Physical Sciences and Mathematics Commons^™

Threshold Free Detection Of Elliptical Landmarks Using Machine Learning, Lifan Zhang

Theses and Dissertations

Elliptical shape detection is widely used in practical applications. Nearly all classical ellipse detection algorithms require some form of threshold, which can be a major cause of detection failure, especially in the challenging case of Moire Phase Tracking (MPT) target images. To meet the challenge, a threshold free detection algorithm for elliptical landmarks is proposed in this thesis. The proposed Aligned Gradient and Unaligned Gradient (AGUG) algorithm is a Support Vector Machine (SVM)-based classification algorithm, original features are extracted from the gradient information corresponding to the sampled pixels. with proper selection of features, the proposed algorithm has a high accuracy …

Improving Version-Aware Word Documents, Alexandre Gustavo Valenca De Azevedo Filho

Theses and Dissertations

Coakley~\textit{et al.} described how they developed Version Aware Word Documents, which is an enhanced document representation that includes a detailed version history that is self-contained and portable. However, they were not able to adopt the unique-ID-based techniques that have been shown to support efficient merging and differencing algorithms.

This thesis describes how it is possible to adapt existing features of MS Word's OOXML representation to provide a system of unique element IDs suitable for those algorithms. This requires taking over Word's Revision Save ID (RSID) system and also defining procedures for specifying ID values for elements that do not support …

Enhanced Version Control For Unconventional Applications, Ahmed Saleh Shatnawi

Theses and Dissertations

The Extensible Markup Language (XML) is widely used to store, retrieve, and share digital documents. Recently, a form of Version Control System has been applied to the language, resulting in Version-Aware XML allowing for enhanced portability and scalability. While Version Control Systems are able to keep track of changes made to documents, we think that there is untapped potential in the technology. In this dissertation, we present novel ways of using Version Control System to enhance the security and performance of existing applications. We present a framework to maintain integrity in offline XML documents and provide non-repudiation security features that …

Utilizing Consumer Health Posts For Pharmacovigilance: Identifying Underlying Factors Associated With Patients’ Attitudes Towards Antidepressants, Maryam Zolnoori

Theses and Dissertations

Non-adherence to antidepressants is a major obstacle to antidepressants therapeutic benefits, resulting in increased risk of relapse, emergency visits, and significant burden on individuals and the healthcare system. Several studies showed that non-adherence is weakly associated with personal and clinical variables, but strongly associated with patients’ beliefs and attitudes towards medications. The traditional methods for identifying the key dimensions of patients’ attitudes towards antidepressants are associated with some methodological limitations, such as concern about confidentiality of personal information. In this study, attempts have been made to address the limitations by utilizing patients’ self report experiences in online healthcare forums to …

Unsupervised Biomedical Named Entity Recognition, Omid Ghiasvand

Theses and Dissertations

Named entity recognition (NER) from text is an important task for several applications, including in the biomedical domain. Supervised machine learning based systems have been the most successful on NER task, however, they require correct annotations in large quantities for training. Annotating text manually is very labor intensive and also needs domain expertise. The purpose of this research is to reduce human annotation effort and to decrease cost of annotation for building NER systems in the biomedical domain. The method developed in this work is based on leveraging the availability of resources like UMLS (Unified Medical Language System), that contain …

Making Substitutions Explicit In Sasylf, Michael David Ariotti

Theses and Dissertations

SASyLF is an interactive proof assistant whose goal is to teach: about type systems,

language meta-theory, and writing proofs in general. This software tool stores user-specified

languages and logics in the dependently-typed LF, and its internal proof structure closely

resembles M2+ . This thesis describes a new usability feature of SASyLF, “where” clauses,

which make explicit previously hidden substitutions that arise through constructs in the proof

code, primarily case analyses. An overview of SASyLF and logical frameworks is given, with

motivating examples. The requirements for “where” clauses are discussed, including a formal

definition of correctness. The feature’s implementation in SASyLF …

Bayesian Methods And Machine Learning For Processing Text And Image Data, Yingying Gu

Theses and Dissertations

Classification/clustering is an important class of unstructured data processing problems. The classification (supervised, semi-supervised and unsupervised) aims to discover the clusters and group the similar data into categories for information organization and knowledge discovery. My work focuses on using the Bayesian methods and machine learning techniques to classify the free-text and image data, and address how to overcome the limitations of the traditional methods. The Bayesian approach provides a way to allow using more variations(numerical or categorical), and estimate the probabilities instead of explicit rules, which will benefit in the ambiguous cases. The MAP(maximum a posterior) estimation is used to …

Automating A 3d Point Matching System For Human Faces, Priya Vashistha

Theses and Dissertations

3D point matching for human faces is opening new possibilities in the fields of face matching, face recognition, face retrieval, biomedical, virtual reality, etc. and is overcoming the limitations of 2D face matching. The purpose of this study is to research and implement an automated 3D point matching system for human faces. This will be added to an existing system implemented for 3D point matching on face models. The current implementation is a manual procedure to find matching between the faces, where a set of landmarks are selected on both sources and target meshes and the faces are registered using …

Analysis Of Bas-Relief Generation Techniques, Zachary Salim Benzaid

Theses and Dissertations

Simplifying the process of generating relief sculptures has been an interesting topic of research in the past decade. A relief is a type of sculpture that does not entirely extend into three-dimensional space. Instead, it has details that are carved into a flat surface, like wood or stone, such that there are slight elevations from the flat plane that define the subject of the sculpture. When viewed orthogonally straight on, a relief can look like a full sculpture or statue in the respect that a full sense of depth from the subject can be perceived. Creating such a model manually …

Analysis Of Bcns And Newhope Key-Exchange Protocols, Seyedamirhossein Hesamian

Theses and Dissertations

Lattice-based cryptographic primitives are believed to offer resilience against attacks by quantum computers. Following increasing interest from both companies and government agencies in building quantum computers, a number of works have proposed instantiations of practical post-quantum key-exchange protocols based on hard problems in lattices, mainly based on the Ring Learning With Errors (R-LWE) problem.

In this work we present an analysis of Ring-LWE based key-exchange mechanisms and compare two implementations of Ring-LWE based key-exchange protocol: BCNS and NewHope. This is important as NewHope protocol implementation outperforms state-of-the art elliptic curve based Diffie-Hellman key-exchange X25519, thus showing that using quantum safe …