Data Science Commons^™

Panda-Plus: Improved Dataset Of Prostate Whole Slide Images From Panda Challenge With Pixel-Level Expert Annotations, Spencer Hopson, Carson Mildon, Corbyn Kubalek, Joshua L. Ebbert, Ryan Vance, Lauren Laverty, Paul Urie, Dennis Della Corte

Faculty Publications

Artificial intelligence (AI)-based prostate cancer detection through whole slide images (WSIs) offers promising potential to address the global pathologist shortage while improving clinical consistency. Digital slides and improving image analysis methods encourage the creation of tools to aid in WSI classification. Despite promising advances, these tools are still limited by available training data. Current publicly available datasets, such as Kaggle's PANDA Challenge, while large in scale, rely on slide-level labels that may introduce noise and limit model reliability. Others contain detailed annotations, but are smaller in size due to manual processing efforts. In this work, we introduce PANDA-PLUS, a 546-image …

Interpretable Machine Learning For Cardiovascular Risk Prediction: Insights From Nhanes Dietary And Health Data, Md Ahiduzzaman, Md Nahid Hasan

Faculty Publications

Background: Cardiovascular diseases (CVD) are one of the leading global causes of death, which requires an accurate early prediction. This study aimed to develop transparent machine learning (ML) models using National Health and Nutrition Examination Survey (NHANES) data from 2017–2023 to predict CVD risk based on dietary and health factors.

Methods: We analyzed data from 12,382 adults (aged 18 and older) from NHANES 2017–2023, including 41 dietary, anthropometric, clinical, and demographic variables. Recursive Feature Elimination (RFE) was used to select an optimal subset of 30 predictors. To address substantial class imbalance in the outcome, we applied the Random Over-Sampling Examples …

From Disruption To Integration: Cryptocurrency Prices, Financial Fluctuations, And Macroeconomy, Zhengyang Chen

Faculty Publications

This paper examines cryptocurrency shock transmission to financial markets and the macroeconomy using a Bayesian structural VAR with Pandemic Priors from 2015 to 2024. By affecting overall risk appetite, cryptocurrency price shocks generate positive financial market spillovers, accounting for 18% of equity and 27% of commodity price fluctuations. Real economic effects are significant in driving investment but remain limited, contributing only 4% to unemployment and 6% to industrial production variance. However, cryptocurrency shocks explain 18% of price-level forecast error variance at long horizons. Narrative analysis reveals sentiment and technology as primary shock drivers. These findings demonstrate cryptocurrency's deep financial system …

Toward Quantifying Interpolation Uncertainty In Set-Line Spacing Hydrographic Surveys, Elias Adediran, Christos Kastrisios, Kim Lowell, Glen Rice, Qi Zhang

Faculty Publications

The oceans remain one of Earth’s last great unknowns, with about 74% still unmapped to modern standards. Consequently, interpolation is employed to create seamless digital bathymetric models (DBMs) from incomplete hydrographic datasets, but this introduces unquantified depth uncertainties. This study aims to estimate and characterize uncertainties arising from set-line spacing hydrographic surveys, which are important for nautical charting, navigational safety, and many other applications. By sampling at different line spacings four complete coverage testbeds that vary in slope and roughness, the study interpolates across entire testbed areas using Spline, Inverse Distance Weighting, and Linear interpolation. The resulting interpolation uncertainties are …

An Integrated Space Test Lexicon: A Taxonomy For The Integrated Test And Evaluation Of Space Systems, Stephen K. Tullino, Andrew S. Keys, Robert A. Bettinger, Amy M. Cox, David R. Jacques

Faculty Publications

The proposed Integrated Space Test Lexicon is intended to amalgamate the numerous definitions of integrated (IT or IT&E), development test (DT or DT&E), and operational test (OT or OT&E) into unified, service-wide definitions, aligned with the Space Test Enterprise Vision. Refining such definitions will help distill the core characteristics of these fundamental test types to first identify space system activities composing what is traditionally known as DT and OT, then to provide a means of how these activities fit into the IT paradigm and support space system development. In forging a common understanding of how DT and OT support space …

Hyperspectral Point Cloud Projection For The Semantic Segmentation Of Multimodal Hyperspectral And Lidar Data With Point Convolution-Based Deep Fusion Neural Networks, Kevin T. Decker, Brett J. Borghetti

Faculty Publications

The fusion of dissimilar data modalities in neural networks presents a significant challenge, particularly in the case of multimodal hyperspectral and lidar data. Hyperspectral data, typically represented as images with potentially hundreds of bands, provide a wealth of spectral information, while lidar data, commonly represented as point clouds with millions of unordered points in 3D space, offer structural information. The complementary nature of these data types presents a unique challenge due to their fundamentally different representations requiring distinct processing methods. In this work, we introduce an alternative hyperspectral data representation in the form of a hyperspectral point cloud (HSPC), which …

Multicollinearity Applied Stepwise Stochastic Imputation: A Large Dataset Imputation Through Correlation‑Based Regression, Benjamin D. Leiby, Darryl K. Ahner

Faculty Publications

This paper presents a stochastic imputation approach for large datasets using a correlation selection methodology when preferred commercial packages struggle to iterate due to numerical problems. A variable range-based guard rail modification is proposed that benefits the convergence rate of data elements while simultaneously providing increased confidence in the plausibility of the imputations. A large country conflict dataset motivates the search to impute missing values well over a common threshold of 20% missingness. The Multicollinearity Applied Stepwise Stochastic imputation methodology (MASS-impute) capitalizes on correlation between variables within the dataset and uses model residuals to estimate unknown values. Examination of the …

Emotion Classification Of Indonesian Tweets Using Bidirectional Lstm, Aaron K. Glenn, Phillip M. Lacasse, Bruce A. Cox

Faculty Publications

Emotion classification can be a powerful tool to derive narratives from social media data. Traditional machine learning models that perform emotion classification on Indonesian Twitter data exist but rely on closed-source features. Recurrent neural networks can meet or exceed the performance of state-of-the-art traditional machine learning techniques using exclusively open-source data and models. Specifically, these results show that recurrent neural network variants can produce more than an 8% gain in accuracy in comparison with logistic regression and SVM techniques and a 15% gain over random forest when using FastText embeddings. This research found a statistical significance in the performance of …

Machine Learning Prediction Of Dod Personal Property Shipment Costs, Tiffany Tucker, Torrey J. Wagner, Paul Auclair, Brent T. Langhals

Faculty Publications

U.S. Department of Defense (DoD) personal property moves account for 15% of all domestic and international moves - accurate prediction of their cost could draw attention to outlier shipments and improve budget planning. In this work 136,140 shipments between 13 personal property shipment hubs from April 2022 through March 2023 with a total cost of $1.6B were analyzed. Shipment cost was predicted using recursive feature elimination on linear regression and XGBoost algorithms, as well as through neural network hyperparameter sweeps. Modeling was repeated after removing 28 features related to shipment hub location and branch of service to examine their influence …

Development Of Advanced Machine Learning Models For Analysis Of Plutonium Surrogate Optical Emission Spectra, Ashwin P. Rao, Phillip R. Jenkins, John D. Auxier Ii, Michael B. Shattan, Anil K. Patnaik

Faculty Publications

This work investigates and applies machine learning paradigms seldom seen in analytical spectroscopy for quantification of gallium in cerium matrices via processing of laser-plasma spectra. Ensemble regressions, support vector machine regressions, Gaussian kernel regressions, and artificial neural network techniques are trained and tested on cerium-gallium pellet spectra. A thorough hyperparameter optimization experiment is conducted initially to determine the best design features for each model. The optimized models are evaluated for sensitivity and precision using the limit of detection (LoD) and root mean-squared error of prediction (RMSEP) metrics, respectively. Gaussian kernel regression yields the superlative predictive model with an RMSEP of …

Monitoring Fine-Scale Forest Health Using Unmanned Aerial Systems (Uas) Multispectral Models, Benjamin T. Fraser, Russell G. Congalton

Faculty Publications

Forest disturbances—driven by pests, pathogens, and discrete events—have led to billions of dollars in lost ecosystem services and management costs. To understand the patterns and severity of these stressors across complex landscapes, there must be an increase in reliable data at scales compatible with management actions. Unmanned aerial systems (UAS or UAV) offer a capable platform for collecting local scale (e.g., individual tree) forestry data. In this study, we evaluate the capability of UAS multispectral imagery and freely available National Agricultural Imagery Program (NAIP) imagery for differentiating coniferous healthy, coniferous stressed, deciduous healthy, deciduous stressed, and degraded individual trees throughout …

Per-Pixel Cloud Cover Classification Of Multispectral Landsat-8 Data, Salome E. Carrasco, Torrey J. Wagner, Brent T. Langhals

Faculty Publications

Random forest and neural network algorithms are applied to identify cloud cover using 10 of the wavelength bands available in Landsat 8 imagery. The methods classify each pixel into 4 different classes: clear, cloud shadow, light cloud, or cloud. The first method is based on a fully connected neural network with ten input neurons, two hidden layers of 8 and 10 neurons respectively, and a single-neuron output for each class. This type of model is considered with and without L2 regularization applied to the kernel weighting. The final model type is a random forest classifier created from an ensemble of …

The Effects Of Individual Differences, Non‐Stationarity, And The Importance Of Data Partitioning Decisions For Training And Testing Of Eeg Cross‐Participant Models, Alexander J. Kamrud, Brett J. Borghetti, Christine M. Schubert Kabban

Faculty Publications

EEG-based deep learning models have trended toward models that are designed to perform classification on any individual (cross-participant models). However, because EEG varies across participants due to non-stationarity and individual differences, certain guidelines must be followed for partitioning data into training, validation, and testing sets, in order for cross-participant models to avoid overestimation of model accuracy. Despite this necessity, the majority of EEG-based cross-participant models have not adopted such guidelines. Furthermore, some data repositories may unwittingly contribute to the problem by providing partitioned test and non-test datasets for reasons such as competition support. In this study, we demonstrate how improper …

Multi-Objective Database Queries In Combined Knapsack And Set Covering Problem Domains, Sean A. Mochocki, Gary B. Lamont, Robert C. Leishman, Kyle J. Kauffman

Faculty Publications

Database queries are one of the most important functions of a relational database. Users are interested in viewing a variety of data representations, and this may vary based on database purpose and the nature of the stored data. The Air Force Institute of Technology has approximately 100 data logs which will be converted to the standardized Scorpion Data Model format. A relational database is designed to house this data and its associated sensor and non-sensor metadata. Deterministic polynomial-time queries were used to test the performance of this schema against two other schemas, with databases of 100 and 1000 logs of …

The Analytics Managers Ultimate Guide For Working With Universities, Robert J. Mcgrath

Faculty Publications

The challenges organizations are having related to finding (and retaining) deep analytical talent did not materialize out of thin air…or overnight. Analytics and Data science – and the role of the analytics professional – has evolved over the last several decades and has been fueled by our ability to capture and process increasingly larger and more complex variations of data and our desire to gain increasingly granular insights to fuel innovation and creativity. While many organizations recognize that a partnership with a university can be a resource to many of these challenges, the best way to start a conversation with …

Photovoltaic System Optimization For An Austere Location Using Time Series Data, Torrey J. Wagner, Eric Lang, Warren Assink, Douglas S. Dudis

Faculty Publications

In this work we test experimental photovoltaic, storage and generator technologies and investigate their potential to meet austere location energy needs. After defining the energy requirements and insolation of a 1,100-person base, we develop a microgrid model and simulation. Cost optimizations were then performed using hourly time-series data to explore the cost and performance trade-space of a PV-battery-generator system. The work highlights the cost of resiliency and the dependencies of optimum system component sizes on duration and the fully burdened cost of fuel.

Tools And Techniques For Computational Reproducibility, Stephen Piccolo, Michael B. Frampton

Faculty Publications

When reporting research findings, scientists document the steps they followed so that others can verify and build upon the research. When those steps have been described in sufficient detail that others can retrace the steps and obtain similar results, the research is said to be reproducible. Computers play a vital role in many research disciplines and present both opportunities and challenges for reproducibility. Computers can be programmed to execute analysis tasks, and those programs can be repeated and shared with others. The deterministic nature of most computer programs means that the same analysis tasks, applied to the same data, will …

Surveying Cost Growth, Michael A. Greiner, Vince Sipple, Edward D. White

Faculty Publications

Cost growth that weapon systems incur throughout their acquisition life cycle concerns those who work in the acquisition environment. One way to reduce the amount of unexpected cost growth is to develop better cost estimates. In attaining better cost estimates though, it is often helpful to understand and account for potential cost drivers. Several cost studies, some of which specifically focus on the aircraft industry, have been performed documenting and investigating these growth factors. Overviews of these various cost growth studies are presented as other tools for the cost estimators and program managers.