Accuracy in turbulence modeling remains a hurdle in the widespread use of Computational Fluid Dynamics (CFD) as a tool for furthering fluids dynamics research. Meanwhile, computational power remains a significant concern for solving real-life wall-bounded flows, which portray a wide range of length and time scales. The tools for turbulence analysis at our disposal, in the decreasing order of their accuracy, include Direct Numerical Simulation (DNS), Large Eddy Simulation (LES), and Reynolds-Averaged Navier Stokes (RANS) based models. While DNS and LES would remain exorbitantly expensive options for simulating high Reynolds number flows for the foreseeable future, RANS is and continues to be a viable option utilized in commercial and academic endeavors. In the first part of the present work, flow over the back-step test case was solved, and parametric studies for various parameters such as re-circulation length (X_r), coefficient of pressure (C_p), and coefficient of skin friction (C_f) are presented and validated with experimental results. The back-step setup was chosen as the test case as turbulent modeling of flow past backward-facing step has been pivotal to understand separated flows better. Turbulence modeling is done on the test case using RANS (k-ε and k-ω models), and LES modeling, for different values of Reynolds number (Re ∈ {2, 2.5, 3, 3.5} × 10⁴) and expansion ratios (ER ∈ {1.5, 2, 2.5, 3}). The LES results show good agreement with experimental results, and the discrepancy between the RANS results and experimental data was highlighted. The results obtained in the first part reveal a pattern of under-prediction noticed with using RANS-based models to analyze canonical setups such as the backward-facing step. The LES results show close proximity to experimental data, as mentioned above, which makes it an excellent source of training data for the machine learning analysis outlined in the second part. The highlighted discrepancy and the inability of the RANS model to accurately predict significant flow properties create the need for a better model. The purpose of the second part of the present study is to make systematic efforts to minimize the error between flow properties from RANS modeling and experimental data, as seen in the first part. A machine learning model was constructed in the second part of the present study to predict the eddy viscosity parameter (μt) as a function of turbulent kinetic energy (TKE) and dissipation rate (ε) derived from LES data, effectively working as an ad hoc eddy-viscosity based turbulence model. The machine learning model does not work well with the flow domain as a whole, but a zonal analysis reveals a better prediction of eddy viscosity than the whole domain. Among the zones, the area in the vicinity of the re-circulation zone gives the best result. The obtained results point towards the need for a zonal analysis for the better performance of the machine learning model, which will enable us to improve RANS predictions by developing a reduced order turbulence model.

No description available.

<p>Predictive modeling in healthcare involves the development of data-driven and computational models which can predict what will happen, be it for a single individual or for an entire system. The adoption of predictive models can guide various stakeholders’ decision-making in the healthcare sector, and consequently improve individual outcomes and the cost-effectiveness of care. With the rapid development in healthcare of big data and the Internet of Things technologies, research in healthcare decision-making has grown in both importance and complexity. One of the complexities facing those who would build predictive models is heterogeneity of patient populations, clinical practices, and intervention outcomes, as well as from diverse health systems. There are many sub-domains in healthcare for which predictive modeling is useful such as disease risk modeling, clinical intelligence, pharmacovigilance, precision medicine, hospitalization process optimization, digital health, and preventive care. In my dissertation, I focus on predictive modeling for applications that fit into three broad and important domains of healthcare, namely clinical practice, public health, and healthcare system. In this dissertation, I present three papers that present a collection of predictive modeling studies to address the challenge of modeling heterogeneity in health care. The first paper presents a decision-tree model to address clinicians’ need to decide among various liver cirrhosis diagnosis strategies. The second paper presents a micro-simulation model to assess the impact on cardiovascular disease (CVD) to help decision makers at government agencies develop cost-effective food policies to prevent cardiovascular diseases, a public-health domain application. The third paper compares a set of data-driven prediction models, the best performing of which is paired together with interpretable machine learning to facilitate the coordination of optimization for hospital-discharged patients choosing skilled nursing facilities. This collection of studies addresses important modeling challenges in specific healthcare domains, and also broadly contribute to research in medical decision-making, public health policy and healthcare systems.</p>

Given that employees are one of the most valuable assets of any organization, losing an employee has a detrimental impact on several aspects of business activities. Loss of competence, deteriorated productivity and increased hiring costs are just a small fraction of the consequences associated with high employee churn. To deal with this issue, organizations within many industries rely on machine learning and predictive analytics to model, predict and understand the cause of employee churn so that appropriate proactive retention strategies can be applied. However, up to this date, the problem of excessive churn prevalent in the healthcare industry has not been addressed. To fill this research gap, this study investigates the applicability of a machine learning-based employee churn prediction model for a Swedish healthcare organization. We start by extracting relevant features from real employee data followed by a comprehensive feature analysis using Recursive Feature Elimination (RFE) method. A wide range of prediction models including traditional classifiers, such as Random Forest, Support Vector Machine and Logistic Regression are then implemented. In addition, we explore the performance of ensemble machine learning model, XGBoost and neural networks, specifically Artificial Neural Network (ANN). The results of this study show superiority of an SVM model with a recall of 94.8% and a ROC-AUC accuracy of 91.1%. Additionally, to understand and identify the main churn contributors, model-agnostic interpretability methods are examined and applied on top of the predictions. The analysis has shown that wellness contribution, employment rate and number of vacations days as well as number of sick day are strong indicators of churn among healthcare employees. / Det sägs ofta att anställda är en verksamhets mest värdefulla tillgång. Att förlora en anställd har därmed ofta skadlig inverkan på flera aspekter av affärsverksamheter. Därtill hör bland annat kompetensförlust, försämrad produktivitet samt ökade anställningskostnader. Dessa täcker endast en bråkdel av konsekvenserna förknippade med en för hög personalomsättningshastighet. För att hantera och förstå hög personalomsättning har många verksamheter och organisationer börjat använda sig av maskininlärning och statistisk analys där de bland annat analyserar beteendedata i syfte att förutsäga personalomsättning samt för att proaktivt skapa en bättre arbetsmiljö där anställda väljer att stanna kvar. Trots att sjukvården är en bransch som präglas av hög personalomsättning finns det i dagsläget inga studier som adresserar detta uppenbara problem med utgångspunkt i maskininlärning. Denna studien undersöker tillämpbarheten av maskininlärningsmodeller för att modellera och förutsäga personalomsättning i en svensk sjukvårdsorganisation. Med utgångspunkt i relevanta variabler från faktisk data på anställda tillämpar vi Recursive Feature Elimination (RFE) som den primära analysmetoden. I nästa steg tillämpar vi flertalet prediktionsmodeller inklusive traditionella klassificerare såsom Random Forest, Support Vector Machine och Logistic Regression. Denna studien utvärderar också hur pass relevanta Neural Networks eller mer specifikt Artificial Neural Networks (ANN) är i syfte att förutse personalomsättning. Slutligen utvärderar vi precisionen av en sammansatt maskininlärningsmodell, Extreme Gradient Boost. Studiens resultat påvisar att SVM är en överlägsen model med 94.8% noggranhet. Resultaten från studien möjliggör även identifiering av variabler som mest bidrar till personalomsättning. Vår analys påvisar att variablerna relaterade till avhopp är friskvårdbidrag, sysselsättningsgrad, antal semesterdagar samt sjuktid är starkt korrelerade med personalomsättning i sjukvården.

This study uses the predictive modeling program Sea-Levels Affecting Marshes Model (SLAMM) to evaluate sea-level rise hazards, such as erosion and inundation, on coastal archaeological sites with a vertical rise of sea level of .98 meters from 2006 to 2100. In total 177 archaeological site locations were collected and georeferenced over GIS outputs maps of wetlands, erosion presence, surface elevation, and accretion. Wetlands data can provide useful information about characteristics of the wetland classes, which make a difference in the ability for coastal archaeological sites to combat sea level rise. Additionally, the study evaluated predicted erosion of archaeological sites by presence or absence of active erosion on a cell-by-cell basis. Elevation map outputs relative to mean tide level allowed for a calculation of individual archaeological site datums to use NOAA tidal databases to identify the potential for their inundation. Accretion maps acquired from the SLAMM run determined the potential for the archaeological site locations to combat rising sea levels and potentially provide protection from wave effects. Results show that the most significant hazard predicted to affect coastal archaeological sites is inundation. Approximately 54% of the total archaeological sites are predicted to be inundated at least half the time by 2100. The hazard of erosion, meanwhile, is expected to affect 33% of all archaeological sites by the end of the century. Although difficult to predict, the study assumes that accretion will not be able to keep pace with sea-level rise. Such findings of hazards prove that SLAMM is a useful tool for predicting potential effects of sea-level rise on coastal archaeological sites. With its ability to customize and as it is complementary, it provides itself not only an economical choice but also one that is adaptable to many scenarios.

Clinical and research practice in the context of Autism rapidly evolved in the last decades. Finer diagnostic procedures, evidence-based models of intervention and higher social inclusivity significantly improved the possibility for autistic children to participate in the fabric of social life. In terms of health best practices, gold-standard procedures still need to be improved, and bridging research and clinical practice still presents several challenges. From the clinical standpoint, the role of process variables, predictors, mechanisms, and timing of change still requires extensive investigation in order to explain response variability and design optimized interventions, tailored to individual needs and maximally effective. Observational techniques represent the elective research methods in child development, especially in clinical contexts, due to their non-invasiveness. However, they still suffer from limited objectivity and poor quantification. Further, their main disadvantage is that they are highly time-consuming and labor-intensive. The aim of this thesis was moving forward to promote translational research in clinical practice of Autism intervention with preschool children. At first, we tried to design and apply quantitative observational techniques to longitudinally study treatment response trajectories during developmental intervention. We tried to characterize different response profiles, and which baseline predictors were able to predict the response over time. Secondly, we investigated mechanisms of change. In particular, we focused on the role of the child-therapist interaction dynamics as a possible active mediator of the process of intervention, especially in the developmental framework that stresses the importance of interpersonal aspects. We also aimed at understanding whether certain time-windows during the intervention were particularly predictive of the response, as well as which specific interaction aspects played a role. Finally, to promote the translational application of observational methods and to improve objective quantification, we proposed and validated an Artificial Intelligence (AI) system to automate data annotation in unconstrained clinical contexts, remaining completely non-invasive and dealing with the specific noisy data that characterize them, for the analysis of the child-therapist acoustic interaction. This effort represents a base building block enabling to employ downstream computational techniques greatly reducing the need for human annotation that usually prevents the application of observational research to large amounts of data . We discuss our findings stressing the importance of assuming a developmental framework in Autism, the key role of the interpersonal experience also in the clinical context, the importance of focusing on trajectories of change and the important need to promote the acquisition of large amounts of quantitative data from the clinical contexts exploiting AI-based systems to assist clinicians, improving objectivity, enabling treatment monitoring, and producing precious data-driven knowledge on treatment efficacy.

No description available.

No description available.

No description available.

<p>  This paper explored the application of three machine learning models focused on predictive motor maintenance. Logistic Regression, Sequential Minimal Optimization (SMO), and NaïveBayes models. A comparative analysis of these models illustrated that while each had an accuracy greater than 95% in this study, the Logistic Regression Model exhibited the most reliable operation.</p>