This study was designed to characterize consumer purchases of organic milk by differentiating consumers based on buying behavior and then evaluating what personal and household characteristics were most prominent in each group. Cluster analysis was used to differentiate four groups of consumers based on their total volume of milk purchases, percentage of organic milk purchases, and frequency of milk purchases. The clusters were then characterized based on household size, household income, age of children, race, Hispanic origin, and head of household's age, education, occupation, and gender. Regression analysis then estimated the effects of the socio-demographic variables on cluster membership. Results were consistent with existing literature. Those who purchased the most organic milk were females with a small household, families consisting of one or two members, or larger families, usually four. These two groups of consumers differentiated themselves from one another and from the other two clusters that purchased less organic milk with larger families purchasing more milk, but a smaller percentage of organic milk purchases. The results of identifying consumers based on their milk buying behavior can be used by marketers and educators to target individuals, based on group membership, for planning and guiding education and advertising campaigns and programs. / Master of Science

Materials have typically been selected based on the familiarities and past experiences of a limited number of designers with a limited number of materials. Problems arise when the designer is unfamiliar with new or improved materials, or production processes more efficient and economical than past choices. Proper utilization of complete materials and processing information would require acquisition, understanding, and manipulation of huge amounts of data, including dependencies among variables and "what-if" situations. The problem of materials selection has been addressed with a variety of techniques, from simple broad-based heuristics as guidelines for selection, to elaborate expert system technologies for specific selection situations. However, most materials selection methodologies concentrate only on material properties, leaving other decision criteria with secondary importance. Factors such as component service environment, design features, and feasible manufacturing methods directly influence the material choice, but are seldom addressed in systematic materials selection procedures. This research addresses the problem of developing a systematic materials selection procedure that can be integrated with standard materials data bases. The three-phase methodology developed utilizes a group technology code and cluster analysis method for the selection. The first phase is of go/no go nature, and utilizes the possible service environment requirements of ferromagnetism and chemical corrosion resistance to eliminate materials from candidacy. In the second phase, a cluster analysis is performed on key design and manufacturing attributes captured in a group technology code for remaining materials. The final phase of the methodology is user-driven, in which further analysis of the output of the cluster analysis can be performed for more specific or subjective attributes. / Master of Science

No / Model interpretation is one of the key aspects of the model evaluation process. The explanation of the relationship between model variables and outputs is relatively easy for statistical models, such as linear regressions, thanks to the availability of model parameters and their statistical significance . For “black box” models, such as random forest, this information is hidden inside the model structure. This work presents an approach for computing feature contributions for random forest classification models. It allows for the determination of the influence of each variable on the model prediction for an individual instance. By analysing feature contributions for a training dataset, the most significant variables can be determined and their typical contribution towards predictions made for individual classes, i.e., class-specific feature contribution “patterns”, are discovered. These patterns represent a standard behaviour of the model and allow for an additional assessment of the model reliability for new data. Interpretation of feature contributions for two UCI benchmark datasets shows the potential of the proposed methodology. The robustness of results is demonstrated through an extensive analysis of feature contributions calculated for a large number of generated random forest models.

Chronic pain is a pervasive health issue, affecting a significant portion of the population and posing complex challenges due to its diverse etiology and individualized impact. To address this complexity, there is a growing interest in grouping chronic pain patients based on their unique treatment needs. While various methodologies for patient grouping have emerged, leveraging graph-based approaches to produce and evaluate such groupings remains largely unexplored. Recent studies have shown promise in integrating knowledge graphs into exploring patient similarity across different biological domains, indicating potential avenues for research. Additionally, there is a growing interest in investigating patient similarity networks, highlighting the importance of innovative approaches to understanding chronic pain. Graphs offer a transparent and easily interpretable framework for analyzing patient classifications, providing valuable insights into underlying patterns and connections. By leveraging graph theory, this thesis proposes a novel approach to address the terminological disparities that exist across disciplines studying chronic pain. By constructing a graph of pain-related terminology sourced from interdisciplinary literature, we aim to facilitate link prediction and clarify connections among disparate terminologies. This approach seeks to bridge disciplinary divides, fostering a cohesive understanding of chronic pain and promoting collaborative efforts toward effective management and treatment strategies. Through the integration of graph theory and interdisciplinary research, this thesis contributes to advancing our understanding of chronic pain and lays the groundwork for future explorations in patient grouping and treatment optimization by proposing a graph-based clustering method as well as a method for evaluating the robustness of a cluster.

No description available.

京都大学 / 新制・課程博士 / 博士(理学) / 甲第25112号 / 理博第5019号 / 京都大学大学院理学研究科物理学・宇宙物理学専攻 / (主査)教授 永江 知文, 教授 田島 治, 教授 萩野 浩一 / 学位規則第4条第1項該当 / Doctor of Science / Kyoto University / DGAM

Thesis (PhD (Physics))-University of Stellenbosch, 2009. / ENGLISH ABSTRACT: A binary cluster model is used to investigate the properties of the ground state band of 212Po, modelled as a 208Pb-alpha core-cluster system. The results obtained using a microscopic corecluster potential are compared to those obtained with a purely phenomenological potential. The two potentials were found to exhibit similar surface behaviour and thus give similar predictions for the ground state alpha decay half-life. They however generate very different energy spectra, with the results from the phenomenological potential clearly superior. We optimize the phenomenological potential parameters, and propose an additional short range interaction to improve the underbinding generally found for the J¼ = 0+ ground state. We then investigate two possible scenarios for generating the negative parity states in 212Po. We find that both are necessary in order to produce low-lying negative parity states which are able to decay via electric dipole transitions to the positive parity states of the ground state band. Finally we present a novel calculation of the properties of the low-lying positive and negative parity states of 218Rn described as a doubly closed 208Pb core plus a 10Be cluster. / AFRIKAANSE OPSOMMING: ’n Binêre bondel model word gebruik om die eienskappe van die grondtoestands energie band van 212Po, te modeleer as ’n 208Pb-alpha kern-bondel sisteem te ondersoek. Die resultate verkry vanaf ’n mikroskopiese kern-bondel potentiaal word vergelyk met die wat verkry is met ’n suiwer fenomenologiese potentiaal. Die twee potentiale is verkry om dieselfde oppervlakte toestande voor te stel en gee sodoende dieselfde voorspellings vir die grondtoestand alpha verval halfleeftyd. Alhoewel dit baie verskillende energie spektra genereer, toon die resultate van die fenomenologiese potentiaal dat dit duidelik beter is. Ons optimiseer hierdie fenomenologiese parameters en stel ’n addisionele kort ry-afstands interaksie voor om die algemene ondergebondenheid wat oor die algemeen by die J¼ = 0+ grondtoestand voorkom, te verbeter. Ons ondersoek ook hierdie twee moontlike scenarios om die negatiewe pariteitstoestande in 212Po te genereer. Ons vind dat beide scenarios noodsaaklik is om laagliggende pariteitstoestande te produseer, sodat verval deur elektriese dipool oorgange na die positiewe pariteitstoestande van die grondtoestandsband moontlik is. Laagliggende positiewe en negatiewe pariteitstoestande, van die 218Rn wat beskryf word as ’n dubbelgeslote 208Pb kern en ’n 10Be bondel.

This thesis generalizes and interprets Kesten\'s Incipient Infinite Cluster (IIC) measure in two ways. Firstly we generalize Járai\'s result which states that for planar lattices the local configurations around a typical point taken from crossing collection is described by IIC measure. We prove in Chapter 2 that for backbone, lowest crossing and set of pivotals, the same hold true with multiple armed IIC measures. We develop certain tools, namely Russo Seymour Welsh theorem and a strong variant of quasi-multiplicativity for critical percolation on 2-dimensional slabs in Chapters 3 and 4 respectively. This enables us to first show existence of IIC in Kesten\'s sense on slabs in Chapter 4 and prove that this measure can be interpreted as the local picture around a point of crossing collection in Chapter 5.

This dissertation focuses on methodology specific to microarray data analyses that organize the data in preliminary steps and proposes a cluster analysis method which improves the interpretability of the cluster results. Cluster analysis of microarray data allows samples with similar gene expression values to be discovered and may serve as a useful diagnostic tool. Since microarray data is inherently noisy, data preprocessing steps including smoothing and filtering are discussed. Comparing the results of different clustering methods is complicated by the arbitrariness of the cluster labels. Methods for re-labeling clusters to assess the agreement between the results of different clustering techniques are proposed. Microarray data involve large numbers of observations and generally present as arrays of light intensity values reflecting the degree of activity of the genes. These measurements are often two dimensional in nature since each is associated with an individual sample (cell line) and gene. The usual hierarchical clustering techniques do not easily adapt to this type of problem. These techniques allow only one dimension of the data to be clustered at a time and lose information due to the collapsing of the data in the opposite dimension. A novel clustering technique based on normal mixture distribution models is developed. This method clusters observations that arise from the same normal distribution and allows the data to be simultaneously clustered in two dimensions. The model is fitted using the Expectation/Maximization (EM) algorithm. For every cluster, the posterior probability that an observation belongs to that cluster is calculated. These probabilities allow the analyst to control the cluster assignments, including the use of overlapping clusters. A user friendly program, 2-DCluster, was written to support these methods. This program was written for Microsoft Windows 2000 and XP systems and supports one and two dimensional clustering. The program and sample applications are available at http://etd.vcu.edu. An electronic copy of this dissertation is available at the same address.

L’industrie française a connu un ralentissement de sa productivité depuis la fin des années 1980 jusqu’à nos jours. Cette situation s’est accentuée avec la montée en puissance de l’Allemagne et l’émergence de pays comme la Chine, l’Inde et le Brésil. Dés lors, la France se devait de réagir car étant soumise à la loi du marché qui est basée sur la compétitivité des produits destinés à l’exportation. C’est dans ce contexte que l’État va s’atteler à la relance de l’économie en créant les pôles de compétitivité en juillet 2005. C’est donc pour étudier cette dynamique de développement que j’ai décidé d’effectuer une thèse de doctorat sur l’enjeu des pôles de compétitivité en Île-de France en s’appuyant sur l’exemple de Systematic-Paris-Région, Cap Digital Paris-Région et Advancity Ville et Mobilité Durables. / Since the 1980’s end in until now, the French industry has known a slowing down of its productivity. The situation became speed with the economic power of Germany and the emergence of countries such as China, India and Basil. Therefore, France had to react because being submitted to the law of the market place which is based on the competitiveness of products intended for export. It is in this context that the State is so going to get down in the economic stimulus plan by creating in July 2005 the poles of competitiveness. It is thus to study this development process that I decided to do doctoral thesis on the stake of the poles of competitiveness in Ile-de-France basing me on the example of Systématic-Paris-Région, Cap Digital Paris-Région and Advancity Ville and Sustainable Mobility.