Data Science Commons^™

Improving Country Conflict And Peace Modeling: Datasets, Imputations, And Hierarchical Clustering, Benjamin D. Leiby

Theses and Dissertations

Many disparate datasets exist that provide country attributes covering political, economic, and social aspects. Unfortunately, this data often does not include all countries nor is the data complete for those countries included, as measured by the dataset’s missingness. This research addresses these dataset shortfalls in predicting country instability by considering country attributes in all aspects as well as in greater thresholds of missingness. First, a structured summary of past research is presented framed by a developed casual taxonomy and functional ontology. Additionally, a novel imputation technique for very large datasets is presented to account for moderate missingness in the expanded …

Three Case Studies Of Using Hybrid Model Machine Learning Techniques In Educational Data Mining To Improve The Classification Accuracies, Sujan Poudyal

Theses and Dissertations

A multitude of data is being produced from the increase in instructional technology, e-learning resources, and online courses. This data could be used by educators to analyze and extract useful information which could be beneficial to both instructors and students. Educational Data Mining (EDM) extracts hidden information from data contained within the educational domain. In data mining, hybrid method is the combination of various machine learning techniques. Through this dissertation, the novel use of machine learning hybrid techniques was explored in EDM using three educational case studies. First, in consideration for the importance of students’ attention, on and off-task data …

Quantifying Aboveground Biomass In A Tropical Forest Using A Lidar Waveform Weighted Allometric Model, Alejandro Rojas

Theses and Dissertations

Our knowledge of the distribution and amount of terrestrial above ground biomass (AGB) has increased using lidar technology. Recent advancements in satellite lidar has enabled global mapping of forest biomass and structure. However, there are large biases in satellite lidar estimates which impacts our understanding of carbon dynamics, particularly in tropical forests.

Ni-Meister et al. (2022) developed a lidar full waveform weighted height-based allometric model which produced very good results in temperate deciduous/conifer forest in the continental US. The purpose of this study was to evaluate this biomass model in an African tropical forest using the Land Vegetation and Ice …

Neural Networks And Stochastic Differential Equations, Stephanie L. Flores

Theses and Dissertations

Influenced by the seminal work, “Physics Informed Neural Networks” by Raissi et al., 2017, there has been a growing interest in solving and parameter estimation of Nonlinear Partial Differential Equations (PDE) with Deep Neural networks in recent years. In fact, this has broadened the pathways and shed light on deep learning of stochastic differential equations (SDE) and stochastic PDE’s (SPDE).In this work, we intend to investigate the current approaches of solving and parameter estimation of the SDE/SPDE with deep neural networks and the possibility of extending them to obtain more accurate/stable solutions with residual systems and/or generative adversarial neural networks. …

Innovative Heuristics To Improve The Latent Dirichlet Allocation Methodology For Textual Analysis And A New Modernized Topic Modeling Approach, Jamie T. Zimmerman

Theses and Dissertations

Natural Language Processing is a complex method of data mining the vast trove of documents created and made available every day. Topic modeling seeks to identify the topics within textual corpora with limited human input into the process to speed analysis. Current topic modeling techniques used in Natural Language Processing have limitations in the pre-processing steps. This dissertation studies topic modeling techniques, those limitations in the pre-processing, and introduces new algorithms to gain improvements from existing topic modeling techniques while being competitive with computational complexity. This research introduces four contributions to the field of Natural Language Processing and topic modeling. …

Impact Of Climate Oscillations/Indices On Hydrological Variables In The Mississippi River Valley Alluvial Aquifer., Meena Raju

Theses and Dissertations

The Mississippi River Valley Alluvial Aquifer (MRVAA) is one of the most productive agricultural regions in the United States. The main objectives of this research are to identify long term trends and change points in hydrological variables (streamflow and rainfall), to assess the relationship between hydrological variables, and to evaluate the influence of global climate indices on hydrological variables. Non-parametric tests, MMK and Pettitt’s tests were used to analyze trend and change points. PCC and Streamflow elasticity analysis were used to analyze the relationship between streamflow and rainfall and the sensitivity of streamflow to rainfall changes. PCC and MLR analysis …

Exploring Technology Advancement Over Time Using Lifespan As The Product Trait And Satellites As The Example Domain, Venkata Jaipal Reddy Batthula

Theses and Dissertations

This research is on trend analysis of average satellite lifetimes. Preliminary research concerned which law (Moore’s Law or Wright’s Law) is better for predicting future satellite lifetimes based on their year of failure. While that work depended on the failure dates of satellites, in this research, using data for the launch dates of satellites, I compare those with their lifetimes to better understand the curves most suitable for determining trends in satellite lifespans and understanding better, based on launch year cohort, the lifetimes of satellites currently in orbit as well as those to be launched in the future. This research …

Telemetry Data Mining For Unmanned Aircraft Systems, Li Yu

Theses and Dissertations

With ever more data becoming available to the US Air Force, it is vital to develop effective methods to leverage this strategic asset. Machine learning (ML) techniques present a means of meeting this challenge, as these tools have demonstrated successful use in commercial applications. For this research, three ML methods were applied to a unmanned aircraft system (UAS) telemetry dataset with the aim of extracting useful insight related to phases of flight. It was shown that ML provides an advantage in exploratory data analysis and as well as classification of phases. Neural network models demonstrated the best performance with over …

Leveraging Machine Learning For Large Scale Analysis Of Publicly-Available Data For Gnss Interference Events, David K. Stamper

Theses and Dissertations

This research documents architecture and implementation of an enhanced interference detection and classification analysis system, using both a database and storage solution utilizing machine learning algorithms to detect changes in Carrier-to-Noise strength over multiple GNSS sites. The system uses publicly-available government supported receivers to detect interference, and built using FOSS packaged as a programming library through Python. Two algorithms are discussed in terms of enhancing interference detection using both non-machine learning and machine learning approaches. Two algorithms are also discussed which are used for classification of events. In addition, an approach to Large Scale data analytics is demonstrated via a …

Generalized Robust Feature Selection, Bradford L. Lott

Theses and Dissertations

Feature selection may be summarized as identifying salient features to a given response. Understanding which features affect the response enables, in the future, only collecting consequential data; hence, the feature selection algorithm may lead to saving effort spent collecting data, storage resources, as well as computational resources for making predictions. We propose a generalized approach to select the salient features of data sets. Our approach may also be applied to unsupervised datasets to understand which data streams provide unique information. We contend our approach identifies salient features robust to the sub-sequent predictive model applied. The proposed algorithm considers all provided …

Constructing Prediction Intervals With Neural Networks: An Empirical Evaluation Of Bootstrapping And Conformal Inference Methods, Alexander N. Contarino

Theses and Dissertations

Artificial neural networks (ANNs) are popular tools for accomplishing many machine learning tasks, including predicting continuous outcomes. However, the general lack of confidence measures provided with ANN predictions limit their applicability, especially in military settings where accuracy is paramount. Supplementing point predictions with prediction intervals (PIs) is common for other learning algorithms, but the complex structure and training of ANNs renders constructing PIs difficult. This work provides the network design choices and inferential methods for creating better performing PIs with ANNs to enable their adaptation for military use. A two-step experiment is executed across 11 datasets, including an imaged-based dataset. …

Transition Metal Phosphides For High Performance Electrochemical Energy Storage Devices, Amina Saleh

Theses and Dissertations

Electrochemical energy storage technologies are nowadays playing a leading role in the global effort to address the energy challenges. A lot of attention has been devoted to designing hybrid devices known as supercapatteries which combine the merits of supercapacitors (high power density) and rechargeable batteries (high energy density). Transition metal phosphides (TMP) are a rising star for supercapattery anode materials thanks to their high conductivity, metalloid characteristics, and kinetic favorability for fast electron transport. Herein, new TMP-based materials were synthesized for use as supercapattery positive electrodes, via a multifaceted approach to yield devices enjoying concurrently high power and energy densities. …

A Study On Developing Novel Methods For Relation Extraction, Darshini Mahendran

Theses and Dissertations

Relation Extraction (RE) is a task of Natural Language Processing (NLP) to detect and classify the relations between two entities. Relation extraction in the biomedical and scientific literature domain is challenging as text can contain multiple pairs of entities in the same instance. During the course of this research, we developed an RE framework (RelEx), which consists of five main RE paradigms: rule-based, machine learning-based, Convolutional Neural Network (CNN)-based, Bidirectional Encoder Representations from Transformers (BERT)-based, and Graph Convolutional Networks (GCNs)-based approaches. RelEx's rule-based approach uses co-location information of the entities to determine whether a relation exists between a selected entity …

Universal Design In Bci: Deep Learning Approaches For Adaptive Speech Brain-Computer Interfaces, Srdjan Lesaja

Theses and Dissertations

In the last two decades, there have been many breakthrough advancements in non-invasive and invasive brain-computer interface (BCI) systems. However, the majority of BCI model designs still follow a paradigm whereby neural signals are preprocessed and task-related features extracted using static, and generally customized, data-independent designs. Such BCI designs commonly optimize narrow task performance over generalizability, adaptability, and robustness, which is not well suited to meeting individual user needs. If one day BCIs are to be capable of decoding our higher-order cognitive commands and conceptual maps, their designs will need to be adaptive architectures that will evolve and grow in …

Temporal Disambiguation Of Relative Temporal Expressions In Clinical Texts Using Temporally Fine-Tuned Contextual Word Embeddings., Amy L. Olex

Theses and Dissertations

Temporal reasoning is the ability to extract and assimilate temporal information to reconstruct a series of events such that they can be reasoned over to answer questions involving time. Temporal reasoning in the clinical domain is challenging due to specialized medical terms and nomenclature, shorthand notation, fragmented text, a variety of writing styles used by different medical units, redundancy of information that has to be reconciled, and an increased number of temporal references as compared to general domain texts. Work in the area of clinical temporal reasoning has progressed, but the current state-of-the-art still has a ways to go before …

Estimating Weighted Panel Sizes For Primary Care Providers: An Assessment Of Clustering And Novel Methods Of Panel Size Estimation On Electronic Medical Records, Martin A. Lavallee

Theses and Dissertations

Primary Care is on the frontlines of healthcare, thus they see the most diverse set of patients. In order to achieve high functioning primary care, a practice must establish empanelment, the pairing of patients to providers. Enumeration of empanelment, or estimating panel sizes, helps ensure that the demands of the patients demand the supply of providers and optimize the balance of primary care resources to improve quality of care. Further we can adjust panel sizes by using patient-level data on healthcare utilization and complexity extracted from the electronic medial record to determine the amount of care or burden of work …

Multi-Modality Automatic Lung Tumor Segmentation Method Using Deep Learning And Radiomics, Siqiu Wang

Theses and Dissertations

Delineation of the tumor volume is the initial and fundamental step in the radiotherapy planning process. The current clinical practice of manual delineation is time-consuming and suffers from observer variability. This work seeks to develop an effective automatic framework to produce clinically usable lung tumor segmentations. First, to facilitate the development and validation of our methodology, an expansive database of planning CTs, diagnostic PETs, and manual tumor segmentations was curated, and an image registration and preprocessing pipeline was established. Then a deep learning neural network was constructed and optimized to utilize dual-modality PET and CT images for lung tumor segmentation. …

Incorporating Ontological Information In Biomedical Entity Linking Of Phrases In Clinical Text, Evan French

Theses and Dissertations

Biomedical Entity Linking (BEL) is the task of mapping spans of text within biomedical documents to normalized, unique identifiers within an ontology. Translational application of BEL on clinical notes has enormous potential for augmenting discretely captured data in electronic health records, but the existing paradigm for evaluating BEL systems developed in academia is not well aligned with real-world use cases. In this work, we demonstrate a proof of concept for incorporating ontological similarity into the training and evaluation of BEL systems to begin to rectify this misalignment. This thesis has two primary components: 1) a comprehensive literature review and 2) …

Computational Analysis Of Drug Targets And Prediction Of Protein-Compound Interactions, Sina Ghadermarzi

Theses and Dissertations

Computational prediction of compound-protein interactions generated a substantial amount of interest in the recent years owing to the importance of the knowledge of these interaction for drug discovery and drug repurposing efforts. Research suggests that the currently known drug targets constitute only a fraction of a complete set of drug targets, limiting our ability to identify suitable targets to develop new drugs or to repurpose current drugs for new diseases. These efforts are further thwarted by our limited knowledge of protein-drug (and more generally protein-compound) interactions, where only a subset of drug targets is typically known for the currently used …

Uncertainty-Aware Deep Learning For Prediction Of Remaining Useful Life Of Mechanical Systems, Samuel J. Cornelius

Theses and Dissertations

Remaining useful life (RUL) prediction is a problem that researchers in the prognostics and health management (PHM) community have been studying for decades. Both physics-based and data-driven methods have been investigated, and in recent years, deep learning has gained significant attention. When sufficiently large and diverse datasets are available, deep neural networks can achieve state-of-the-art performance in RUL prediction for a variety of systems. However, for end users to trust the results of these models, especially as they are integrated into safety-critical systems, RUL prediction uncertainty must be captured. This work explores an approach for estimating both epistemic and heteroscedastic …

Stock Markets Performance During A Pandemic: How Contagious Is Covid-19?, Yara Abushahba

Theses and Dissertations

Background and Motivation: The coronavirus (“COVID-19”) pandemic, the subsequent policies and lockdowns have unarguably led to an unprecedented fluid circumstance worldwide. The panic and fluctuations in the stock markets were unparalleled. It is inarguable that real-time availability of news and social media platforms like Twitter played a vital role in driving the investors’ sentiment during such global shock.

Purpose:The purpose of this thesis is to study how the investor sentiment in relation to COVID-19 pandemic influenced stock markets globally and how stock markets globally are integrated and contagious. We analyze COVID-19 sentiment through the Twitter posts and investigate its …

Estimation Of The Planetary Boundary Layer Height: Part 1: Global Radar Wind Profiler Network Data; Part 2: A Comparison To Ceilometer Data, Holly Josephs

Theses and Dissertations

Two methods for estimating the planetary boundary layer, an algorithm to identify a maximum in the backscatter and a covariance wavelet transform method, are explored and applied to global radar wind profiler network data and ceilometer data respectively. The objective of the study is to establish that the data sources and algorithms can be used to estimate planetary boundary layer heights so that global studies can make use of these estimates. Data from the global network of wind profilers required significant restructuring and quality control in order to be used for the present study. The maximum backscatter identification algorithm was …

Contract Information Extraction Using Machine Learning, Zachary E. Butcher

Theses and Dissertations

The Air Force Sustainment Center assisted by the Data Analytics Resource Team and the Defense Logistics Agency collected four million contracts onto one of the Air Force Research Laboratory’s high power computers. This thesis focuses on the effort to determine if parts are available through those contracts. Some information is extracted using machine learning in combination with natural language processing. Where machine learning methods are unsuccessful or inappropriate, text mining techniques, such as pattern recognition and rules, are used. Upon completion, the information is combined into a Gantt chart for quick evaluation. Only 21% of the contracts have their information …

Deep Learning For Multi-Tissue Cancer Classification Of Gene Expressions, Tarek Khorshed

Theses and Dissertations

We contribute in saving the lives of cancer patients through early detection and diagnosis, since one of the major challenges in cancer treatment is that patients are diagnosed at very late stages when appropriate medical interventions become less effective and full curative treatment is no longer achievable. Cancer classification using gene expressions is extremely challenging given the complexity and high dimensionality of the data. Current classification methods typically rely on samples collected from a single tissue type and perform a prerequisite of gene feature selection to avoid processing the full set of genes. These methods fall short in taking advantage …

Creating A Machine Learning Model For The Prediction Of Refugee Flows, Esther Mead

Theses and Dissertations

The world-wide refugee problem has a long history, but continues to this day, and will unfortunately continue into the foreseeable future. Efforts to adequately anticipate, mitigate and prepare for refugee flows, however, are still lacking. There are many potential causes for refugee flows, but the published research has primarily focused on identifying ways to integrate already existing refugees into the various communities wherein they ultimately reside after having fled their home countries, rather than on the idea of figuring out ways to prevent the situations that initially caused them to flee. The model proposed in this dissertation uses a set …

Statistical Approaches For Estimation And Comparison Of Brain Functional Connectivity, Jifang Zhao

Theses and Dissertations

Drug addiction can lead to many health-related problems and social concerns. Functional connectivity obtained from functional magnetic resonance imaging (fMRI) data promotes a variety of fundamental understandings in such association. Due to its complex correlation structure and large dimensionality, the modeling and analysis of the functional connectivity from neuroimage are challenging. By proposing a spatio-temporal model for multi-subject neuroimage data, we incorporate voxel-level spatio-temporal dependencies of whole-brain measurements to improve the accuracy of statistical inference. To tackle large-scale spatio-temporal neuroimage data, we develop a computationally efficient algorithm to estimate the parameters. Our method is used to identify functional connectivity and …

Information Architecture For A Chemical Modeling Knowledge Graph, Adam R. Luxon

Theses and Dissertations

Machine learning models for chemical property predictions are high dimension design challenges spanning multiple disciplines. Free and open-source software libraries have streamlined the model implementation process, but the design complexity remains. In order better navigate and understand the machine learning design space, model information needs to be organized and contextualized. In this work, instances of chemical property models and their associated parameters were stored in a Neo4j property graph database. Machine learning model instances were created with permutations of dataset, learning algorithm, molecular featurization, data scaling, data splitting, hyperparameters, and hyperparameter optimization techniques. The resulting graph contains over 83,000 nodes …

Reliable And Interpretable Machine Learning For Modeling Physical And Cyber Systems, Daniel L. Marino Lizarazo

Theses and Dissertations

Over the past decade, Machine Learning (ML) research has predominantly focused on building extremely complex models in order to improve predictive performance. The idea was that performance can be improved by adding complexity to the models. This approach proved to be successful in creating models that can approximate highly complex relationships while taking advantage of large datasets. However, this approach led to extremely complex black-box models that lack reliability and are difficult to interpret. By lack of reliability, we specifically refer to the lack of consistent (unpredictable) behavior in situations outside the training data. Lack of interpretability refers to the …

Improving Space Efficiency Of Deep Neural Networks, Aliakbar Panahi

Theses and Dissertations

Language models employ a very large number of trainable parameters. Despite being highly overparameterized, these networks often achieve good out-of-sample test performance on the original task and easily fine-tune to related tasks. Recent observations involving, for example, intrinsic dimension of the objective landscape and the lottery ticket hypothesis, indicate that often training actively involves only a small fraction of the parameter space. Thus, a question remains how large a parameter space needs to be in the first place — the evidence from recent work on model compression, parameter sharing, factorized representations, and knowledge distillation increasingly shows that models can be …

Learning From Multi-Class Imbalanced Big Data With Apache Spark, William C. Sleeman Iv

Theses and Dissertations

With data becoming a new form of currency, its analysis has become a top priority in both academia and industry, furthering advancements in high-performance computing and machine learning. However, these large, real-world datasets come with additional complications such as noise and class overlap. Problems are magnified when with multi-class data is presented, especially since many of the popular algorithms were originally designed for binary data. Another challenge arises when the number of examples are not evenly distributed across all classes in a dataset. This often causes classifiers to favor the majority class over the minority classes, leading to undesirable results …