Common authorship attribution is well described by various authors summed up in Jacques Savoy’s work. Namely, authorship attribution is the process “whereby the author of a given text must be determined based on text samples written by known authors [48].” The field of authorship attribution has been explored in various contexts. Most of these works have been done on the authors written text. This work seeks to approach a similar field to authorship attribution. We seek to attribute not a given author to a work based on style, but a style itself that is used by a group of people. Our work classifies an author into a category based off the spoken dialogue they have said, not text they have written down. Using this system, we differentiate California State Legislators from other entities in a hearing. This is done using audio transcripts of the hearing in question. As this is not Authorship Attribution, the work can better be described as ”Conversational Style Attribution”. Used as a tool in speaker identification classifiers, we were able to increase the accuracy of audio recognition by 50.9%, and facial recognition by 51.6%. These results show that our research into Conversational Style Attribution provides a significant benefit to the speaker identification process.

Parameter estimation is a pivotal task across various domains such as system identification, statistics, and machine learning. The literature presents numerous estimation procedures, many of which are backed by well-studied asymptotic properties. In the contemporary landscape, highly advanced digital twins (DTs) offer the capability to faithfully replicate real systems through proper tuning. Leveraging these DTs, data-driven estimators can alleviate challenges inherent in traditional methods, notably their computational cost and sensitivity to initializations. Furthermore, traditional estimators often rely on sensitive data, necessitating protective measures. In this thesis, we consider data-driven and privacy-preserving approaches to parameter estimation that overcome many of these challenges. The first part of the thesis delves into an exploration of modern data-driven estimation techniques, focusing on the two-stage (TS) approach. Operating under the paradigm of inverse supervised learning, the TS approach simulates numerous samples across parameter variations and employs supervised learning methods to predict parameter values. Divided into two stages, the approach involves compressing data into a smaller set of samples and the second stage utilizes these samples to predict parameter values. The simplicity of the TS estimator underscores its interpretability, necessitating theoretical justification, which forms the core motivation for this thesis. We establish statistical frameworks for the TS estimator, yielding its Bayes and minimax versions, alongside developing an improved minimax TS variant that excels in computational efficiency and robustness to distributional shifts. Finally, we conduct an asymptotic analysis of the TS estimator. The second part of the thesis introduces an application of data-driven estimation methods, that includes the TS and neural network based approaches, in the design of tuning rules for PI controllers. Leveraging synthetic datasets generated from DTs, we train machine learning algorithms to meta-learn tuning rules, streamlining the calibration process without manual intervention. In the final part of the thesis, we tackle scenarios where estimation procedures must handle sensitive data. Here, we introduce differential privacy constraints into the Bayes point estimation problem to protect sensitive information. Proposing a unified approach, we integrate the estimation problem and differential privacy constraints into a single convex optimization objective, thereby optimizing the accuracy-privacy trade-off. In cases where both observations and parameter spaces are finite, this approach reduces to a tractable linear program which is solvable using off-the-shelf solvers. In essence, this thesis endeavors to address computational and privacy concerns within the realm of parameter estimation. / Skattning av parametrar utgör en fundamental uppgift inom en mängd fält, såsom systemidentifiering, statistik och maskininlärning. I litteraturen finns otaliga skattningsmetoder, utav vilka många understödjs av välstuderade asymptotiska egenskaper. Inom dagens forskning erbjuder noggrant kalibrerade digital twins (DTs) möjligheten att naturtroget återskapa verkliga system. Genom att utnyttja dessa DTs kan data-drivna skattningsmetoder minska problem som vanligtvis drabbar traditionella skattningsmetoder, i synnerhet problem med beräkningsbörda och känslighet för initialiseringvillkor. Traditionella skattningsmetoder kräver dessutom ofta känslig data, vilket leder till ett behov av skyddsåtgärder. I den här uppsatsen, undersöker vi data-drivna och integritetsbevarande parameterskattningmetoder som övervinner många av de nämnda problemen.  Första delen av uppsatsen är en undersökning av moderna data-drivna skattningtekniker, med fokus på två-stegs-metoden (TS). Som metod inom omvänd övervakad maskininlärning, simulerar TS en stor mängd data med ett stort urval av parametrar och tillämpar sedan metoder från övervakad inlärning för att förutsäga parametervärden. De två stegen innefattar datakomprimering till en mindre mängd, varefter den mindre mängden data används för parameterskattning. Tack vare sin enkelhet och tydbarhet lämpar sig två-stegs-metoden väl för teoretisk analys, vilket är uppsatsens motivering. Vi utvecklar ett statistiskt ramverk för två-stegsmetoden, vilket ger Bayes och minimax-varianterna, samtidigt som vi vidareutvecklar minimax-TS genom en variant med hög beräkningseffektivitet och robusthet gentemot skiftade fördelningar. Slutligen analyserar vi två-stegs-metodens asymptotiska egenskaper.  Andra delen av uppsatsen introducerar en tillämpning av data-drivna skattningsmetoder, vilket innefattar TS och neurala nätverk, i designen och kalibreringen av PI-regulatorer. Med hjälp av syntetisk data från DTs tränar vi maskininlärningsalgoritmer att meta-lära sig regler för kalibrering, vilket effektiverar kalibreringsprocessen utan manuellt ingripande.  I sista delen av uppsatsen behandlar vi scenarion då skattningsprocessen innefattar känslig data. Vi introducerar differential-privacy-begränsningar i Bayes-punktskattningsproblemet för att skydda känslig information. Vi kombinerar skattningsproblemet och differential-privacy-begränsningarna i en gemensam konvex målfunktion, och optimerar således avvägningen mellan noggrannhet och integritet. Ifall både observations- och parameterrummen är ändliga, så reduceras problemet till ett lätthanterligt linjärt optimeringsproblem, vilket löses utan vidare med välkända metoder.  Sammanfattningsvis behandlar uppsatsen beräkningsmässiga och integritets-angelägenheter inom ramen för parameterskattning. / <p>QC 20240306</p>

<p> A new technique for the systematic identification of metal-protein complexes combining gel chromatography with either neutron activation analysis or radioactive tracer methods has been proposed. The technique has been tested on the copper in serum situation to evaluate the results obtained on a well-known system.</p> <p> It was then applied to manganese in serum, manganese in erythrocytes and copper in erythrocytes. The results indicate that serum contains two manganese-binding proteins, one of low molecular weight and relatively labile in nature, the other of higher molecular weight and incorporating radioactive manganese in vivo at some definite time interval subsequent to the isotope's administration.</p> <p> Manganese in erythrocytes occurs as a porphyrin bound to apoglobin as a manganese analogue of hemoglobin.</p> <p> Copper in erythrocytes appears to exist in two forms - one firmly bound to erythrocuprein, the other more loosely bound to the same protein.</p> / Thesis / Doctor of Philosophy (PhD)

Batch reactors are often used to produce high quality products because any batch that does not meet quality speci cations can be easily discarded. However, for high-value products, even a few wasted batches constitute substantial economic loss. Fortunately, databases of historical data that can be exploited to improve operation are often readily available. Motivated by these considerations, this thesis addresses the problem of direct, data-based quality control for batch processes. Speci cally, two novel datadriven modeling and control strategies are proposed. The rst approach addresses the quality modeling problem in two steps. To begin, a partial least squares (PLS) model is developed to relate complete batch trajectories to resulting batch qualities. Next, the so called missing-data problem, encountered when using PLS models partway through a batch, is addressed using a data-driven, multiple-model dynamic modeling approach relating candidate input trajectories to future output behavior. The resulting overall model provides a causal link between inputs and quality and is used in a model predictive control scheme for direct quality control. Simulation results for two di erent polymerization reactors are presented that demonstrate the e cacy of the approach. The second strategy presented in this thesis is a state-space motivated, timeinvariant quality modeling and control approach. In this work, subspace identi cation methods are adapted for use with transient batch data allowing state-space dynamic models to be identifi ed from historical data. Next, the identifi ed states are related through an additional model to batch quality. The result is a causal, time-independent model that relates inputs to product quality. This model is applied in a shrinking horizon model predictive control scheme. Signi cantly, inclusion of batch duration as a control decision variable is permitted because of the time-invariant model. Simulation results for a polymerization reactor demonstrate the superior capability and performance of the proposed approach. / Thesis / Doctor of Philosophy (PhD) / High-end chemical products, ranging from pharmaceuticals to specialty plastics, are key to improving quality of life. For these products, production quality is more important than quantity. To produce high quality products, industries use a piece of equipment called a batch reactor. These reactors are favorable over alternatives because if any single batch fails to meet a quality specifi cation, it can be easily discarded. However, given the high-value nature of these products, even a small number of discarded batches is costly. This motivates the current work which addresses the complex topic of batch quality control. This task is achieved in two steps: first methods are developed to model prior reactor behavior. These models can be applied to predict how the reactor will behave under future operating policies. Next, these models are used to make informed decisions that drive the reaction to the desired end product, eliminating o -spec batches.

<p> With the growth of technology there is recognition of the fact that communication requires improving between decision-makers and the people who will eventually use or be affected by the system under consideration. The main thrust of this work is to explore means of facilitating clear unambiguous communication of relevant needs to all parties involved in the design process.</p> <p> A number of approaches to this problem from different disciplines are reviewed. Some of these approaches are already in existence while others require adapting to the particular problems encountered in the design process.</p> <p> Suggestions are put foreward as to how these techniques can be integrated to produce a unified approach to the problem of producing a Total Specification embodying all information necessary to the designer in his capacity as decision-maker.</p> / Thesis / Master of Engineering (MEngr)

<p> The role of verbal hypotheses in concept identification was explored by manipulating three variables affecting the relation between verbalized rules and classification performance. (i) Verbalizing rules before and after classification changed subjects' cue-sampling strategies and the control of verbal hypotheses over sorting performance. (ii) The difficulty of stimulus description affected how subjects utilized verbal hypotheses, and whether verbalized rules completely specified the cues used for classification. (iii) The number of irrelevant attributes changed the relative efficiency of stimulus-learning over rule-learning for concept identification.</p> <p> These investigations demonstrate effective techniques for varying and evaluating the importance of verbal rules for classification; and suggest that subjects' prior verbal habits markedly affect the degree of reliance placed on verbal hypotheses in concept attainment.</p> / Thesis / Doctor of Philosophy (PhD)

This study aims to explore nursing students' knowledge and perceptions of identifying and treating victims of sexual assault and sex trafficking. Survey data was collected from second to fifth semester nursing students in Eastern Tennessee. The study aims to identify students' perceptions of medical personnel's ability to identify and treat sexual assault and sex trafficking victims, examine whether adherence to myths affects knowledge and confidence levels, determine students' confidence in identifying and treating victims, and evaluate whether demographic characteristics affect identification and treatment. Results will help improve our approach towards these issues.

Organizations have begun to focus heavily on diversity. As a result, organizations spend time and resources creating diversity policies and investing extensively in diversity training programs. While an abundance of research exists on demographic diversity, research has just begun to incorporate employees’ perceptions of diversity as an influential factor affecting organizationally relevant employee outcomes. Employees are a crucial reference in understanding whether organizations benefit from engaging in such actions. The purpose of this study is to examine the influence of diversity climate on employees’ organizational identification. Furthermore, I investigate how organizational identification mediates the relationship between diversity climate perceptions and outcomes including turnover intentions, job satisfaction, and organizational citizenship behavior. I refine our understanding by identifying personal characteristics that influence the diversity climate (PDC) – organizational identification (OID) relationship. This research offers several contributions to management literature and scholars as well as practitioners. First this study empirically examines the relationship between PDC and OID. This connection is important as it identifies the psychological mechanism linking PDC to subsequent outcomes as well as showing how positive climate perception can influence an employee’s sense of belonging. The second contribution is the in-depth identification of personal characteristics and their role in this relationship specifically, demographics, values, and attachment to demographic category. Individuals will differ in their beliefs and thus their attachment based on climate perceptions. Finally, this study links diversity climate to organizationally relevant outcomes through organizational identification.

Nonfamily employees make up a substantial portion of family firm personnel and are crucial to success for these firms. Retaining these employees is complicated by the presence of family members and family-centric goals, which often results in the bifurcated treatment of nonfamily employees. However, the relationships between family and nonfamily employees could have implications for how nonfamily employees perceive the firm. This study examines how nonfamily employees’ turnover intentions are influenced by their embeddedness in family member friendship networks, family firm identification, and perceptions of organizational support. Drawing on a sample of 103 nonfamily employees working in a family firm, my analysis shows that identification fully mediates the effects of nonfamily employee degree centrality in family friendship networks and turnover intentions. Drawing on social identification theory, degree centrality in family friendship networks is theorized to influence perceptions of belongingness in the family firm, which negatively impact turnover intentions. Implications for understanding how nonfamily employees and employee retention may be influence by social networks are also discussed.

Identifying the location of sunken logs is a task of considerable interest in today?s world economy. The main motive of this work is to find and locate sunken cypress logs that were lost during the transit to a lumber mills. Underwater logging is possible because of the fact that many of the logs were barely affected by the decades of submersion. Cypress logs, the types of logs used in this research have a natural resistant to rotting. The other probability for the logs not being affected significantly, even staying in water for decades, is the high density of the growth rings. The quality of these sunken logs is far superior because of their high density in growth rings and they have a high economic value compared to present day logs. Sidescan sonar is proposed for the work of locating the sunken logs. Based on various research and studies, which involve several similar projects, sidescan sonar is proposed to locate and identify these sunken targets. These images that resemble a cylinder in some aspects can then be compared with a template for pattern matching. Any image size that is not matched with the acceptable size can be rejected. Using this template matching procedure, the size of the object is matched and the logs can be located and recovered. Based on various technical papers and studies involving similar projects, conclusions were drawn and future work has been suggested.