Digital Commons Network^™

Weather-Related Road Condition Detection Using Co-Developed Machine Learning Methods, Carly Sutter

Electronic Theses & Dissertations (2024 - present)

Transportation agencies make critical operational decisions during hazardous weather events, including assessment of road conditions and resource allocation. In this study, machine learning models are developed to provide additional support for the New York State Department of Transportation (NYSDOT) by automatically classifying road conditions across the state. Convolutional neural networks and random forests are trained on NYSDOT roadside camera images and weather data to predict road surface conditions. This task draws critically on a labeled dataset of 22,000 camera images containing six road surface conditions (severe snow, snow, wet, dry, poor visibility, and obstructed) generated from an iterative hand-labeling process …

The Ellipsoidal Principal Semi-Axis Geometry Of The Solution To An Ivp For A Matrix Diffusion Pde, Brandon M. Fox

Electronic Theses & Dissertations (2024 - present)

We analyze the underlying geometry of the solution to an IVP for a matrix diffusion PDE. We first derive the fundamental solution to the PDE. We then determine the unique solution to the IVP. From there, we begin analyzing its underlying geometry. We first observe that the geometry exhibits an ellipsoidal nature. Furthermore, we observe that it is described by the principal semi-axis geometry of the ellipsoids associated with the solution. This conclusion follows from applying the Principal Axis Theorem to the associated ellipsoids to establish their principal semi-axis geometry, as governed by the eigenstructure of the matrix. This thesis …

Essays On Financial Econometrics And Macro-Financial Forecasting, Zhendong A. Li

Electronic Theses & Dissertations (2024 - present)

The first chapter proposes an innovative supervised learning technique for dimension reduction and forecasting financial and macroeconomic time series in the presence of weak factors that can undermine the effectiveness of traditional Principal Component Analysis (PCA). This approach employs double or multiple supervised learning procedures and is termed ``Supervised Scaled Principal Component Analysis'' (SsPCA). Initially, each predictor is scaled using its predictive slope on the target forecast variable, giving more weight to those with stronger predictive abilities and less to those with weaker ones. Subsequently, utilizing the scaled predictors, we intelligently identify the most informative subset for prediction. This involves …

Improving Modeling Of Corrosion Products In The Primary Circuit Of Light Water Reactors Through The Experimental Determination Of Crud Characteristics, Sri Saravana Konganapuram Narasimma Bharathi

Electronic Theses & Dissertations (2024 - present)

High-temperature water flowing through the coolant circuits in pressurized water reactors (PWRs) creates a harsh environment, deteriorating these materials. This corrosion results in the formation of oxide layer(s) primarily composed of nickel ferrites, iron oxides, nickel oxides, and other nickel-iron-chrome spinel oxides. Being exposed to fluid with high flow rates and pressure, these oxide layers can be eroded, resulting in particulate fouling due to the release of corrosion products (Chalk River Unidentified Deposits, CRUD) into the coolant circuit. When CRUD subsequently deposits on fuel surfaces, it negatively affects the fuel performance (heat transfer and fuel failure); in addition, the particles …

Estimation Of Optimal Treatment Regimes In The Presence Of Missing Data: An Application To Opioid Use Disorder Treatment, Abdullah Albalawi

Electronic Theses & Dissertations (2024 - present)

Opioid use disorder (OUD) remains a major public health challenge, and identifying treatment strategies tailored to individual patients over time is an important methodological and clinical problem. Dynamic treatment regimes (DTRs) provide a framework for such individualized strategies, but conventional estimation methods are often presented under complete-data assumptions. Missingness, especially dropout in multistage studies, can introduce bias and affect estimated treatment rules. Comparatively little work has examined how missing data should be handled in sequential multiple assignment randomized trials (SMARTs), where the timing and ordering of variables are central to estimation.

This dissertation examines how different missing-data approaches affect DTR …

Students For The Exploration And Development Of Space (Seds) Air Brake Subsystem: High-Altitude Autonomous Apogee Modulator System For High-Powered Rockets (Haamshr), Camden J. Maclean, Matthew Wharton, Nick Revis, Colin Guido

Honors Theses and Capstones

The objective of this project was to research, design, fabricate, and analyze an autonomous apogee modulation air brake system for the University of New Hampshire (UNH) Students for Exploration and Development of Space (SEDS) high-powered rocket as competitors in the Friends of Amateur Rocketry – Oxidizers Uninhibited Tournament (FAR-OUT) competition.

This air brake system would be developed with considerations for full autonomy, structural reliability, and repeatable deployment. The design would also be easily integrated into the existing high-powered rocket airframe and mechanically simple to increase reliability and practical functionality. The final design would be evaluated using finite element analysis simulation …

Below The Rows, Beyond The Roots: An Art Exhibition Depicting Agriculture Across The Globe, Maggie Enoch

Honors Theses and Capstones

In Below the Rows, Beyond the Roots, artist Maggie Enoch creates multimedia works inspired by her exposure to diverse agricultural systems and perspectives while studying geography and sustainable agriculture/food systems around the world. By integrating complex histories with the contemporary realities of farming, Maggie paints vivid pictures of the power of food in this five-piece exhibition.

Entry Requirements As Predictors Of Early Academic Success And Student Performance In Undergraduate Occupational Therapy Education, Eileen Du Plooy, Daleen Casteleijn, Denise Franzsen, Gopika Ramkilawon

Journal of Occupational Therapy Education

The selection process for health sciences programs such as occupational therapy is complex, involving a combination of academic and non-academic selection criteria as entry requirements. This study aimed to investigate the predictive value of entry requirement variables on academic performance during the first and second year of an undergraduate occupational therapy program in South Africa. A quantitative, cross-sectional design was utilized, and the sample included 129 first- and second- year occupational therapy students. Data was collected retrospectively through educational data mining of university records and institutional dashboards. The variables analyzed included National Senior Certificate Grade12 (NSC12) grades (Mathematics, Life Sciences, …

Professional Identity Building Scale (Pibs) Development: Measuring Self-Authorship And Dimensions Of Professional Identity In Graduate Students, Anne M. Haskins, Sarah Nielsen, Nicole C. Harris, Adrienne M. Salentiny, Marilyn G. Klug

Journal of Occupational Therapy Education

Grounded professional identity is needed for individuals to function successfully within their professions. The purpose of this study was to develop and test a new instrument intended to measure the professional identity of graduate students. Within a recursive methodological design, we developed a 71-item Professional Identity Building Scale (PIBS) based on a new conceptualized combination of Baxter Magolda’s Epistemological Reflection Model phases and Villanueava and Nadelson’s dimensions of professional identity. We pilot tested 129 occupational therapy graduate students at two sites in two states, adjusted the instrument and then retested the PIBS with data from 347 respondents in the same …

Polysemicolon; Novice Programmers And Java Keywords, Briana C. Bettin

Michigan Tech Publications

Most industrial programming languages leverage the English language for reserved keywords – words which a program compiler recognizes as specific execution commands. The divide between expert and novice programmers showcases an intriguing middle-ground by which the polysemy of many keywords becomes revealed. This essay explores a sampling of the multitude of keyword interpretations that a novice programmer may derive from the Java language’s syntactic style and keywords specifically, and how the polysemy of both “English” and “code” meanings to these terms affects the novice-expert programmer transition.The transition from novice to expert, and the mapping of the career of metaphor to …

Large Aerosol Particles Favor Haze Conditions Through Limitations On Water Budget And Activation Kinetics, Hamed F. Sadi, Ernie Lewis, Kadja Flore Gali, Fan Yang, Jesse Anderson, Suryadev Pratap Singh, Jae Min Yeom, Will Cantrell, Raymond Shaw

Michigan Tech Publications

Experiments in the Pi Convection‐Cloud Chamber conducted by systematically changing the diameter of injected dry aerosol particles while holding the temperature difference constant demonstrate that dry diameter strongly influences the onset of haze‐dominated conditions. Two factors contribute: the system becomes water‐limited, resulting in reduction of supersaturation by growing aerosol particles to the activation diameter; and the activation process becomes kinetically limited. Dry aerosol diameter exerts a strong influence on activation time, with a power‐law exponent of 9/2. Kinetically limited activation occurs when the ratio of the activation and droplet residence times is greater than unity. The findings demonstrate that a …

Predicting Oil Contamination In Water Using Machine Learning On Microbial Compositions, Tong Gao, Isaac Bigcraft, Stephen Techtmann, Issei Nakamura

Michigan Tech Publications

We present a compact and generative machine-learning framework that predicts oil contamination based on microbial community compositions from experimental samples. Our method combines dimensionality reduction with data augmentation and generative modeling to address high-dimensional, non-linear, and sparse microbial data. To reduce the 503-dimensional bacterial composition dataset, we compared three dimensionality reduction techniques: feature importance from random forest, principal component analysis (PCA), and t-distributed stochastic neighbor embedding (t-SNE). Feature importance outperformed PCA and t-SNE, improving predictive performance and identifying microbial species most strongly correlated with oil contamination. To mitigate data scarcity, we augmented the training data using an augmented data neural …