Statistical Models Commons^™

Bias Reduction In Machine Learning Classifiers For Spatiotemporal Analysis Of Coral Reefs Using Remote Sensing Images, Justin J. Gapper

Computational and Data Sciences (PhD) Dissertations

This dissertation is an evaluation of the generalization characteristics of machine learning classifiers as applied to the detection of coral reefs using remote sensing images. Three scientific studies have been conducted as part of this research: 1) Evaluation of Spatial Generalization Characteristics of a Robust Classifier as Applied to Coral Reef Habitats in Remote Islands of the Pacific Ocean 2) Coral Reef Change Detection in Remote Pacific Islands using Support Vector Machine Classifiers 3) A Generalized Machine Learning Classifier for Spatiotemporal Analysis of Coral Reefs in the Red Sea. The aim of this dissertation is to propose and evaluate a …

Leveraging Reviews To Improve User Experience, Anthony Schams, Iram Bakhtiar, Cristina Stanley

SMU Data Science Review

In this paper, we will explore and present a method of finding characteristics of a restaurant using its reviews through machine learning algorithms. We begin by building models to predict the ratings of individual reviews using text and categorical features. This is to examine the efficacy of the algorithms to the task. Both XGBoost and logistic regression will be examined. With these models, our goal is then to identify key phrases in reviews that are correlated with positive and negative experience. Our analysis makes use of review data publicly made available by Yelp. Key bigrams extracted were non-specific to the …

Repairing Landsat Satellite Imagery Using Deep Machine Learning Techniques, Griffin J. Lane, Patricia Goresen, Robert Slater

SMU Data Science Review

Satellite Imagery is one of the most widely used sources to analyze geographic features and environments in the world. The data gathered from satellites are used to quantify many vital problems facing our society, such as the impact of natural disasters, shore erosion, rising water levels, and urban growth rates. In this paper, we construct machine learning and deep learning algorithms for repairing anomalies in the Landsat satellite imagery data which arise for various reasons ranging from cloud obstruction to satellite malfunctions. The accuracy of GIS data is crucial to ensuring the models produced from such data are as close …

Visualization And Machine Learning Techniques For Nasa’S Em-1 Big Data Problem, Antonio P. Garza Iii, Jose Quinonez, Misael Santana, Nibhrat Lohia

SMU Data Science Review

In this paper, we help NASA solve three Exploration Mission-1 (EM-1) challenges: data storage, computation time, and visualization of complex data. NASA is studying one year of trajectory data to determine available launch opportunities (about 90TBs of data). We improve data storage by introducing a cloud-based solution that provides elasticity and server upgrades. This migration will save $120k in infrastructure costs every four years, and potentially avoid schedule slips. Additionally, it increases computational efficiency by 125%. We further enhance computation via machine learning techniques that use the classic orbital elements to predict valid trajectories. Our machine learning model decreases trajectory …

Leveraging Natural Language Processing Applications And Microblogging Platform For Increased Transparency In Crisis Areas, Ernesto Carrera-Ruvalcaba, Johnson Ekedum, Austin Hancock, Ben Brock

SMU Data Science Review

Through microblogging applications, such as Twitter, people actively document their lives even in times of natural disasters such as hurricanes and earthquakes. While first responders and crisis-teams are able to help people who call 911, or arrive at a designated shelter, there are vast amounts of information being exchanged online via Twitter that provide real-time, location-based alerts that are going unnoticed. To effectively use this information, the Tweets must be verified for authenticity and categorized to ensure that the proper authorities can be alerted. In this paper, we create a Crisis Message Corpus from geotagged Tweets occurring during 7 hurricanes …

A Mathematical Investigation On Tumor-Immune Dynamics: The Impact Of Vaccines On The Immune Response, Jonathan Quinonez, Neethi Dasu, Mahboobi Qureshi

Rowan-Virtua Research Day

Mathematical models analyzing tumor-immune interactions provide a framework by which to address specific scenarios in regard to tumor-immune dynamics. Important aspects of tumor-immune surveillance to consider is the elimination of tumor cells from a host’s cell-mediated immunity as well as the implications of vaccines derived from synthetic antigen. In present studies, our mathematical model examined the role of synthetic antigen to the strength of the immune system. The constructed model takes into account accepted knowledge of immune function as well as prior work done by de Pillis et al. All equations describing tumor-immune growth, antigen presentation, immune response, and interaction …

Do Metabolic Networks Follow A Power Law? A Psamm Analysis, Ryan Geib, Lubos Thoma, Ying Zhang

Senior Honors Projects

Inspired by the landmark paper “Emergence of Scaling in Random Networks” by Barabási and Albert, the field of network science has focused heavily on the power law distribution in recent years. This distribution has been used to model everything from the popularity of sites on the World Wide Web to the number of citations received on a scientific paper. The feature of this distribution is highlighted by the fact that many nodes (websites or papers) have few connections (internet links or citations) while few “hubs” are connected to many nodes. These properties lead to two very important observed effects: the …

Predictive Distributions Via Filtered Historical Simulation For Financial Risk Management, Tyson Clark

All Graduate Plan B and other Reports, Spring 1920 to Spring 2023

Filtered historical simulation with an underlying GARCH process can be used as a valuable tool in VaR analysis, as it derives risk estimates that are sensitive to the distributional properties of the historical data of the produced predictive density. I examine the applications to risk analysis that filtered historical simulation can provide, as well as an interpretation of the predictive density as a poor man’s Bayesian posterior distribution. The predictive density allows us to make associated probabilistic statements regarding the results for VaR analysis, giving greater measurement of risk and the ability to maintain the optimal level of risk per …

A Bayesian Framework For Estimating Seismic Wave Arrival Time, Hua Zhong

Graduate Theses and Dissertations

Because earthquakes have a large impact on human society, statistical methods for better studying earthquakes are required. One characteristic of earthquakes is the arrival time of seismic waves at a seismic signal sensor. Once we can estimate the earthquake arrival time accurately, the earthquake location can be triangulated, and assistance can be sent to that area correctly. This study presents a Bayesian framework to predict the arrival time of seismic waves with associated uncertainty. We use a change point framework to model the different conditions before and after the seismic wave arrives. To evaluate the performance of the model, we …

Comparing Elo, Glicko, Irt, And Bayesian Irt Statistical Models For Educational And Gaming Data, Breanna Morrison

Graduate Theses and Dissertations

Statistical models used for estimating skill or ability levels often vary by field, however their underlying mathematical models can be very similar. Differences in the underlying models can be due to the need to accommodate data with different underlying formats and structure. As the models from varying fields increase in complexity, their ability to be applied to different types of data may have the ability to increase. Models that are applied to educational or psychological data have advanced to accommodate a wide range of data formats, including increased estimation accuracy with sparsely populated data matrices. Conversely, the field of online …

Effects Of Perioperative Hyperglycemia In Patients With Diabetes Compared To Patients Without Diabetes: A Retrospective Study Of Treatment And Outcomes, Matthew Anderson

Capstone Experience: Master of Public Health

The main goal of this project was to examine the differences in perioperative hyperglycemia treatment received by patients with a diagnosis of diabetes mellitus (DM) and patients without a diagnosis of diabetes (NDM); and how these treatment differences can affect the length of hospital stay. Studies have revealed that, when comparing DM and NDM patients with the same degree of perioperative hyperglycemia, NDM patients suffer worse outcomes. It has been suggested in previous research that this may be because NDM patients receive treatment that does not measure up to the standard of care treatment that DM patients receive. In this …

Deep Neural Network Architectures For Music Genre Classification, Kai Middlebrook, Shyam Sudhakaran, Kunal Sonar, David Guy Brizan

Creative Activity and Research Day - CARD

With the recent advancements in technology, many tasks in fields such as computer vision, natural language processing, and signal processing have been solved using deep learning architectures. In the audio domain, these architectures have been used to learn musical features of songs to predict: moods, genres, and instruments. In the case of genre classification, deep learning models were applied to popular datasets--which are explicitly chosen to represent their genres--and achieved state-of-the-art results. However, these results have not been reproduced on less refined datasets. To this end, we introduce an un-curated dataset which contains genre labels and 30-second audio previews for …

A Data-Driven Approach For Modeling Agents, Hamdi Kavak

Computational Modeling & Simulation Engineering Theses & Dissertations

Agents are commonly created on a set of simple rules driven by theories, hypotheses, and assumptions. Such modeling premise has limited use of real-world data and is challenged when modeling real-world systems due to the lack of empirical grounding. Simultaneously, the last decade has witnessed the production and availability of large-scale data from various sensors that carry behavioral signals. These data sources have the potential to change the way we create agent-based models; from simple rules to driven by data. Despite this opportunity, the literature has neglected to offer a modeling approach to generate granular agent behaviors from data, creating …

Assessment And Correction Of Lidar-Derived Dems In The Coastal Marshes Of Louisiana, William M. Lauve

LSU Master's Theses

The onset of airborne light detection and ranging (lidar) has resulted in expansive, precise digital elevation models (DEMs). DEMs are essential for modeling complex systems, such as the coastal land margin of Louisiana. They are used for many applications (e.g. tide, storm surge, and ecological modeling) and by diverse groups (e.g. state and federal agencies, NGOs, and academia). However, in a marsh environment, it is difficult for airborne lidar to produce accurate bare-earth measurements and even accurate elevations are rarely verified by ground truth data. The accuracy of lidar in marshes is limited by the sensor’s resolution …

Unified Methods For Feature Selection In Large-Scale Genomic Studies With Censored Survival Outcomes, Lauren Spirko-Burns, Karthik Devarajan

COBRA Preprint Series

One of the major goals in large-scale genomic studies is to identify genes with a prognostic impact on time-to-event outcomes which provide insight into the disease's process. With rapid developments in high-throughput genomic technologies in the past two decades, the scientific community is able to monitor the expression levels of tens of thousands of genes and proteins resulting in enormous data sets where the number of genomic features is far greater than the number of subjects. Methods based on univariate Cox regression are often used to select genomic features related to survival outcome; however, the Cox model assumes proportional hazards …

Non Parametric Test For Testing Exponentiality Against Exponential Better Than Used In Laplace Transform Order, Mahmoud Mansour, M A W Mahmoud Prof.

Basic Science Engineering

In this paper, the test statistic for testing exponentiality against exponential better than used in Laplace transform order (EBUL) based on the Laplace transform technique is proposed. Pitman’s asymptotic efficiency of our test is calculated and compared with other tests. The percentiles of this test are tabulated. The powers of the test are estimated for famously used distributions in aging problems. In the case of censored data, our test is applied and the percentiles are also calculated and tabulated. Finally, real examples in different areas are utilized as practical applications for the proposed test.

Neural Shrubs: Using Neural Networks To Improve Decision Trees, Kyle Caudle, Randy Hoover, Aaron Alphonsus

SDSU Data Science Symposium

Decision trees are a method commonly used in machine learning to either predict a categorical response or a continuous response variable. Once the tree partitions the space, the response is either determined by the majority vote – classification trees, or by averaging the response values – regression trees. This research builds a standard regression tree and then instead of averaging the responses, we train a neural network to determine the response value. We have found that our approach typically increases the predicative capability of the decision tree. We have 2 demonstrations of this approach that we wish to present as …

Predicting Unplanned Medical Visits Among Patients With Diabetes Using Machine Learning, Arielle Selya, Eric L. Johnson

SDSU Data Science Symposium

Diabetes poses a variety of medical complications to patients, resulting in a high rate of unplanned medical visits, which are costly to patients and healthcare providers alike. However, unplanned medical visits by their nature are very difficult to predict. The current project draws upon electronic health records (EMR’s) of adult patients with diabetes who received care at Sanford Health between 2014 and 2017. Various machine learning methods were used to predict which patients have had an unplanned medical visit based on a variety of EMR variables (age, BMI, blood pressure, # of prescriptions, # of diagnoses on problem list, A1C, …

Application Of A Hybrid Statistical–Dynamical System To Seasonal Prediction Of North American Temperature And Precipitation, Sarah Strazzo, Dan C. Collins, Andrew Schepen, Q. J. Wang, Emily Becker, Liweli Jia

Publications

Recent research demonstrates that dynamical models sometimes fail to represent observed teleconnection patterns associated with predictable modes of climate variability. As a result, model forecast skill may be reduced. We address this gap in skill through the application of a Bayesian postprocessing technique—the calibration, bridging, and merging (CBaM) method—which previously has been shown to improve probabilistic seasonal forecast skill over Australia. Calibration models developed from dynamical model reforecasts and observations are employed to statistically correct dynamical model forecasts. Bridging models use dynamical model forecasts of relevant climate modes (e.g., ENSO) as predictors of remote temperature and precipitation. Bridging and calibration …

An Evaluation Of Training Size Impact On Validation Accuracy For Optimized Convolutional Neural Networks, Jostein Barry-Straume, Adam Tschannen, Daniel W. Engels, Edward Fine

SMU Data Science Review

In this paper, we present an evaluation of training size impact on validation accuracy for an optimized Convolutional Neural Network (CNN). CNNs are currently the state-of-the-art architecture for object classification tasks. We used Amazon’s machine learning ecosystem to train and test 648 models to find the optimal hyperparameters with which to apply a CNN towards the Fashion-MNIST (Mixed National Institute of Standards and Technology) dataset. We were able to realize a validation accuracy of 90% by using only 40% of the original data. We found that hidden layers appear to have had zero impact on validation accuracy, whereas the neural …

Political Profiling Using Feature Engineering And Nlp, Chiranjeevi Mallavarapu, Ramya Mandava, Sabitri Kc, Ginger M. Holt

SMU Data Science Review

Public surveys are predominantly used when forecasting election outcomes. While the approach has had significant successes, the surveys have had their failures as well, especially when it comes to accuracy and reliability. As a result, it becomes challenging for political parties to spend their campaign budgets in a manner that facilitates the growth of a favorable and verifiable public opinion. Consequently, it is critical that a more accurate methodology to predict election outcome is developed. In this paper, we present an evaluation of the impact of utilizing dynamic public data on predicting the outcome of elections. Our model yielded a …

Pedestrian Safety -- Fundamental To A Walkable City, Joshua Herrera, Patrick Mcdevitt, Preeti Swaminathan, Raghuram Srinivas

SMU Data Science Review

In this paper, we present a method to identify urban areas with a higher likelihood of pedestrian safety related events. Pedestrian safety related events are pedestrian-vehicle interactions that result in fatalities, injuries, accidents without injury, or near--misses between pedestrians and vehicles. To develop a solution to this problem of identifying likely event locations, we assemble data, primarily from the City of Cincinnati and Hamilton County, that include safety reports from a five year period, geographic information for these events, citizen survey of pedestrian reported concerns, non-emergency requests for service for any cause in the city, property values and public transportation …

Improving Vix Futures Forecasts Using Machine Learning Methods, James Hosker, Slobodan Djurdjevic, Hieu Nguyen, Robert Slater

SMU Data Science Review

The problem of forecasting market volatility is a difficult task for most fund managers. Volatility forecasts are used for risk management, alpha (risk) trading, and the reduction of trading friction. Improving the forecasts of future market volatility assists fund managers in adding or reducing risk in their portfolios as well as in increasing hedges to protect their portfolios in anticipation of a market sell-off event. Our analysis compares three existing financial models that forecast future market volatility using the Chicago Board Options Exchange Volatility Index (VIX) to six machine/deep learning supervised regression methods. This analysis determines which models provide best …

Missing Data Augmentation For Bayesian Multiplex Ergms, Robert Krause, Alberto Caimo

Conference papers

In this paper we present an estimation algorithm for Bayesian multiplex exponential random graphs (BmERGMs) under missing net- work data. Social actors are often connected with more than one type of relation, thus forming a multiplex network. It is important to consider these multiplex structures simultaneously when analyzing a multiplex network. The importance of proper models of multiplex network structures is even more pronounced under the issue of missing network data. The proposed algorithm is able to estimate BmERGMs under missing data and can be used to obtain proper multiple imputations for multiplex network structures. It is an extension of …

Controlling For Confounding Via Propensity Score Methods Can Result In Biased Estimation Of The Conditional Auc: A Simulation Study, Hadiza I. Galadima, Donna K. Mcclish

Community & Environmental Health Faculty Publications

In the medical literature, there has been an increased interest in evaluating association between exposure and outcomes using nonrandomized observational studies. However, because assignments to exposure are not random in observational studies, comparisons of outcomes between exposed and nonexposed subjects must account for the effect of confounders. Propensity score methods have been widely used to control for confounding, when estimating exposure effect. Previous studies have shown that conditioning on the propensity score results in biased estimation of conditional odds ratio and hazard ratio. However, research is lacking on the performance of propensity score methods for covariate adjustment when estimating the …

Package Development, Jason Klaassen, Randall Pruim

Summer Research

Project MOSAIC maintains several R packages that can be used by any R users. These users can suggest improvements and request new features. In addition, changes to dependency packages and the creation of new packages can require internal changes to the MOSAIC suite of packages. Unit testing is important to make sure that new features work as designed and that updates to packages do not break old behavior.

The main projects I worked on were:

• The mosaic package (updates and unit tests)
• The leaflethex package (new package)
• Lock5WithR Textbook Companion created with bookdown (revise and reformat)

The Use Of 3-D Highway Differential Geometry In Crash Prediction Modeling, Kiriakos Amiridis

Theses and Dissertations--Civil Engineering

The objective of this research is to evaluate and introduce a new methodology regarding rural highway safety. Current practices rely on crash prediction models that utilize specific explanatory variables, whereas the depository of knowledge for past research is the Highway Safety Manual (HSM). Most of the prediction models in the HSM identify the effect of individual geometric elements on crash occurrence and consider their combination in a multiplicative manner, where each effect is multiplied with others to determine their combined influence. The concepts of 3-dimesnional (3-D) representation of the roadway surface have also been explored in the past aiming to …

Essays On Mixture Models, Trevor R. Camper

College of Graduate Studies: Theses & Dissertations

When considering statistical scenarios where one can sample from populations that are not of interest for the purposes of a study, bivariate mixture models can be used to study the effect that this missampling can have on parameter estimation. In this thesis, we will examine the behavior that bivariate mixture models have on two statistical constructs: Cronbach's alpha \cite{C51}, and Spearman's rho \cite{S04}. Chapter 1 will introduce notions of mixture models and the definition of bias under mixture models which will serve as the central concept of this thesis. Chapter 2 will investigate a particular psychometric issue known as insufficient …

Some New Generalized Distribution Via Lindley-Weibuli And Lindley-Log-Logistic Distributions With Applications, Soliu A. Raheem

College of Graduate Studies: Theses & Dissertations

In this thesis, new generalized distributions, namely Beta Lindley-Log-Logistic (BLLLoG) distribution, Marshall-Olkin Lindley-Weibull (MOLW) distribution, and Gamma LindleyWeibull (GLW) distribution as well as related sub-distributions are proposed. Series expansion of the densities are obtained. Statistical properties of these distributions, including hazard function, reverse hazard function, moments, reliability, quantile function, mean deviations, Bonferroni and Lorenz curves, entropy and Fisher information are derived. Method of maximum likelihood is used to estimate the parameters of the new distributions. Monte Carlo simulation is employed to examine the performance of the proposed distributions. Applications of the generalized distributions to real lifetime data are presented to …

Variable Selection In Accelerated Failure Time (Aft) Frailty Models: An Application Of Penalized Quasi-Likelihood, Sarbesh R. Pandeya

College of Graduate Studies: Theses & Dissertations

Variable selection is one of the standard ways of selecting models in large scale datasets. It has applications in many fields of research study, especially in large multi-center clinical trials. One of the prominent methods in variable selection is the penalized likelihood, which is both consistent and efficient. However, the penalized selection is significantly challenging under the influence of random (frailty) covariates. It is even more complicated when there is involvement of censoring as it may not have a closed-form solution for the marginal log-likelihood. Therefore, we applied the penalized quasi-likelihood (PQL) approach that approximates the solution for such a …