This study aims to examine and identify possibilities andprerequisites for implementing a High Performance Work System(HPWS) in a Swedish non-profit association’s operations. Theessay assumes a set of frameworks in the form of HPWS practiceswhich are defined in previous research in order to determine andevaluate the implementation possibilities in the association. Thestudy takes place in “SRL Spelförening”, a non-profit associationwhich conduct welfare processes in the form of esports in theSwedish grassroot scene. The association has during its lifespanundergone large changes within all aspects of its operation – notleast the structure of work processes, something that has meantthat many parts of the workflow are unorganized and unstructured.This study analyzes the current state of the association’sprocesses with a quantitative interview approach focused on a setof work-related variables. The data that is generated is then usedas a control tool when the association’s prevalent prerequisites ofHPWS are to be determined. The data was also applied in a linearregression model generating correlation coefficients among thework-related variables – information which in turn gets applied inorder to decide the association’s individual attitude to HPWS. Theanalysis points to the association generally meeting the HPWSrequirements which were cited in earlier research. Some aspectswere however determined to lie beneath the bar and thereforerequire changes in accordance with earlier similar HPWS relatedcases. Furthermore, the correlation results show that theassociation’s workers’ overall attitude towards HPWS was positive,where a higher appreciation of a HPWS was related to higherengagement and lower turnover intention.

The Free-To-Play industry relies on getting a huge inflow of new players that might result in future gross bookings. Consequently, getting organic new players is crucial to ensure its health, especially as they have no direct associated acquisition cost. In addition, forecasting helps business planning as future gross bookings result from those news installs. This thesis investigates methods such as Linear Regression, Ridge, Lasso regularization, time-series analysis, and Prophet to forecast the inflow of organic installs and try to understand the factors impacting it. Using the data from 3 games for two platforms and 15 countries, it investigates the differences in behavior observed over the segments. This thesis first focuses on a specific segment by modeling the inflow of organic installs for the game number 17 on iOS in the United States of America. On this segment, the best model is the Lasso model using, among others, a Prophet model as a variable. However, the generalization to all segments is difficult. On average, exponential decay over time is the best way to forecast the future inflow of organic as it presents the more consistent performances over all segments. / Free-To-Play-branschen är beroende av att få ett stort inflöde av nya spelare, som sedan eventuellt kan generera framtida intäkter. För att kunna säkerställa ett spels fortsatta hälsa är det därför avgörande att få nya spelare organiskt. Detta är särskilt viktigt då det inte innebär någon anskaffningskostnad. Då framtida intäkter är beroende av nya nedladdningar är prognostisering till stor nytta i företagsplanering. Denna uppsats använder metoder som linjär regression, Ridge, Lasso-regularization, tidsserieanalys och Prophet för att förutspå inflödet av organiska nedladdningar och förstå vilka faktorer som påverkar detta inflöde.Genom användningen av data från tre spel från två plattformar och 15 länder undersöks skillnader i beteende för olika segment. Denna uppsats fokuserar på ett specifikt segment genom att modellera inflödet av organiska nedladdningar för spel nummer 17 på iOS i USA. För detta segment är Lasso-modellen bäst, som bland annat använder Prophet-modellen som variabel. Det är dock svårt att överföra slutsatserna på andra segment. Istället är det bättre att anta en exponentiell nedgång över tid när man förutspår framtida inflöden av organiska nedladdningar, då det ger mer konsekventa resultat för alla segment.

No description available.

No description available.

Nanopore sequencing is the next generation ofsequencing methods which promises to deliver cheaper andmore portable genome sequencing capabilities. A single DNAor RNA strand is passed through a nanopore nested in anartificial membrane with an electric potential applied across it.The nucleotide bases of the helix then interact with the ioniccurrent in the nanopore, resulting in a unique signal that canbe translated into the correct corresponding nucleotide sequence.This project investigated whether features of the raw signal datacould be used as predictive indicators of the duration time ofeach nucleotide base in the nanopore. This is done in orderto segment the signal before translation. The training data setused came from the sequenced DNA molecules of an E. Colibacterium. Distribution candidates were fitted to a histogram ofthe duration data of the training set. Features of the currentsignal and distribution parameters were correlated in orderinvestigate if a linear predictive model could be created. Theresults indicate that the feature zero-crossings is not an optimaloption for construction of a linear model, while the large jumpsand moving variance features often generate linear patterns. The parameter of the Log-logistic distribution had the best fit withthe lowest relative root mean square deviation (rRMSD) of 2.7%. / Nanopore sequencing är nästa generationensmetod för DNA sekvensering som kommer att bidra medbilligare och mer portabla sekvenseringsmöjligheter. Metodeninnebär att en enkelsträngad DNA eller RNA molekyl passerargenom porer i nanostorlek, placerade i ett artificiellt membransamtidigt som en elektrisk potential appliceras över membranet.Nukleotiderna i genmolekylen interagerar med jonströmmen iporen, vilket resulterar i en unik signal som kan översättas tillden korresponderande sekvensen av nukleotider som passerat.Detta projekt gick ut på att undersöka om egenskaper frånsignalen kan användas som predikativa indikatorer för varaktighetensom varje nukleotid befinner sig i membranporen. Dettaför att sedan kunna segmentera signalen före översättningen tillDNA sekvensen. Träningsdata som användes är sekvenserad DNAfrån en E. Coli bakterie. Kandiderande sannolikhetsfördelningaranpassades till ett histogram som beskriver varaktigheten.Egenskaperna och parametrar från fördelningarna korreleradesför att skapa en linjär modell. Resultatet visade att antaletskärningar i x-axeln som signalegenskap inte är det optimalavalet för konstruktion av en linjär modell. Skillnaden mellan två signalvärden som är mindre än en varierbar konstant ochglidande variansen som signalegenskaper genererar ofta linjäramönster. Resultatet visade även att sannolikhetsfördelningen Loglogistichade lägst relativ medelkvadratavvikelse (rRMSD) på 2.7%. / Kandidatexjobb i elektroteknik 2021, KTH, Stockholm

Estimating the variables of importance in inferentialmodelling is of significant interest in many fields of science,engineering, biology, medicine, finance and marketing. However,variable selection in high-dimensional data, where the number ofvariables is relatively large compared to the observed data points,is a major challenge and requires more research in order toenhance reliability and accuracy. In this bachelor thesis project,several known methods of variable selection, namely orthogonalmatching pursuit (OMP), ridge regression, lasso, adaptive lasso,elastic net, adaptive elastic net and multivariate adaptive regressionsplines (MARS) were implemented on a high-dimensional dataset.The aim of this bachelor thesis project was to analyze andcompare these variable selection methods. Furthermore theirperformance on the same data set but extended, with the numberof variables and observations being of similar size, were analyzedand compared as well. This was done by generating models forthe different variable selection methods using built-in packagesin R and coding in MATLAB. The models were then used topredict the observations, and these estimations were compared tothe real observations. The performances of the different variableselection methods were analyzed utilizing different evaluationmethods. It could be concluded that some of the variable selectionmethods provided more accurate models for the implementedhigh-dimensional data set than others. Elastic net, for example,was one of the methods that performed better. Additionally, thecombination of final models could provide further insight in whatvariables that are crucial for the observations in the given dataset, where, for example, variable 112 and 23 appeared to be ofimportance. / Att skatta vilka variabler som är viktigai inferentiell modellering är av stort intresse inom mångaforskningsområden, industrier, biologi, medicin, ekonomi ochmarknadsföring. Variabel-selektion i högdimensionella data, därantalet variabler är relativt stort jämfört med antalet observeradedatapunkter, är emellertid en stor utmaning och krävermer forskning för att öka trovärdigheten och noggrannheteni resultaten. I detta projekt implementerades ett flertal kändavariabel-selektions-metoder, nämligen orthogonal matching pursuit(OMP), ridge regression, lasso, elastic net, adaptive lasso,adaptive elastic net och multivariate adaptive regression splines(MARS), på ett högdimensionellt data-set. Syftet med dettakandidat-examensarbete var att analysera och jämföra resultatenav dessa metoder. Vidare analyserades och jämfördes metodernasresultat på samma data-set, fast utökat, med antalet variableroch observationer ungefär lika stora. Detta gjordes genom attgenerera modeller för de olika variabel-selektions-metodernavia inbygga paket i R och programmering i MATLAB. Dessamodeller användes sedan för att prediktera observationer, ochestimeringarna jämfördes därefter med de verkliga observationerna.Resultaten av de olika variabel-selektions-metodernaanalyserades sedan med hjälp av ett flertal evaluerings-metoder.Det kunde fastställas att vissa av de implementerade variabelselektions-metoderna gav mer relevanta modeller för datanän andra. Exempelvis var elastic net en av metoderna sompresterade bättre. Dessutom drogs slutsatsen att kombineringav resultaten av de slutgiltiga modellerna kunde ge en djupareinsikt i vilka variabler som är viktiga för observationerna, där,till exempel, variabel 112 och 23 tycktes ha betydelse. / Kandidatexjobb i elektroteknik 2021, KTH, Stockholm

The purpose of this study is to investigate if it is possible to decrease Sweden's energy consumption through adaptive heating that uses climate data to detect occupancy in apartments using machine learning. The application of the study has been made using environmental data from one of KTH Live-In Labs apartments. The data was first used to investigate the possibility to detect occupancy through machine learning and was then used as input in an adaptive heating model to investigate potential benefits on the energy consumption and costs of heating. The result of the study show that occupancy can be detected using environmental data but not with 100% accuracy. It also shows that the features that have greatest impact in detecting occupancy is light and carbon dioxide and that the best performing machine learning algorithm, for the used dataset, is the Decision Tree algorithm. The potential energy savings through adaptive heating was estimated to be up to 10,1%. In the final part of the paper, it is discussed how a value creating service can be created around adaptive heating and its possibility to reach the market.

The mean variance framework (MV) developed by Markowitz in his groundbreaking paper offers a quantitative and rational approach to portfolio selection. It is well known to market practitioners however that the MV optimal portfolios tend to perform subpar. One of the issues of the MV portfolios is that they require the inverse of a large covariance matrix, which is often ill-conditioned. In this thesis, we develop a new approach to circumvent these issues. We propose an optimisation approach akin to least squares linear regression and compare the performance with an establish method, covariance shrinkage. When tested on a set of 30 futures contracts, we find that the models yield promising results albeit somewhat lower than that of the benchmark. / Mean variance ramverket (MV) framtaget av Markowitz i sin banbrytande artikel möjliggör en kvantitativ och rationell metod för portföljallokering. Det är däremot ett väletablerat faktum bland marknadsaktörer att Markowitz-optimala portföljer tenderar att prestera relativt dåligt. Ett av tillkortakommandena av ramverket är den ofta problemtyngda inverteringen av, den ofta stora, kovariansmatrisen som är illa konditionerad. I denna uppsats föreslår vi en ny metod för att kringgå detta problem. Vi föreslår en optimeringsmetodologi mycket lik minsta kvadratmetoden i linjär regression. Denna metod utvärderas sedan mot en vedertagen metod, kovarianskrympning. När vi utvärderar vår modell på 30 stycken terminskontrakt ser vi lovande resultat men finner en Sharpekvot något lägre än referensportföljens.

WiFi can provide network coverage for users on land at anytime and anywhere, but on the sea, the wireless communication scenes change dramatically due to the signals are non-existence. Although some techniques (e.g. satellite, undersea fiber, microwave communication) have been used in marine communication, they are either too expensive with very small bandwidth, or too limited in its coverage range. We propose to develop a marine wireless mesh network which is formed by low cost buoyed wireless base stations to provide broadband connectivity for users on the sea. Ocean wave simulation and prediction are key technologies in developing marine mesh network, because marine environments are dramatically different from terrestrial environment. The ocean waves have characteristics of rhythmic oscillations and the line of sight between two communication nodes is often blocked by them. Therefore, we have to develop a new wave-state-aware networking protocol which is suitable for marine environments. Ocean wave simulation technology can simulate this kind of dynamic environments and provide a test platform for the development of marine mesh network. Ocean wave prediction technology can improve the throughput of marine wireless network. Thus, they are indispensable technologies in developing marine mesh network. In this thesis, we designed an ocean wave measurement method, two ocean wave prediction methods, and an ocean wave simulation method. Firstly, we designed an accelerometer-based ocean wave measurement method. It can measure the real time wave height accurately. Secondly, we designed an Elman-neural-network-based ocean wave prediction method for nonlinear waves. It has a higher prediction accuracy than other neural network methods in nonlinear wave prediction. Thirdly, we designed a multiple-linear-regression-based ocean wave prediction method for linear waves. It has a higher prediction accuracy and less time consumption than other methods in linear wave prediction. Finally, we implemented and improved a spectrum-based ocean wave simulation method which is originally proposed by Tessendorf. It can present the movement of ocean waves realistically and in real time. To sum up, above four methods provide an effective test platform and technical support for the development of our marine mesh network. / Master of Science / With the development of wireless communication technology, WiFi has been an indispensable resource for daily work and pleasure. However, in the marine environments, WiFi is not exist. Thus, passengers and workers on the sea are eager for it. We propose to develop a marine wireless mesh network which is formed by low cost buoyed wireless base stations to provide WiFi for users on the sea. Marine environments are dramatically different from terrestrial environments. The ocean waves have characteristics of rhythmic oscillations and the link between two buoys is often blocked. Therefore, the signals are also intermittent. We decided to develop a new wave-state-aware networking protocol to eliminate the harmful effect of this kind of rhythmic oscillations. Ocean wave simulation and prediction are key technologies in developing networking protocol, in which ocean wave simulation technology can simulate the marine environments and provide a test platform for developing networking protocol. Ocean wave prediction technology can improve the network throughput. Thus, they are indispensable technologies in developing marine mesh network. In this thesis, we mainly research three problems that related to ocean waves, they are ocean wave measurement, ocean wave prediction and ocean wave simulation. Ocean wave measurement can tell us the current wave height of a buoy, ocean wave prediction can tell us the future height of a buoy, after we know these information, we can decide whether allow the buoy to send signal. It can not only save energy, but also improve the success rate of communication. Ocean wave simulation can provide us a dynamic environment to test whether our networking protocol works well. To sum up, these methods provide an effective test platform and technical support for the development of our marine mesh network.

This thesis examined the sensitivity of the EQ-5D-5L instrument in measuring health-related quality of life (HRQoL) among patients with persistent symptoms following COVID-19, including fatigue, memory and concentration problems, and dyspnea. Additionally, it was analyzed whether adding these symptoms to the EQ-5D-5L improved the explained variance for HRQoL. Patients from Uppsala University Hospital, Sweden, answered a survey that included questions on five dimensions of health represented by the EQ-5D-5L and an additional question on general health score called EQ-VAS. Multiple linear regression, Spearman’s rank correlation coefficient, and Least Absolute Shrinkage and Selection Operator (LASSO) were used to examine the sensitivity of the EQ-5D-5L. For the explanatory analysis, the Adjusted 𝑅2 was used to evaluate explanatory power with and without the presence of the symptoms. The results showed that the EQ-5D-5L dimensions explained a moderate proportion of the variance for fatigue and memory/concentration problems and a weak proportion for dyspnea. The explanatory analysis provided findings that fatigue significantly improved the explained variance of EQ-VAS by 5.5%, adding memory/concentration problems only improved it marginally, and adding dyspnea was non-significant. Additionally, strong to moderate correlations between fatigue and memory/concentration problems were found with multiple dimensions of the EQ-5D-5L. These findings suggest that the EQ-5D-5L instrument may be a valuable tool in assessing HRQoL in patients with persistent COVID-19 symptoms and that adding fatigue to the EQ-5D-5L could be beneficial for improving explanatory power to HRQoL in patients suffering from infectious disease. / COMBAT post-covid