Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network™

Open Access. Powered by Scholars. Published by Universities.®

2016

Discipline
Institution
Keyword
Publication
Publication Type
File Type

Articles 1051 - 1080 of 24391

Full-Text Articles in Entire DC Network

A Quantitative Policy Analysis Of Bronx County Public High School Students’ Mathematics Course Completion | A Quantitative Policy Analysis Of Bronx County Public High School Students’ Mathematics Course Completion, Ramon Emilio Fernandez Dec 2016

A Quantitative Policy Analysis Of Bronx County Public High School Students’ Mathematics Course Completion | A Quantitative Policy Analysis Of Bronx County Public High School Students’ Mathematics Course Completion, Ramon Emilio Fernandez

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Education reform remains a work in progress. Research, government, and policy reports emphasize that a high-quality high school mathematics education is key to the future of the nation. Technical and research work in science, technology, engineering, mathematics (STEM), social sciences, and life sciences have been identified as essential requirements to bolster the economic growth, national competitiveness, and security of the United States. The academic preparedness, college aspiration, persistence, graduation, as well as earnings of high school graduates who complete college preparatory and advanced math courses are all positively, strongly, and significantly correlated to their math course completion. Despite various efforts …

Go to article

Evaluation Of Contrast Agents Used In Computed Tomography, Michael Joseph Bonvento Dec 2016

Evaluation Of Contrast Agents Used In Computed Tomography, Michael Joseph Bonvento

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Contrast agents have been routinely employed in radiographic applications for more than 80 years and in computed tomography (CT) for more than 50 years. These agents have high atomic number increasing the photoelectric interaction probability thereby reducing photon intensity projected through the contrast containing structure and improving available image contrast. A wide variety of contrast agents have been examined over the years, however, iodine and barium containing agents make up the vast majority of applications. Other agents are or may become available which may find utility due to reduced toxicity, better characteristics for imaging or dose reduction. This is particularly …

Go to article

Multiscale Particle-Based Modeling Of Mechanotransduction Process In Flow-Induced Platelet Activation Using Dissipative Particle Dynamics And Coarse Grained Molecular Dynamics, Chao Gao Dec 2016

Multiscale Particle-Based Modeling Of Mechanotransduction Process In Flow-Induced Platelet Activation Using Dissipative Particle Dynamics And Coarse Grained Molecular Dynamics, Chao Gao

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Thrombosis in cardiovascular diseases and prosthetic cardiovascular devices can be potentiated by pathological flow patterns that enhance hemostatic responses including platelet activation, aggregation, and adhesion. Platelets upon activation react to pathological shear stresses with complex biochemical and morphological changes, aggregate, and adhere to blood vessels or device surfaces to form thrombi. Computational modeling and simulation are extensively employed to study the shear-induced platelet activation. Numerical simulations of this complex process based on Computational Fluid Dynamics (CFD) treat blood as a continuum and solve the Navier-Stokes equations to resolve the process to μm scales level. Due to the limited scales range, …

Go to article

Diffuse Correlation And Optical Spectroscopies For The Monitoring Of Spinal Cord Hemodynamics, Angela Sofia Kogler Dec 2016

Diffuse Correlation And Optical Spectroscopies For The Monitoring Of Spinal Cord Hemodynamics, Angela Sofia Kogler

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Spinal cord ischemia, caused by a prolonged loss of blood flow to the spinal cord, can occur as a result of direct trauma to the spinal cord or as a complication of major vascular, spine and spinal cord surgery, and surgeries for the stabilization of spinal cord trauma, often resulting in partial or complete paresis/paralysis. Current electrophysiological methods employed to detect spinal cord ischemia, namely somatosensory and motor evoked potentials, are indirect, temporally insensitive, nonspecific, and cumbersome. There is no technology currently available that can directly and immediately detect the onset of spinal cord ischemia, nor provide immediate feedback on …

Go to article

Statistical Image Reconstruction For Low-Dose X-Ray Computed Tomography: Statistical Models And Regularization Strategies, Hao Zhang Dec 2016

Statistical Image Reconstruction For Low-Dose X-Ray Computed Tomography: Statistical Models And Regularization Strategies, Hao Zhang

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Low-dose X-ray computed tomography (CT) imaging is desirable due to the growing concerns about excessive radiation exposure to the patients. However, the reconstructed CT images by the conventional filtered back-projection (FBP) method from the low-dose acquisitions may be severely degraded. Statistical image reconstruction (SIR) methods have shown potential to substantially improve the image quality of low-dose CT as compared to the FBP method. According to the maximum a posteriori (MAP) estimation, the SIR methods can be typically formulated by an objective function consisting of two terms: (1) data-fidelity term modeling the statistics of projection measurements, and (2) regularization term reflecting …

Go to article

Geometric Optimization Problems In Sensor Networks, Gui Benjamin Citovsky Dec 2016

Geometric Optimization Problems In Sensor Networks, Gui Benjamin Citovsky

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

In this thesis, we address a variety of algorithmic problems motivated by applications in sensor networks. In many of these problems we consider that the placement of the sensors is in a general metric space and in all of the problems we consider the case that the sensors lie in the Euclidean plane and exploit geometric properties in order to achieve better results. We introduce the \sinrk\ model which is a generalization of the SINR model. Given a set of sender-receiver requests in the Euclidean plane, the goal is to minimize the number of rounds of scheduling needed to satisfy …

Go to article

Development And Application Of An Integrated Parallel Platform On Short–Read Sequences Assembly | Development And Application Of An Integrated Parallel Platform On Short–Read Sequences Assembly, Fei He Dec 2016

Development And Application Of An Integrated Parallel Platform On Short–Read Sequences Assembly | Development And Application Of An Integrated Parallel Platform On Short–Read Sequences Assembly, Fei He

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Rapid and automated next generation sequencing (NGS) methods have emerged recently and significantly accelerated the research in biological and medical fields. The high-throughput NGS usually generates billions of shorter reads, which poses great bioinformatics challenges on extracting meaningful information from these massive data, one of which is de novo assembly. At the same time, the fast development of massive parallel processing (MPP) systems presents a substantial opportunity for processing larger datasets. Therefore, using supercomputer innovations on NGS research promises a good strategy; however, this application is not straightforward and requires new algorithms and parallel design for efficient implementations. In this …

Go to article

Exploration Of Statistical Learning Strategies And Their Applications On Medical Image Data For Computer-Aided Diagnosis, Yifan Hu Dec 2016

Exploration Of Statistical Learning Strategies And Their Applications On Medical Image Data For Computer-Aided Diagnosis, Yifan Hu

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Machine learning addresses the question of how computer make decisions and predictions automatically through existing experiences and data, which has become an increasingly important topic with the advent of modern data science and automated big data analysis. Several algorithms are widely used in machine learning. However, each classifier, inevitably, has certain inadequacy for which we hope to compensate. To address these issues, this study first introduces the necessary theoretical background and principles for machine learning and those typical classifiers. Based on these classifiers, this paper attempts to (1) use bagging/boosting to improve the simple classifier, and, (2) find some combination …

Go to article

Complexity Estimates And Reductions To Discounting For Total And Average-Reward Markov Decision Processes And Stochastic Games, Jefferson Huang Dec 2016

Complexity Estimates And Reductions To Discounting For Total And Average-Reward Markov Decision Processes And Stochastic Games, Jefferson Huang

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Recently there has been a resurgence of interest in the complexity of algorithms for Markov decision processes (MDPs) and stochastic games. Much of this work was inspired by recent groundbreaking results on the complexity of policy iteration algorithms for MDPs under the Blum-Shub-Smale (BSS) model of computation. In particular, for discounted MDPs with a fixed discount factor, Yinyu Ye showed that the number of arithmetic operations needed by two classic variants of policy iteration can be bounded above by a polynomial in the number of state-action pairs only. A natural question is whether a similar complexity estimate exists for the …

Go to article

Don’T Look Now: The Child In Horror Cinema And Media | Don’T Look Now: The Child In Horror Cinema And Media, Hans Staats Dec 2016

Don’T Look Now: The Child In Horror Cinema And Media | Don’T Look Now: The Child In Horror Cinema And Media, Hans Staats

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

This dissertation examines the definition of the monstrous child in horror cinema and media. Spanning from 1955 to 2009 and beyond, the question of what counts as a monstrous child illuminates a perennial cinematic preoccupation with monstrosity and the relation between the normal and the pathological. Films like The Night of the Hunter (Charles Laughton, 1955), The Bad Seed (Mervyn LeRoy, 1956), Village of the Damned (Wolf Rilla, 1960), The Innocents (Jack Clayton, 1961), Don’t Look Now (Nicolas Roeg, 1973), Profondo rosso/Deep Red (Dario Argento, 1975), Carrie (Brian De Palma, 1976), Halloween (John Carpenter, 1978), Child’s Play (Tom Holland, 1988), …

Go to article

An Isoform-Free Model For Differential Expression Analysis In Rna-Seq Data, Yang Liu Dec 2016

An Isoform-Free Model For Differential Expression Analysis In Rna-Seq Data, Yang Liu

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Next generation sequencing (NGS) technology has been widely used in biomedical research, particularly on those genomics-related studies. One of the NGS applications is high-throughput mRNA sequencing (RNA-seq), which is usually applied to discover alternative splicing events, to evaluate gene expression level and to identify differentially expressed genes. Compared with the traditional microarrays, RNA-seq is more efficient and economical. Currently, many useful software tools have been developed for RNA-seq differential expression (DE) analyses, such as edgeR, DESeq and Cufflinks; however, all these methods either ignore the isoforms of mRNA transcript, or rely on the predefined isoform structures, or depend on the …

Go to article

Efficient Iterative And Multigrid Solvers With Applications, Cao Lu Dec 2016

Efficient Iterative And Multigrid Solvers With Applications, Cao Lu

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Iterative methods are some of the most important techniques in solving large scale linear systems. Compared to direct methods, iterative solvers have the advantage of lower storage cost and better scalability as the problem size increases. Among the methods, multigrid solvers and multigrid preconditioners are often the optimal choices for solving systems that arise from partial differential equations (PDEs). In this dissertation, we introduce several efficient algorithms for various scientific applications. Our first algorithm is a specialized geometric multigrid solver for ill-conditioned systems from Helmholtz equations. Such equations appear in climate models with pure Neumann boundary condition and small wave …

Go to article

An Exploratory Study On Process Representations, Chetan Naik Dec 2016

An Exploratory Study On Process Representations, Chetan Naik

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Knowledge about processes is essential for AI systems to understand and reason about the real world events. And, the systems need some form of semantic representation to perform reasoning. At the simplest level, even knowing which class of entities play key roles can be helpful in recognizing and reasoning about events. For instance, given a description ``a puddle drying in the sun", one can recognize this as an instance of the evaporation process using simple role knowledge which asserts (among other things) that the undergoer is a kind of liquid (the puddle), and the enabler is a heat source (the …

Go to article

Selection On Stability In Food Webs, Jonathan Joseph Borrelli Dec 2016

Selection On Stability In Food Webs, Jonathan Joseph Borrelli

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Whereas much of ecological research has been focused on enumerating the differences among ecological communities, it is equally important to understand their similarities. Food webs exhibit remarkably conserved patterns regardless of the type of environment in which they are found. Evolutionary and ecological processes are able to generate a variety of community configurations, but some of these will have a higher chance of being stable. Selection on these configurations based on their stability properties should lead towards an increased representation of stable structures. Moreover this selective process will operate the same across different environmental contexts. The goal of this dissertation …

Go to article

Education Dynamics In A Developing Country: Evidence From Indonesia, Elif Deniz Sumengen Dec 2016

Education Dynamics In A Developing Country: Evidence From Indonesia, Elif Deniz Sumengen

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

There is an urgent need for upper secondary-level and above educated people in Indonesia. According to a recent report, Indonesian companies cannot fill 50% of their entry level positions. To increase the educational attainment, government has been implementing various polices, such as school construction program, compulsory education and allocating 20% of its budget to education, but inadequate enrollment at upper secondary and tertiary levels and the quality of education still remain as big problems. To shed a light on these urgent and recent problems, I ask four questions: a) What is the effect of school quality on tertiary attainment? b) …

Go to article

Detecting Fraud In Public Procurement, Yajun Wang Dec 2016

Detecting Fraud In Public Procurement, Yajun Wang

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Fraud in public procurement is a big problem in public sector all over the world, and is very difficult to detect in empirical studies. Common fraud schemes include corruption, collusive bidding, failure to provide the required quality, and false statements, etc. In this paper, I employed game theory, machine learning, and statistical methods to detect fraud risk in Federal Procurement Contract Data, and studied the relationship of fraud, competition and contract types. In the first section, I studied a procurement game and found that if the firms' types are close enough to each other, their strategies regarding whether or not …

Go to article

Sequential And Non-Sequential Licensing Of Innovation With Potential Entrants, Chang Zhao Dec 2016

Sequential And Non-Sequential Licensing Of Innovation With Potential Entrants, Chang Zhao

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

This dissertation consists of two essays that study the economic impact of innovations when the buyers are not symmetric. Namely, when potential licensees involves both entrants and incumbent firms. In Chapter 2, a non-sequential licensing approach is analyzed. Licenses in this chapter are sold simultaneously by auction aiming to maximize the revenue of the innovator. The post innovation market structure, the diffusion of the innovation and the incentive to innovate are analyzed and compared with the case where licenses are sold only to incumbent firms and not to entrants. In Chapter 3, a sequential licensing approach is analyzed in a …

Go to article

Mesh Refinement And High-Order Reconstruction For Finite Element Methods On Unstructured Meshes, Xinglin Zhao Dec 2016

Mesh Refinement And High-Order Reconstruction For Finite Element Methods On Unstructured Meshes, Xinglin Zhao

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

In large scale simulations of complex partial differential equations (PDE’s) using finite element methods (FEM), mesh generation, remeshing and linear solver are the most vital steps to obtain accurate solutions. All these areas have been explored quite extensively. We seek to develop an integrated framework for these steps. During simulation it is often desirable to start with a relatively coarse mesh and then refine the mesh accordingly (since in most cases the criteria for mesh resolution is not known a priori). The mesh hierarchy generated from mesh refinement could be utilized by efficient linear solvers like geometric multigrid methods (GMG), …

Go to article

Optimization Of Cips Based Opto-Electronic Gas Detectors. Methane Detector., William Cheng Dec 2016

Optimization Of Cips Based Opto-Electronic Gas Detectors. Methane Detector., William Cheng

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

The infrared molecular absorption spectra of certain gases are used for the spectroscopic detection of the presence or concentration of gas. Various and unique techniques utilizing this spectrum have been employed to improve detection, each with its own merits. CIPS (Correlated interference polarization spectroscopy) is unique in how it provides high sensitivity along with high selectivity. The work presented builds on the achievements of CIPS as it was developed by BAH Holdings and its members. This Dissertation reports on modelling of CIPS and its constituents such as the electro-optical modulator. The development of the generator used in this system was …

Go to article

Analog Circuit Design Knowledge Mining And Circuit Causal Information Modeling, Fanshu Jiao Dec 2016

Analog Circuit Design Knowledge Mining And Circuit Causal Information Modeling, Fanshu Jiao

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

This thesis proposes novel approaches for analog circuit design knowledge mining and circuit causal information modeling. In particular, knowledge mining discovers and decomposes analog circuit design knowledge into three components: (1) a conceptual hierarchy for a group of circuit topologies, (2) circuits' performance capabilities (including trade-offs and bottlenecks), and (3) circuits' design causal reasoning strategies. Causal reasoning strategies lead to the development of reasoning-based topology synthesis and design verification, thus bring new perspective to existing approaches. Extended from performance capabilities, the thesis proposes circuit causal information modeling, which models relations of parameters deciding circuit performance attributes and coupling with other …

Go to article

Enhancing Power And Signal Integrity In Three-Dimensional Integrated Circuits, Hailang Wang Dec 2016

Enhancing Power And Signal Integrity In Three-Dimensional Integrated Circuits, Hailang Wang

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Three-dimensional (3D) integration has emerged as an enabling technology for integrated circuits (ICs) in the interconnect-centric design era, where the interconnects have become a bottleneck for the overall system performance. With 3D integration technology, multiple planar dies are stacked vertically while the communication among different dies is achieved by low impedance vertical connections such as through silicon vias (TSVs) or monolithic inter-tier vias (MIVs). Due to the unique characteristics of 3D ICs, various challenges exist in the fabrication, design and testing of 3D integrated systems. The research work proposed in this dissertation is focused on 3D design methodologies with emphasis …

Go to article

Atomic Substitutions In Synthetic Apatite; Insights From Solid-State Nmr Spectroscopy, John Vaughn Dec 2016

Atomic Substitutions In Synthetic Apatite; Insights From Solid-State Nmr Spectroscopy, John Vaughn

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Apatite, Ca5(PO4)3X (where X = F, Cl, or OH), is a unique mineral group capable of atomic substitutions for cations and anions of varied size and charge. Accommodation of differing substituents requires some kind of structural adaptation, e.g. new atomic positions, vacancies, or coupled substitutions. These structural adaptations often give rise to important physicochemical properties relevant to a range of scientific disciplines. Examples include volatile trapping during apatite crystallization, substitution for large radionuclides for long-term storage of nuclear fission waste, substitution for fluoride to improve acid resistivity in dental enamel composed dominantly of hydroxylapatite, and the development of novel biomaterials …

Go to article

Spatial Characteristics Of The Low-Latitude Atlantic Multidecadal Variability During The Past Millennium And Evaluation Of Cmip5 Model Simulations, Tingyin Xiao Dec 2016

Spatial Characteristics Of The Low-Latitude Atlantic Multidecadal Variability During The Past Millennium And Evaluation Of Cmip5 Model Simulations, Tingyin Xiao

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Atlantic multidecadal variability (AMV) influences climate of Atlantic coastal continents, including the Atlantic hurricanes, European summer rainfall, Sahelian precipitation, and African dust. Identifying corresponding climate proxies and integrating them with modern instrumental and reanalysis records are important to understand it in the context of future changes caused by human activities. In this study, we used the high-resolution and marine-based Globigerina bulloides abundance data from Cariaco Basin, the 20th Century reanalysis data, as well as other paleoclimate records to investigate the spatial pattern and coherence of the AMV. We then evaluated the ability of climate models in simulating the AMV. From …

Go to article

Quantum Phase Transition And Quantum Entanglement In The Generalized Cluster-Xy Model, Aydin Deger Dec 2016

Quantum Phase Transition And Quantum Entanglement In The Generalized Cluster-Xy Model, Aydin Deger

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

In this work, we give a detailed analytic treatment of one-dimensional anisotropic XY model in the transverse field. We present a multipartite geometric measure of entanglement per site and per block and use it for quantifying global entanglement in many-body systems. We also investigate spontaneous symmetry breaking and Quantum Phase Transition (QPT) in the model. Further, we extend the solution of the XY model to the n-site interaction and diagonalize the Hamiltonian and obtain energy levels and eigenvalues. We also examine Quantum Entanglement and QPT for next-nearest neighbor interaction and halfway interaction. At last, we introduce a Generalized Cluster-XY Hamiltonian …

Go to article

The Explosive Possibilities Of Little Dwarfs: Low-Mach Number Modeling Of Thin Helium Shells On Sub-Chandrasekhar Mass White Dwarfs, Adam Michael Jacobs Dec 2016

The Explosive Possibilities Of Little Dwarfs: Low-Mach Number Modeling Of Thin Helium Shells On Sub-Chandrasekhar Mass White Dwarfs, Adam Michael Jacobs

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

The classic model of type Ia supernovae still taught in many textbooks describes a white dwarf primarily composed of carbon and oxygen accreting from a companion until it nears the critical Chandrasekhar mass, contracts, ignites carbon fusion and explodes. The research community, however, is seeing whatever consensus that may have existed on this model as the dominant channel to normal type Ia’s erode in the face of both observational and theoretical challenges. In my dissertation I present the largest ever suite of three-dimensional models of an alternative type Ia progenitor model: the double detonation model. This model evades the requirement …

Go to article

Investigations In The Crystal Growth And Neutron Scattering Of Superconductors And A Relaxor Ferroelectric, John Schneeloch Dec 2016

Investigations In The Crystal Growth And Neutron Scattering Of Superconductors And A Relaxor Ferroelectric, John Schneeloch

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

In this dissertation, I present research on four materials with properties that are not well understood, and illustrate the many roles inhomogeneity and disorder may play in material properties. First, we investigated materials synthesis and annealing conditions of the proposed topological superconductor CuxBi2Se3, finding that quenching above a minimum temperature was essential for superconductivity. Due to the inhomogeneity of CuxBi2Se3, we suggest that a metastable secondary phase may be responsible for the superconductivity. Second, we performed neutron scattering measurements on samples in the Fe1+yTe1−xSex family of iron-based superconductors, focusing on the anomalous phonon mode recently discovered near Bragg peaks forbidden …

Go to article

The Integration Of Mathematics In Middle School Science: Student And Teacher Impacts Related To Science Achievement And Attitudes Towards Integration, Luisa Mchugh Dec 2016

The Integration Of Mathematics In Middle School Science: Student And Teacher Impacts Related To Science Achievement And Attitudes Towards Integration, Luisa Mchugh

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Contemporary research has suggested that in order for students to compete globally in the 21st century workplace, pedagogy must shift to include the integration of science and mathematics, where teachers effectively incorporate the two disciplines seamlessly. Mathematics facilitates a deeper understanding of science concepts and has been linked to improved student perception of the integration of science and mathematics. Although there is adequate literature to substantiate students’ positive responses to integration in terms of attitudes, there has been little empirical data to support significant academic improvement when both disciplines are taught in an integrated method. This research study, conducted at …

Go to article

Increasing College Students’ Interest And Engagement In Stem: A Comparison Of Strategies For Challenging Stem Stereotypes | Increasing College Students’ Interest And Engagement In Stem: A Comparison Of Strategies For Challenging Stem Stereotypes, Jiyun Elizabeth Shin Dec 2016

Increasing College Students’ Interest And Engagement In Stem: A Comparison Of Strategies For Challenging Stem Stereotypes | Increasing College Students’ Interest And Engagement In Stem: A Comparison Of Strategies For Challenging Stem Stereotypes, Jiyun Elizabeth Shin

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Increasing science, technology, engineering, and mathematics (STEM) graduates has become an important part of the education agenda in the U.S. in recent years. Stereotypes about STEM (i.e. | belief that STEM abilities are innate, and that European American men are best suited for STEM) have been identified as one of the critical factors that may contribute to low recruitment and retention of STEM students. Drawing from the literatures on biological essentialism and role models, this study compared different strategies for challenging STEM stereotypes among undergraduate students in STEM and non-STEM fields. STEM stereotypes were challenged directly with research articles that …

Go to article

Multi-Objective Clustering Analysis, Tingjun Ruan Dec 2016

Multi-Objective Clustering Analysis, Tingjun Ruan

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

Cluster analysis is an important tool for unsupervised learning. It is commonly used for pattern recognition and dimension reduction. Traditional clustering algorithms include hierarchical clustering and k-means clustering, as well as model based approach such as the group trajectory analysis. A major draw-back of the traditional clustering analysis is that it considers only a single objective (dissimilarity measurement) whilst in reality, one usually holds several criteria for the classification. Therefore, in this thesis, we strive to develop novel multiple-objective clustering methods – with a focus on the more approachable dual-objective ones. This thesis consists of two parts. In the first …

Go to article

Advanced Applications Of Generalized Hyperbolic Distributions In Portfolio Allocation And Measuring Diversification, Xiang Shi Dec 2016

Advanced Applications Of Generalized Hyperbolic Distributions In Portfolio Allocation And Measuring Diversification, Xiang Shi

Stony Brook Theses and Dissertations Collection, 2006-2020 (closed to submissions)

This thesis consists of two parts. The first part addresses the parameter estimation and calibration of the Generalized Hyperbolic (GH) distributions. In this part we review the classical expectation maximization (EM) algorithm and factor analysis for the GH distribution. We also propose a simple shrinkage estimator driven from the penalized maximum likelihood. In addition an on-line EM algorithm is implemented to the GH distribution; and its regret for general exponential family can be represented as a mixture of Kullback-Leibler divergence. We compute the Hellinger distance of the joint GH distribution to measure the performances of all the estimators numerically. Empirical …

Go to article

First Prev Next Last