making is becoming the new normal in many industries. The competitive advantages are widely known as it helps companies to evolve. This case study aims to highlight the possibilities data-driven optimization provides when it comes to improving services and adapting to the future for ski resorts. Our focus is skier movement patterns which we generated by analyzing ski lift transportation data with a process mining tool and other methods for visualizations. Hence, our research questions: What information can be extracted from lift usage data? In what way can this information create value in an organization? Previous studies done in the field demonstrate many possibilities with data mining and urges for continued research. The research provided by this study is a contribution to the field through the research done on specific age-groups as this has not previously been done. This study introduces findings based on differences in the movement patterns based on skier age groups which lead to possible areas of optimization. In addition to highlighting possible ways to improve decision making using data, this study shows a significant shift in the type of skier visiting the Swedish ski-resorts 2021, possibly due to The Alps being closed this season. In the future, this study could play an essential role in studying how Covid-19 impacted Swedish ski-resorts.

In recent years, many sectors such as insurance, banking, retail, etc. have adopted Big Data architectures to boost their business activities. Such tools not only suppose a greater profit for thesecompanies but also allow them to gain a better understanding of their customers and their needs.These techniques are rapidly being adopted, this also being the case of sports and team sportsfor tasks such as injury prediction and prevention, performance improvement, or fan engagement.The aim of this project is to analyze the implications of data-driven decisions focusing on theiractual and future use in sports. Finally, a player scouting and team tailoring application would bedesigned and deployed to help the technical staff decision-making process which will also supposea budget optimization. For doing so, “Python” programming language and “Rapidminer” will beused, implementing “fuzzy logic” techniques for player scouting and “knapsack problem” algorithms for budget optimization plus an additional price prediction algorithm. The outcome wouldbe the application which given certain player needs (e.g., a midfielder with a high pass accuracyand a high ball recovery and a goalkeeper with a big number of saves and many minutes played)and the available budget will suggest the best possible combination of players given the availablebudget and the algorithm capable of predicting prices. This project also intends to study how thisapplication could be deployed in a real case situation by estimating the work team and budget todo so.

Background: The idea of ​​achieving success in sport is something both players as well as fans dream of, but few clubs achieve it. Oakland Athletics succeeded in what many thought was impossible when in the 2002 season, they managed to perform better than most of their competitors whilst having one of the leagues smallest budgets, by recruiting undervalued players based on data and statistics. The concept of "moneyball" was coined therefrom and has since then influenced sport organizations more and more. But how the use of data and statistics has affected the governance in sport organizations is relatively unexplored.  Purpose: The purpose is to create an understanding of how data analytics has affected sports organizations  Method: The study is a qualitative multiple-case study based on an abductive approach to intertwine the theoretical framework together with the empirical data in an analysis that results in conclusions. Seven sport organizations within football and hockey have been the basis for the empirical data.  Conclusion: Data analytics has influenced the corporate governance in sport organizations in many ways. Data and statistics have provided an objective approach to investments and acquisitions of players that did not previously exist. As a result, sport organizations can recruit players who fit their strategy and style of play with greater accuracy. Furthermore, sport organizations can use data analytics as a competitive advantage by using resources more efficiently to find undervalued players in the market and experience both financial and sporting success. However, “moneyball” is a combination of objective aspects in terms of data and statistics, together with subjective aspects, where both are important to be able to use it as a competitive advantage. Today, data analytics is incorporated as part of sport operations where it is used as a part of designing strategies, as well as a basis for decision-making regarding investment appraisal and recruitment. / Bakgrund: Tanken om att nå sportslig framgång är något spelare såväl som fans drömmer om, men få klubbar uppnår det. Oakland Athletics lyckades med det som många trodde var omöjligt när de säsongen 2002, lyckades prestera bättre än de flesta av konkurrenterna samtidigt som man förhöll sig till en av ligans minsta budget genom att värva undervärderade spelare baserat på data och statistik. Konceptet “moneyball” myntades därifrån och har sedan dess influerat sportorganisationer mer och mer. Men hur användningen av data och statistik har påverkat styrningen i sportorganisationer är relativt outforskat.   Syfte: Syftet är att skapa förståelse för hur dataanalys har påverkat sportorganisationer.  Metod: Studien är en kvalitativ flerfallsstudie med utgångspunkt i en abduktiv ansats för att sammanfläta den teoretiska referensramen tillsammans med den empiriska datan i en analys som mynnar ut i konklusioner. Sju sportorganisationer inom fotboll och hockey har varit till grund för det empiriska datan.   Slutsats: Dataanalys har influerat verksamhetsstyrningen i sportorganisationer på många sätt. Data och statistik har tillfört ett objektivt synsätt vid investeringar och förvärv av spelare som tidigare inte fanns. Till följd av detta kan sportorganisationer rekrytera spelare som passar deras strategi och spelsystem med större träffsäkerhet. Därtill kan sportorganisationer använda dataanalys som konkurrensfördel genom att mer effektivt nyttja resurserna för att hitta undervärderade spelare i marknaden och uppleva både ekonomiska såväl som sportsliga framgångar. Däremot är “moneyball” en kombination av det objektiva i form av data och statistik tillsammans med det subjektiva, där båda aspekterna är betydelsefulla för att kunna använda det som en konkurrensfördel. Dataanalys är idag en integrerad del i sportsliga verksamheter där det används i utformandet av strategier såväl som underlag vid beslutsfattning gällande investeringsbedömning och rekrytering.

This thesis provides a discrete-event simulation framework that can be used to analyze  and  dimension  computing  systems.  The  simulation  framework  can define  and  parametrize  the  flexible  queueing  system.  We  use  the  simulation framework to explore the data collected from the real-world system. We analyze the metrics, including waiting time and server utilization of single-server and multi-server  queueing  systems.  In  particular,  we  study  the  impact  of  the number of servers on waiting time and server utilization. The experiments show it  is  possible  to  increase  server  utilization  and  decrease  the  server  number without  significantly  increasing  waiting  time,  and  flexible  architectures  canlead to significant gains. / Detta  examensarbete  tillhandahåller  ett  ramverk  som  kan  användas  för  att analysera och dimensionera dator-system. Simuleringsramverket kan definera och parameterisera ett flexibelt kösystem baserat på data från ett system i drift. Vi använder simuleringsramverket för att undersöka datat insamlat från skarpa system.  Vi  analyserar  prestandatal,  såsom  väntetid  och  utnyttjandegrad  för system  med  en  och  flera  betjänare.  Framför  allt  undersöker  vi  hur  antalet betjänare  påverkar  väntetid  och  utnyttjandegrad.   Försöken  visar  att  det  är möjligt  att  öka  uttnyttjandegraden  och  minska  antalet  betjänare  utan  att märkbart öka väntetiden, och att en flexibel arkitektur kan leda till märkbaraförbättringar. / <p>Industrial Advisors: Olga Grinchtein and Johan Karlsson </p>

The increasing amount and variety of data available in the web leads to new possibilities in end-user focused data analysis. While the classic data base technologies for data integration and analysis (ETL and BI) are too complex for the needs of end users, newer technologies like web mashups are not optimal for data analysis. To make productive use of the data available on the web, end users need easy ways to find, join and visualize it. We propose a domain specific language (DSL) for querying a repository of heterogeneous web data. In contrast to query languages such as SQL, this DSL describes the visualization of the queried data in addition to the selection, filtering and aggregation of the data. The resulting data mashup can be made interactive by leaving parts of the query variable. We also describe an abstraction layer above this DSL that uses a recommendation-driven natural language interface to reduce the difficulty of creating queries in this DSL.

I dagens samhälle har digitalisering blivit en stor del av vår vardag. Med global digitalisering kommer förändringar i hur organisationer och företag fungerar, detta inkluderar även hälso- och sjukvården. En viktig aspekt av digitaliseringen är mängden data som den genererar. Det har blivit en viktig aspekt för framgång under de senaste åren har varit relaterad till hur organisationer använder data till sin egen fördel. Användningen av data har ökat dramatiskt på en global skala och vi kan nu se fördelarna med att ha dataanalys inte bara i organisationen som helhet utan också använda den utvunna data för beslutsfattande. Denna studie syftar till att klargöra hur datadrivet beslutsfattande uppfattas av anställda inom hälso-. och sjukvården. Samt hur de uppfattar användande, möjligheter, begränsningar och risker med att fatta datadrivna beslut. Denna studien är skriven på svenska och har utförts genom en kvalitativ metod. Det har genomförts en liten-n-studie där enskilda intervjuer med fyra stycken respondenter genomförts. Respondenterna upplever att användandet av datadrivet beslutsfattande som något positivt och ser framtida möjligheter för datadrivet beslutsfattande inom hälso- och sjukvården. Dem identifierar risker och begränsningar med att använda denna typ av beslutsfattande, trots detta är fördelarna samtliga respondenter uttrycker övervägande gentemot dem risker och begränsningar som detta medför. / In today's day and age digitalisation has become a big part of our society. With global digitalisation comes changes in how organizations and companies function, this also includes healthcare. An important aspect of digitization is the amount of data it generates. It has become an important aspect of success in recent years has been related to how organizations use data to their own advantage. The use of data has increased dramatically on a global scale and we can now see the benefits of having data analysis not only in the organization as a whole but also using the extracted data for decision making. This study aims to clarify how data-driven decision-making is perceived by health care employees. and healthcare. And how they perceive use, opportunities, limitations and risks in making data-driven decisions. This study is written in Swedish and has been performed using a qualitative method. A small-n study has been conducted in which individual interviews with four respondents were conducted. The respondents perceive the use of data-driven decision-making as something positive and see future opportunities for data-driven decision-making in the health care sector. They identify risks and limitations with using this type of decision-making, despite this the advantages all respondents express are predominantly positive compared to the negative factors regarding data-driven decision-making.

Digital healthcare monitoring uses multidisciplinary sensing techniques to track diverse human data and behaviors. Machine learning can promote an individual's well-being through more efficient and accurate health status monitoring. However, challenges hinder precise monitoring, such as privacy concerns, varied subjects, diverse sensors, and different objectives. To help address these challenges, this thesis explores projects spanning various healthcare domains. Explainable and robust machine-learning solutions are proposed and tested, which include novel signal processing guidelines, innovative feature engineering methods, and pioneering deep-learning networks. These solutions contribute to the state-of-the-art in their respective healthcare domains. The first project addressed the challenge of assessing fall risk among individuals with varying levels of mobility using inertial sensors. Machine-learning models were developed and evaluated using datasets from stroke survivors and community-dwelling elders with participants of varying levels of mobility. Risk indicators were obtained through kinematics simplification that are both explainable and modifiable. These indicators considerably enhance fall risk classification performance compared to existing approaches and the conclusions align with available biomechanical evidence. In the second project, a new machine-learning architecture was created for fall detection and classification using multistatic radar sensing. This new approach (called eMSFRNet) solved the common problem of weak and varied Doppler signatures caused by line-of-sight restrictions. It is the first method that can classify among fall types using radar sensing, and yielded state-of-the-art accuracy for both fall detection (99.3%) and seven fall types classification (76.8%) tasks. In the third project, a novel combination of signal processing and a machine learning framework (named MIND) was designed to detect and forecast motor restricted and repetitive behaviors (RRBs) among children with autism spectrum disorder (ASD), using data from multiple wearable sensors. Contrary to prior beliefs that such detection or forecasting was unattainable, the novel MIND AI framework offers a comprehensive and generalizable approach. Transition behaviors were first defined and then identified, suggesting the potential to detect behavioral shifts preceding motor RRBs. The new signal monitoring quantification (MQ) guidelines minimize the impacts of inconsistent data caused by individualized sensor placements. MIND achieved 100% accuracy in detecting motor RRBs on new subjects with unfamiliar behavior types and 92.2% accuracy in forecasting motor RRBs. In conclusion, the work in this thesis showcases the pivotal contributions of robust and explainable machine learning solutions tailored for specific healthcare challenges. These contributions either solve longstanding problems in different healthcare fields or guide new research directions. The new methodologies introduced – including the MQ guidelines, modifiable fall risk indicators, and innovative deep learning models – all help to advance healthcare machine learning applications by merging accuracy with explainability. / Doctor of Philosophy / Digital healthcare monitoring uses advanced techniques to monitor a person's health and behavior. With the help of machine learning (think of this as teaching computers to think and learn), it is possible to improve health monitoring to be faster and more accurate. Still, there are important challenges to overcome, including concerns regarding personal privacy, the variety of ways in which data can be collected, and the diverse goals of each monitoring tool. This research addressed these challenges by creating and evaluating new machine learning methods for application to multiple healthcare areas. New, understandable, and powerful machine learning methods were developed, pushing the boundaries of how best to use varied technologies for monitoring. A few highlights of the research include the following. First, a method was developed to better determine if an older adult is at a higher risk of falling. The ability of the method to estimate falling risk was very strong, and superior to previously-reported methods. This new method can also explain why an individual might be at a higher risk of falling and offers suggestions on how to walk more stably. Second, a technique was created to process radar signals to detect falls and to determine the type of fall that occurred. This technique solves a long-standing problem with radar, specifically that this sensing technology often provides unclear and unstable signals. Third, a machine-learning method was constructed to identify repetitive (self-injurious) behaviors among children with autism spectrum disorder using signals from wearable sensors. This novel method can detect behaviors quite accurately, even in challenging scenarios. One notable finding was changes in normal behavior can be identified shortly before the repetitive behaviors occur. Overall, this research contributes substantially new and effective methods for healthcare and understandable machine learning solutions. These contributions help to solve challenging, ongoing problems and pave the way for future innovations. Methods such as those developed promise a future where technology can better assist in healthcare, making it more precise and understandable for everyone.