Physical Sciences and Mathematics Commons^™

Machine Learning Applications For Drug Repurposing, Hansaim Lim

Dissertations, Theses, and Capstone Projects

The cost of bringing a drug to market is astounding and the failure rate is intimidating. Drug discovery has been of limited success under the conventional reductionist model of one-drug-one-gene-one-disease paradigm, where a single disease-associated gene is identified and a molecular binder to the specific target is subsequently designed. Under the simplistic paradigm of drug discovery, a drug molecule is assumed to interact only with the intended on-target. However, small molecular drugs often interact with multiple targets, and those off-target interactions are not considered under the conventional paradigm. As a result, drug-induced side effects and adverse reactions are often neglected …

A Semi-Automated Approach To Medical Image Segmentation Using Conditional Random Field Inference, Yu-Chi Hu

Dissertations, Theses, and Capstone Projects

Medical image segmentation plays a crucial role in delivering effective patient care in various diagnostic and treatment modalities. Manual delineation of target volumes and all critical structures is a very tedious and highly time-consuming process and introduce uncertainties of treatment outcomes of patients. Fully automatic methods holds great promise for reducing cost and time, while at the same time improving accuracy and eliminating expert variability, yet there are still great challenges. Legally and ethically, human oversight must be integrated with ”smart tools” favoring a semi-automatic technique which can leverage the best aspects of both human and computer.

In this work …

Valid Time Rdf, Hsien-Tseng Wang

Dissertations, Theses, and Capstone Projects

The Semantic Web aims at building a foundation of semantic-based data models and languages for not only manipulating data and knowledge, but also supporting decision making by machines. Naturally, time-varying data and knowledge are required in Semantic Web applications to incorporate time and further reason about it. However, the original specifications of Resource Description Framework (RDF) and Web Ontology Language (OWL) do not include constructs for handling time-varying data and knowledge. For simplicity, RDF model is confined to binary predicates, hence some form of reification is needed to represent higher-arity predicates. To this date, there are many proposals extending RDF …

Unclonable Secret Keys, Marios Georgiou

Dissertations, Theses, and Capstone Projects

We propose a novel concept of securing cryptographic keys which we call “Unclonable Secret Keys,” where any cryptographic object is modified so that its secret key is an unclonable quantum bit-string whereas all other parameters such as messages, public keys, ciphertexts, signatures, etc., remain classical. We study this model in the authentication and encryption setting giving a plethora of definitions and positive results as well as several applications that are impossible in a purely classical setting.

In the authentication setting, we define the notion of one-shot signatures, a fundamental element in building unclonable keys, where the signing key not only …

Set Operators, Xiaojin Ye

Dissertations, Theses, and Capstone Projects

My research is centered on set operators. These are universally applicable regardless of the internal structure (numeric or non-numeric) of each individual observed datum. In our research, we have developed the theory of set operators to fill holes and gaps in observed data and eliminate paper shred garbage, thereby changing the observed symbolic data set into one whose pattern is closer to the pattern in the underlying population from which the observed data set was sampled with perturbations.

We describe different set operators including increasing operators, decreasing operators, ex- pansive operators, contractive operators, union preserving operators, intersection preserving op- erators, …

Role Of Influence In Complex Networks, Nur Dean

Dissertations, Theses, and Capstone Projects

Game theory is a wide ranging research area; that has attracted researchers from various fields. Scientists have been using game theory to understand the evolution of cooperation in complex networks. However, there is limited research that considers the structure and connectivity patterns in networks, which create heterogeneity among nodes. For example, due to the complex ways most networks are formed, it is common to have some highly “social” nodes, while others are highly isolated. This heterogeneity is measured through metrics referred to as “centrality” of nodes. Thus, the more “social” nodes tend to also have higher centrality.

In this thesis, …

Snow-Albedo Feedback In Northern Alaska: How Vegetation Influences Snowmelt, Lucas C. Reckhaus

Theses and Dissertations

This paper investigates how the snow-albedo feedback mechanism of the arctic is changing in response to rising climate temperatures. Specifically, the interplay of vegetation and snowmelt, and how these two variables can be correlated. This has the potential to refine climate modelling of the spring transition season. Research was conducted at the ecoregion scale in northern Alaska from 2000 to 2020. Each ecoregion is defined by distinct topographic and ecological conditions, allowing for meaningful contrast between the patterns of spring albedo transition across surface conditions and vegetation types. The five most northerly ecoregions of Alaska are chosen as they encompass …

Qwasi: The Quantum Walk Simulator, Warren V. Wilson

Theses and Dissertations

As quantum computing continues to evolve, the ability to design and analyze novel quantum algorithms becomes a necessary focus for research. In many instances, the virtues of quantum algorithms only become evident when compared to their classical counterparts, so a study of the former often begins with a consideration of the latter. This is very much the case with quantum walk algorithms, as the success of random walks and their many, varied applications have inspired much interest in quantum correlates. Unfortunately, finding purely algebraic solutions for quantum walks is an elusive endeavor. At best, and when solvable, they require simple …

New Approaches To Frequent And Incremental Frequent Pattern Mining, Mehmet Bicer

Dissertations, Theses, and Capstone Projects

Data Mining (DM) is a process for extracting interesting patterns from large volumes of data. It is one of the crucial steps in Knowledge Discovery in Databases (KDD). It involves various data mining methods that mainly fall into predictive and descriptive models. Descriptive models look for patterns, rules, relationships and associations within data. One of the descriptive methods is association rule analysis, which represents co-occurrence of items or events. Association rules are commonly used in market basket analysis. An association rule is in the form of X → Y and it shows that X and Y co-occur with a given …

Novel Fast Algorithms For Low Rank Matrix Approximation, John T. Svadlenka

Dissertations, Theses, and Capstone Projects

Recent advances in matrix approximation have seen an emphasis on randomization techniques in which the goal was to create a sketch of an input matrix. This sketch, a random submatrix of an input matrix, having much fewer rows or columns, still preserves its relevant features. In one of such techniques random projections approximate the range of an input matrix. Dimension reduction transforms are obtained by means of multiplication of an input matrix by one or more matrices which can be orthogonal, random, and allowing fast multiplication by a vector. The Subsampled Randomized Hadamard Transform (SRHT) is the most popular among …

Emerging Technologies In Healthcare: Analysis Of Unos Data Through Machine Learning, Reyhan Merekar

Student Theses and Dissertations

The healthcare industry is primed for a massive transformation in the coming decades due to emerging technologies such as Artificial Intelligence (AI) and Machine Learning. With a practical application to the UNOS (United Network of Organ Sharing) database, this Thesis seeks to investigate how Machine Learning and analytic methods may be used to predict one-year heart transplantation outcomes. This study also sought to improve on predictive performances from prior studies by analyzing both Donor and Recipient data. Models built with algorithms such as Stacking and Tree Boosting gave the highest performance, with AUC’s of 0.6810 and 0.6804, respectively. In this …

Robust Neural Machine Translation, Abdul Rafae Khan

Dissertations, Theses, and Capstone Projects

This thesis aims for general robust Neural Machine Translation (NMT) that is agnostic to the test domain. NMT has achieved high quality on benchmarks with closed datasets such as WMT and NIST but can fail when the translation input contains noise due to, for example, mismatched domains or spelling errors. The standard solution is to apply domain adaptation or data augmentation to build a domain-dependent system. However, in real life, the input noise varies in a wide range of domains and types, which is unknown in the training phase. This thesis introduces five general approaches to improve NMT accuracy and …

Multimodal Data Integration For Real-Time Indoor Navigation Using A Smartphone, Yaohua Chang

Dissertations and Theses

We propose an integrated solution of indoor navigation using a smartphone, especially for assisting people with special needs, such as the blind and visually impaired (BVI) individuals. The system consists of three components: hybrid modeling, real-time navigation, and client-server architecture. In the hybrid modeling component, the hybrid model of a building is created region by region and is organized in a graph structure with nodes as destinations and landmarks, and edges as traversal paths between nodes. A Wi-Fi/cellular-data connectivity map, a beacon signal strength map, a 3D visual model (with destinations and landmarks annotated) are collected while a modeler walks …

V-Slam And Sensor Fusion For Ground Robots, Ejup Hoxha

Dissertations and Theses

In underground, underwater and indoor environments, a robot has to rely solely on its on-board sensors to sense and understand its surroundings. This is the main reason why SLAM gained the popularity it has today. In recent years, we have seen excellent improvement on accuracy of localization using cameras and combinations of different sensors, especially camera-IMU (VIO) fusion. Incorporating more sensors leads to improvement of accuracy,but also robustness of SLAM. However, while testing SLAM in our ground robots, we have seen a decrease in performance quality when using the same algorithms on flying vehicles.We have an additional sensor for ground …