Thesis (M.S.)--University of Akron, Dept. of Biomedical Engineering, 2008. / "December, 2008." Title from electronic thesis title page (viewed 12/12/2009) Advisor, Dale H. Mugler; Committee members, Daniel B. Sheffer, Bruce C. Taylor; Department Chair, Daniel B. Sheffer; Dean of the College, George K. Haritos; Dean of the Graduate School, George R. Newkome. Includes bibliographical references.

This dissertation develops statistical and data mining based methods for insurance fraud detection. Insurance fraud is very costly and has become a world concern in recent years. Great efforts have been made to develop models to identify potentially fraudulent claims for special investigations. In a broader context, insurance fraud detection is a classification task. Both supervised learning methods (where a dependent variable is available for training the model) and unsupervised learning methods (where no prior information of dependent variable is available for use) can be potentially employed to solve this problem. First, an unsupervised method is developed to improve detection effectiveness. Unsupervised methods are especially pertinent to insurance fraud detection since the nature of insurance claims (i.e., fraud or not) is very costly to obtain, if it can be identified at all. In addition, available unsupervised methods are limited and some of them are computationally intensive and the comprehension of the results may be ambiguous. An empirical demonstration of the proposed method is conducted on a widely used large dataset where labels are known for the dependent variable. The proposed unsupervised method is also empirically evaluated against prevalent supervised methods as a form of external validation. This method can be used in other applications as well. Second, another set of learning methods is then developed based on the proposed unsupervised method to further improve performance. These methods are developed in the context of a special class of data mining methods, active learning. The performance of these methods is also empirically evaluated using insurance fraud datasets. Finally, a method is proposed to estimate the fraud rate (i.e., the percentage of fraudulent claims in the entire claims set). Since the true nature of insurance claims (and any level of fraud) is unknown in most cases, there has not been any consensus on the estimated fraud rate. The proposed estimation method is designed based on the proposed unsupervised method. Implemented using insurance fraud datasets with the known nature of claims (i.e., fraud or not), this estimation method yields accurate estimates which are superior to those generated by a benchmark naïve estimation method. / text

Many important scientific questions can not be studied properly using a single measurement as a response. For example, many phenotypes of interest in recent clinical research may be difficult to characterize due to their inherent complexity. It may be difficult to determine the presence or absence of disease based on a single measurement, or even a few measurements, or the phenotype may only be defined based on a series of symptoms. Similarly, a set of related phenotypes or measurements may be studied together in order to detect a shared etiology. In this work, we propose methods for studying complex phenotypes of these types, where the phenotype may be characterized either longitudinally or by a diverse set of continuous, discrete, or not fully observed components. In chapter 1, we seek to identify predictors that are related to multiple components of diverse outcomes. We take up specifically the question of identifying a multiple regulator, where we seek a genetic marker that is associated with multiple biomarkers for autoimmune disease. To do this, we propose sparse multiple regulation testing (SMRT) both to estimate the relationship between a set of predictors and diverse outcomes and to provide a testing framework in which to identify which predictors are associated with multiple elements of the outcomes, while controlling error rates. In chapter 2, we seek to identify risk profiles or risk scores for diverse outcomes, where a risk profile is a linear combination of predictors. The risk profiles will be chosen to be highly correlated to latent traits underlying the outcomes. To do this, we propose semiparametric canonical correlation analysis (sCCA), an updated version of the classical canonical correlation analysis. In chapter 3, the scientific question of interest pertains directly to the progression of disease over time. We provide a testing framework in which to detect the association between a set of genetic markers and the progression of disease in the context of a GWAS. To test for this association while allowing for highly nonlinear longitudinal progression of disease, we propose functional principal variance component (FPVC) testing.

Not available / text

This dissertation addresses the creation of polarization vortex beams. Vortex retarders are components with uniform retardance but a fast axis which rotates around its center with can create polarization vortices. The goal was to develop a simple method for producing vortex retarders for visible wavelengths, with a continuous fast axis, and for multiple vortex modes.The approach was to use photo-aligned liquid crystal polymers (LCP). The target was a halfwave retardance for wavelengths in the range of 540~550nm. A photo-alignment layer was spin-coated onto a substrate, baked, and alignment was set through exposure to linear polarized UV (LPUV) light. The alignment layer was exposed through a narrow wedge shaped aperture located between the substrate and polarizer. Both the polarizer and substrate were continuously rotated during exposure process in order to create a continuous variation in photo-alignment orientation with respect to azimuthal locations on the substrate. The mode of the vortex retarder was determined by the relative rotation speeds. The LCP precursor was spin-coated and subsequently polymerized using a UV curing processes. Elements produced were analyzed by measuring the space variant Mueller Matrix of each component. Our measurements demonstrated that the vortex retarders were half wave plates with a continuous fast axis orientation. Measurement of the center region of the vortex retarders identifies a 100-200um region of disorientation. At 0.5mm resolution, a high depolarization index in the center of the vortex retarders was observed. The DOP was low in the center for a horizontal linear polarized input field but remained high for circular polarized input.The viability of these components was assessed by determining the point spread matrix (PSM) and the optical transfer matrix (OTM) and comparing these to theoretical calculations. The agreement between the measured and predicted PSM was excellent. The major difference was the non-zero response in the m03 and m30 elements indicating circular diattenuation. The OTM comparison between measured and predicted demonstrated an excellent quantitative match at lower spatial frequencies and a good qualitative match at higher spatial frequencies. Measured results confirm that vortex retarders produced using photo-aligned LCP produce near theoretical performance in an optical system.

A diallel analysis of eight upland cotton (Gossypium hirsutum L.) genotypes was conducted in the field over two years to determine the potential for improvement in within-boll seed yield components and fiber quality parameters. Four exotic germplasm lines from the converted race stock (CRS) collection and four commercial types representing Texas, mid-South, and Eastern production regions were crossed and evaluated in a diallel with parents but without reciprocals according to Griffing's Model I, Method 2. Significant variation for genotypic, general combining ability (GCA) effects, and specific combining ability (SCA) effects (P 0.05) were identified for all traits studied indicating potential for improvements through selection. Significant interactions of these parameters with years were also observed, suggesting that selection should be based on multiple years and or locations. In addition to effects on yield, individual seed number traits were found to respond to heat stress under controlled growth chamber conditions, suggesting their potential for use in screening genotypes for heat tolerance. These traits were not found to interact with temperature, which indicates that selection for improvements in these traits could be conducted in any environment. Improvements in seed yield components and, putatively, in heat tolerance could be achieved using CRS M-9044-0162. As expected, CRS accessions reduced fiber quality parameters in addition to other agronomic traits, suggesting that improvements for within-boll seed yield components and heat tolerance should be made utilizing a backcross approach. Also observed in this population was a superior hybrid for fiber length and fiber strength from the cross of TAM 94L-25 with PD 6186. This combination could lead to improved fiber length and strength potential in upland cotton.

This thesis presents an evaluation of algorithms for classification of functional MRI data. We evaluated the performance of probabilistic classifiers that use a Gaussian model against a popular non-probabilistic classifier (support vector machine, SVM). A pool of classifiers consisting of linear and quadratic discriminants, linear and non-linear Gaussian Naive Bayes (GNB) classifiers, and linear SVM, was evaluated on several sets of real and simulated fMRI data. Performance was measured using two complimentary metrics: accuracy of classification of fMRI volumes within a subject, and reproducibility of within-subject spatial maps; both metrics were computed using split-half resampling. Regularization parameters of multivariate methods were tuned to optimize the out-of-sample classification and/or within-subject map reproducibility. SVM showed no advantage in classification accuracy over Gaussian classifiers. Performance of SVM was matched by linear discriminant, and at times outperformed by quadratic discriminant or nonlinear GNB. Among all tested methods, linear and quadratic discriminants regularized with principal components analysis (PCA) produced spatial maps with highest within-subject reproducibility. We also demonstrated that the number of principal components that optimizes the performance of linear / quadratic discriminants is sensitive to the mean magnitude, variability and connectivity of simulated active signal. In real fMRI data, this number is correlated with behavioural measures of post-stroke recovery , and, in a separate study, with behavioural measures of self-control. Using the data from a study of cognitive aspects of aging, we accurately predicted the age group of the subject from within-subject spatial maps created by our pool of classifiers. We examined the cortical areas that showed difference in recruitment in young versus older subjects; this difference was demonstrated to be primarily driven by more prominent recruitment of task-positive network in older subjects. We conclude that linear and quadratic discriminants with PCA regularization are well-suited for fMRI data classification, particularly for within-subject analysis.

In spite of the number of participants in soccer, it would appear that there is no specific physical, motor, anthropometric and sport psychological profile by which soccer players can be evaluated to determine whether they comply with the specific requirements of soccer. Therefore, the purpose of this study was to determine which physical, motor performance, anthropometric and sport psychological variables distinguish soccer teams of different participation levels. Fifteen Uniwest (classed as successful), twelve Vaal Triangle Technikon (classed as less successful) and sixteen North-West Sports Academy players (classed as the developmental team) were subjected to a test battery that consisted of 8 physical and motor tests as well as 14 anthropometric measurements. Only two teams (Uniwest and Vaal Triangle Technikon) completed the CSAI-2, AMSSE, ACSI-28 and PVI sport psychological questionnaires. The results of the stepwise forward discriminant analysis showed that isokinetic dorsi and plantarflexion peak torque, together with right hamstring flexibility, agility, muscle mass percentage, speed over 5m and abdominal muscle strength, were the physical, motor performance and anthropometric test variables which significantly (p ≤0.05) and accurately (94.74%) distinguish between soccer teams of different participation levels. The results of the sport psychological variables revealed that goal directedness, concentration, optimal performance under pressure, goal setting, performance motivation and activation control are the variables that have an 86.1 1% success rate in discriminating between successful and less-successful soccer players. In conclusion, although the potential of a physical, motor performance, anthropometric and sport psychological test battery to discriminate accurately between soccer players of different participation levels can not be discounted, it appears that the successful soccer team will not necessarily achieve better test battery results than players of other participation levels. The successful group only obtained significantly better results in 4 variables (speed over 5, 10 and 20m as well as striving for success) when compared to the less successful group, who achieved significantly better results in 16 variables. / Thesis (M.Sc. (Human Movement Science))--North-West University, Potchefstroom Campus, 2005.

This thesis presents an evaluation of algorithms for classification of functional MRI data. We evaluated the performance of probabilistic classifiers that use a Gaussian model against a popular non-probabilistic classifier (support vector machine, SVM). A pool of classifiers consisting of linear and quadratic discriminants, linear and non-linear Gaussian Naive Bayes (GNB) classifiers, and linear SVM, was evaluated on several sets of real and simulated fMRI data. Performance was measured using two complimentary metrics: accuracy of classification of fMRI volumes within a subject, and reproducibility of within-subject spatial maps; both metrics were computed using split-half resampling. Regularization parameters of multivariate methods were tuned to optimize the out-of-sample classification and/or within-subject map reproducibility. SVM showed no advantage in classification accuracy over Gaussian classifiers. Performance of SVM was matched by linear discriminant, and at times outperformed by quadratic discriminant or nonlinear GNB. Among all tested methods, linear and quadratic discriminants regularized with principal components analysis (PCA) produced spatial maps with highest within-subject reproducibility. We also demonstrated that the number of principal components that optimizes the performance of linear / quadratic discriminants is sensitive to the mean magnitude, variability and connectivity of simulated active signal. In real fMRI data, this number is correlated with behavioural measures of post-stroke recovery , and, in a separate study, with behavioural measures of self-control. Using the data from a study of cognitive aspects of aging, we accurately predicted the age group of the subject from within-subject spatial maps created by our pool of classifiers. We examined the cortical areas that showed difference in recruitment in young versus older subjects; this difference was demonstrated to be primarily driven by more prominent recruitment of task-positive network in older subjects. We conclude that linear and quadratic discriminants with PCA regularization are well-suited for fMRI data classification, particularly for within-subject analysis.

No description available.