[Abstract]: Outlier detection is an important research problem in data mining that aims to discover useful abnormal and irregular patterns hidden in large data sets. Most existing outlier detection methods only deal with static data with relatively low dimensionality.Recently, outlier detection for high-dimensional stream data became a new emerging research problem. A key observation that motivates this research is that outliersin high-dimensional data are projected outliers, i.e., they are embedded in lower-dimensional subspaces. Detecting projected outliers from high-dimensional streamdata is a very challenging task for several reasons. First, detecting projected outliers is difficult even for high-dimensional static data. The exhaustive search for the out-lying subspaces where projected outliers are embedded is a NP problem. Second, the algorithms for handling data streams are constrained to take only one pass to process the streaming data with the conditions of space limitation and time criticality. The currently existing methods for outlier detection are found to be ineffective for detecting projected outliers in high-dimensional data streams.In this thesis, we present a new technique, called the Stream Project Outlier deTector (SPOT), which attempts to detect projected outliers in high-dimensionaldata streams. SPOT employs an innovative window-based time model in capturing dynamic statistics from stream data, and a novel data structure containing a set oftop sparse subspaces to detect projected outliers effectively. SPOT also employs a multi-objective genetic algorithm as an effective search method for finding theoutlying subspaces where most projected outliers are embedded. The experimental results demonstrate that SPOT is efficient and effective in detecting projected outliersfor high-dimensional data streams. The main contribution of this thesis is that it provides a backbone in tackling the challenging problem of outlier detection for high-dimensional data streams. SPOT can facilitate the discovery of useful abnormal patterns and can be potentially applied to a variety of high demand applications, such as for sensor network data monitoring, online transaction protection, etc.

Magíster en Gestión de Operaciones. Ingeniero Civil Industrial / En este trabajo se desarrollar una metodología para enfrentar el problema de clustering cuando alguno de los atributos se encuentra incompleto y se va completando en forma dinámica. Y se implementa dicha metodología en un modelo particular. El modelo implementado en este trabajo se basa en el modelo de projected clustering (Proclus) desarrollado por Aggarwal et al. en 1999. Al problema de dinamismo se le agregan las siguientes restricciones: La imposibilidad de imputar los valores faltantes (los que todavía no llegan) al igual que la imposibilidad de marginalizar las las con dichos valores faltantes. Estas restricciones se imponen ya que de lo contrario el problema se puede resolver en fácilmente de forma estática y/o tiene soluciones dinámicas conocidas. Se modificó el modelo de proyected clustering para considerar las restricciones impuestas al igual que implementar el dinamismo buscado. Para evaluar el modelo se generaron datos de forma sintética (95000 filas), con diferentes instancias en las que se buscan generar distintos escenarios donde la estructura de los clusters cambia a medida que los nuevos datos llegan. La generación sintética permitió evaluar los resultados y observar la evolución en la detección de las dimensiones y los clusters. Dado el modelo base escogido dicha modificación manifiesta alguna de sus mismas limitaciones, como es el caso de necesitar un número elevado de dimensiones. Los resultados entregados por la implementación del modelo fueron satisfactorios. Encontrando las soluciones esperadas después de un número razonable de iteraciones y realizado las operaciones en un tiempo menor que la aplicación estática del modelo tras la llegada de cada lote de datos. De igual forma se generó una medida para analizar y/o detectar los cambios en la estructura de los clusters a medida que llegan los datos de la nueva columna. Finalmente, en relación a los objetivos planteados en este trabajo, se puede concluir que el modelo desarrollado logra cumplir con los objetivos planteados, logrando desarrollar un modelo y metodológica que enfrente en forma efectiva el problema antes descrito al igual que el aplicarlo a datos simulados y analizar dichos resultados.

The current study examined the influence that perceived parenting, psychopathology, and the environment have on the development of projected parenting styles (defined for the study as the way participants predict they will parent when the opportunity arises) in college students. Overall, participants (N = 412) report that they will adopt a style of projected parenting that is similar to how they perceive their parents’ parenting. One exception is that participants of overprotective parents tended to project utilizing less overprotection, perhaps a sign of rejection for the control that was placed on them by their parents. Perceived paternal parenting was mediated by parental psychopathology, and surprisingly, perceived maternal psychopathology was found to be positively associated with positive projected parenting. Participants’ own psychopathology had no impact on projected parenting when examined simultaneously with the other variables.

The master’s thesis is focused on the draft of a financial plan for a real company for four future periods. The first part of thesis is dealing with theoretical aspects, which are necessary to know for setting up a financial plan. This part is followed by a practical part, which includes presentation of the company, its contemporary state’s and its business environment’s analysis. In the end financial plan is proposed in two variants.

This work was motivated by the well-known question: "Does there exist a nondesarguesian projective plane of prime order?" For a prime p < 11, there is only the pappian plane of order p. Hence, such planes are indeed desarguesian. Thus, it is of interest to examine whether there are non-desarguesian planes of order 11. A suggestion by Ascher Wagner in 1985 was made to Spyros S. Magliveras: "Begin with a non-desarguesian plane of order pk, k > 1, determine all subplanes of order p up to collineations, and check whether one of these is non-desarguesian." In this manuscript we use a group-theoretic methodology to determine the subplane structures of some non-desarguesian planes. In particular, we determine orbit representatives of all proper Q-subplanes both of a Veblen-Wedderburn (VW) plane of order 121 and of the Hughes plane of order 121, under their full collineation groups. In PI, there are 13 orbits of Baer subplanes, all of which are desarguesian, and approximately 3000 orbits of Fano subplanes. In Sigma , there are 8 orbits of Baer subplanes, all of which are desarguesian, 2 orbits of subplanes of order 3, and at most 408; 075 distinct Fano subplanes. In addition to the above results, we also study the subplane structures of some non-desarguesian planes, such as the Hall plane of order 25, the Hughes planes of order 25 and 49, and the Figueora planes of order 27 and 125. A surprising discovery by L. Puccio and M. J. de Resmini was the existence of a plane of order 3 in the Hughes plane of order 25. We generalize this result, showing that there are subplanes of order 3 in the Hughes planes of order q2, where q is a prime power and q 5 (mod 6). Furthermore, we analyze the structure of the full collineation groups of certain Veblen- Wedderburn (VW) planes of orders 25, 49 and 121, and discuss how to recover the planes from their collineation groups. / by Cafer Caliskan. / Thesis (Ph.D.)--Florida Atlantic University, 2010. / Includes bibliography. / Electronic reproduction. Boca Raton, Fla., 2010. Mode of access: World Wide Web.

In modern data and signal acquisition, one main challenge arises from the growing scale of data. The data acquisition devices, however, are often limited by physical and hardware constraints, precluding sampling with the desired rate and precision. It is thus of great interest to reduce the sensing complexity while retaining recovery resolution. And that is why we are interested in reconstructing a signal from a small number of randomly observed time domain samples. The main contributions of this thesis are as follows. First, we consider reconstructing a one-dimensional (1-D) spectrally sparse signal from a small number of randomly observed time-domain samples. The signal of interest is a linear combination of complex sinusoids at R distinct frequencies. The frequencies can assume any continuous values in the normalized frequency domain [0, 1). After converting the spectrally sparse signal into a low-rank Hankel structured matrix completion problem, we propose an efficient feasible point approach, named projected Wirtinger gradient descent (PWGD) algorithm, to efficiently solve this structured matrix completion problem. We give the convergence analysis of our proposed algorithms. We then apply this algorithm to a different formulation of structured matrix recovery: Hankel and Toeplitz mosaic structured matrix. The algorithms provide better recovery performance; and faster signal recovery than existing algorithms including atomic norm minimization (ANM) and Enhanced Matrix Completion (EMaC). We further accelerate our proposed algorithm by a scheme inspired by FISTA. Extensive numerical experiments are provided to illustrate the efficiency of our proposed algorithms. Different from earlier approaches, our algorithm can solve problems of very large dimensions very efficiently. Moreover, we extend our algorithms to signal recovery from noisy samples. Finally, we aim to reconstruct a two-dimension (2-D) spectrally sparse signal from a small size of randomly observed time-domain samples. We extend our algorithms to high-dimensional signal recovery from noisy samples and multivariate frequencies.

The Research Topic and the Need for It: This thesis starts with a review of what the literature says about the importance of corporate image and how it needs to be managed as a strategic asset. However, the problem is there is no model that shows what corporate image comprises and explains how its various components interact with one another so that it can be managed. The result is a number of confusing and contradictory definitions and unproductive discussions about things like whether corporate reputation and corporate image are different or synonymous. In response to this need, it is suggested that corporate image comprises three different image perspectives; namely, Self Image, Projected Image and Perceived Image and that it is only when these are defined separately and regarded holistically that corporate image can be properly defined, understood and managed. Objective: The objective of this research was to develop and test this model using triangulated approaches in which data could be acquired and understood from different sources. To this end questionnaires were developed by document analysis, consultation and discussion. This research was conducted in two very different organisations - a new university campus and a sugar co-operative. In the interests of confidentiality they have been renamed Barton University's Kingsley Campus and Sunstate Sugar Co-operative Association Limited. Data was input into both SPSS and HIPSYS computer programs for the Kingsley Campus research and into HIPSYS for the Sunstate Sugar research. For both research sites the results were discussed with members of all response groups so that accurate interpretations of the data could be made and additional meaningful data acquired. For Kingsley Campus, response groups included all Academic and General Staff of Kingsley Campus for the Self Image and the Projected Image, and for the Perceived Image all Current and Past Students, a representative sample of Grade 12 high school students, advanced diploma students of Kingsley TAFE, and Community Leaders. In all 3,693 questionnaires were distributed and 934 completed questionnaires were processed. For Sunstate Sugar, response groups included all employees for the Self Image separated by Management, Supervisors and Workforce, all Board members and all Employees who interface with the growers (members of the co-operative) for the Projected Image, and all members of the co-operative for the Perceived Image. In all 1830 questionnaires were distributed and 916 completed questionnaires were processed. Findings: The results from the Kingsley Campus research showed that the Projected Image needed to be more effectively targeted at the Grade 12 target group. The results from the Sunstate Sugar research showed that its Perceived Image was affected by its Self Image as well as by its Projected Image and that its Self Image in particular needed to be made more positive. The results from both organisations suggest that a positive corporate Self Image influences the Projected Image and can have as much impact on the Perceived Image as does the Projected Image. In exploring and discussing the results of this research, each organization derived recommendations which led to their developing action plans for the more effective management of their corporate image. These results indicate that the model created has eliminated a gap in the literature, diffused the confusion regarding what corporate image is, and provided a structure and a methodology by which corporate image can be identified and managed. It has been shown to have considerable utility.

A series of sol-gel based photopolymerizable silica glass for holographic storage have been synthesized via a facile chemical design in an effort to overcome the cracking problem incurred during the irradiation stage. The holographic composite material includes a low molecular weight polydimethylsiloxane (PDMS) with end-capped hydroxyl groups, an epoxide-containing coupling agent, a photopolymerizable acrylate monomer, and the sol-gel-derived silica matrix. Inclusion of PDMS provides improved compression stress and strain and toughness over the original unmodified samples, without deterioration on the diffraction efficiency (£b). A plateau value of £b ~ 40 % can be found under a beam power of 5.02 mW. Correlation between the molecular weight of acrylate polymer and £b of the holographic composite material is described and the discrepancies analyzed. The premature saturation of polymerization in the holographic system is attributed to the retarded free radical polymerization within the silica matrix. Minor variation of £b with photoinitiator concentration is observed, indicating that only moderate molecular weight is required for a reasonably high £b. The crack-free mechanism is based on the chemical and physical interactions within the material system. We also investigated the pore size and volume effect for optical properties, especially in studies of diffraction efficiency. With mixing rubber additives, the pore characteristics change via measurement of BET technique. The results indicated that moderate pore size made high diffraction efficiency for porous matrix and some characterizations also were presented. On the other hand, the optical application of this recording medium was described via 3D projected fringes profilometry (PFP) measurement. We recorded coded pattern on medium by employing fiber devices as light source. Using endoscope as image-derived tool, we get double-projected fringe images on tiny object. By PFP technique, a performed retrieved image can be achieved.

A technique using diffractive elements for finding the absolute shape of a large-scale object is proposed. An accurate projected fringe profilometry can be built by applying the holographic technique in this system. The advantages of using the presented technique for projected fringe profilemetry are : (1) a large depth of field ; (2) very low fringe distortion ; (3) a compact design for the measurement system ; (4) high accuracy ; (5) fast measurement speed.

Abstract A projected fringe profilomertry ¡]PFP¡^ using a supercontinuum light illumination for micro-scale measurement is proposed. The supercontinuum light is generated by launching ultra short laser into a highly nonlinear photonic crystal fibers. The supercontinuum light with the following advantage¡G ¡]1¡^ Depth of the field is very large in the projected system. ¡]2¡^No speckle noise in the illumination system. Experiment results has shown that using supercontinuum light is superior to other illumination system This study indicates that the proposed measurement scheme could be applied to 3D shape measurements with large depth variation, especially for semi-conductor devices¡Bmicro electro-mechanical devices and biomedical species.