Physical Sciences and Mathematics Commons^™

A Comparative Study Of Machine Learning And Deep Learning Models In Binary And Multiclass Classification For Intrusion Detection Systems, Ayesha Alharthi, Meera Alaryani, Sanaa Kaddoura

All Works

Network infrastructure evolution has significantly expanded the attack surface, leading to increasingly complex and sophisticated cybersecurity threats. Traditional rule-based intrusion detection systems (IDS) often fail to detect emerging attack vectors, prompting the need for intelligent, data-driven approaches. This study evaluates and compares the performance of machine learning (ML) and deep learning (DL) models for network intrusion detection. Two publicly available datasets were utilized: a binary-labeled software-defined networking (SDN) dataset and a multiclass industrial control system dataset based on the IEC 60870-5-104 protocol. Preprocessing steps included normalization, label encoding, and a 70:10:20 train-validation-test split. Seven models, Random Forest, Decision Tree, K-Nearest …

An Efficient Detection And Deep Clustering Based Pipeline For Reliable Rodent Ultrasonic Vocalization Analysis, Sabah S. Anis

Theses and Dissertations

Ultrasonic vocalizations (USVs) are critical for understanding rodents' emotional states and social behaviors. However, manual analysis of USVs is time-consuming, subjective, and prone to errors. This thesis presents an automated pipeline that addresses these challenges by performing efficient USV detection and clustering. The proposed approach significantly reduces the time and effort needed to analyze USV data while improving accuracy and reproducibility.

To address this gap, we introduce ContourUSV, a five-step pipeline for USV detection. First, it begins with generating spectrograms from audio recordings, which are then pre-processed to enhance the contrast between USVs and background noise. Key steps include median …

Post-Selection Inference In Regression Models, Qinyan Shen

Theses and Dissertations

This dissertation develops new methodology for valid statistical inference following model selection in various regression settings. We first consider the logistic regression model for a binary response that can only be observed at the group level, as in group testing, and is subject to testing error. With the true responses only partially observed, we employ the expectation-maximization (EM) algorithm to account for missing information in the response data and simultaneously conduct variable selection using the LASSO-penalized log-likelihood function. After variable selection, we extend an existing post-selection inference method based on the polyhedral lemma \parencite{lee2016exact} to make inferences on selected covariates, …

Methods And Applications For Bayesian Semiparametric Survival Analysis, Zile Zhao

Theses and Dissertations

Survival analysis is a cornerstone of biomedical and clinical research and plays an important role in fields as diverse as engineering, actuarial science, and sociology. In this dissertation, we develop new semiparametric Bayesian methodology for three problems from survival analysis: 1) adjustment for treatment crossover in randomized controlled trials (RCTs), 2) multilevel modeling of clustered survival outcomes when the cluster size is also informative, and 3) divide-and-conquer Bayesian inference for massive survival data. Our methods are semiparametric in the sense that we assume the covariates have a linear effect with regard to the log-hazard or the log- survival time; however, …

Quinone-Mediated Extracellular Electron Transfer In Escherichia Coli During Glucose Oxidation Metabolism, Megan Danielle Whisonant

Theses and Dissertations

The growing global demand for energy, ongoing reliance on fossil fuels, and increasing water pollution from industrial and anthropogenic sources present significant environmental challenges. In response to these issues, renewable and sustainable energy sources offer substantial potential for reducing dependence on fossil fuels and ensuring access to clean water. Microbial electrochemical systems (MESs) have emerged as promising, eco-friendly solutions for energy-efficient wastewater treatment and bioremediation. A key challenge in MESs development is facilitating effective electron transfer between microorganisms and electrode surfaces. The first chapter of this thesis discusses the fundamentals of MES types, explains mechanisms of extracellular electron transfer, and …

The Potential Importance Of Microenvironment On Polymer Bound Chemical Reagents, Nathan Joseph Halsteter

Theses and Dissertations

In this thesis will provide a brief history of polymer bound reagents, their uses, and advancements. The importance of polymer microenvironments will be explored using a model kinetic resolution reaction utilizing polymer bound reagents to observe how changes in a polymer’s microenvironment effects the yield and selectivity of a reaction. It was found that there are copious factors that affect polymer bound reagents, and no direct conclusion could be drawn from the study.

Regression With Atypical Data: Measurement Error, Periodicity, And Non-Normality, Nicholas W. Woolsey

Theses and Dissertations

Regression is a ubiquitous and fundamental method that can be found in any ele- mentary statistics course. The simplicity and self evidently useful nature of linear regression beguiles a non-negligible portion of researchers into disrespecting assump- tions required by these models, namely in terms of accuracy of covariates and the underlying nature of the data. This disregard can at best lead to meaningless results and at worse cause significant misunderstandings in scientific pursuit.

In this dissertation we strive propose remedies to violations of specific assump- tions. Namely the assumptions that covariates are either observed without measure- ment error or they …

Reactivity Of Redox-Active Carboranyl Diphosphines And Carboranyl Diphosphoniums: Metal-Free Pathways For Small Molecule Activations And Transformations, Amanda Lynn Humphries

Theses and Dissertations

Transition metal catalysis has been an integral part of synthetic chemistry for its ability to selectively activate strong substrate bonds, promoting numerous crucial transformations. Despite their utility, the precious metals that are often employed in these catalytic reactions suffer from several drawbacks (including high toxicity, low natural abundance, high costs, and low sustainability), increasing the motivation to design suitable metal-free alternatives. Towards this end, several ambiphilic main-group systems have been devised to show metal-like reactivity, such as carbenes, borylenes, and Frustrated Lewis Pairs. This manuscript will describe the ambiphilic reactivity of carborane-based phosphorus compounds, highlighting the unique metallomimetic reactivity that …

Characterizing Dissolved Organic Matter Composition In A Southeastern United States Watershed, Gwendolyn Marcelette Hopper

Theses and Dissertations

Dissolved organic matter (DOM) has important roles in many biogeochemical cycles. DOM is primarily composed of dissolved organic carbon (DOC), nitrogen, and phosphorus, and the processing of DOM is important for nutrient regulation and carbon cycling. In the coastal plains of the southeastern United States, there are many rivers and streams known as “blackwaters” with exceptionally high concentrations of chromophoric dissolved organic matter (CDOM) leached from terrestrial soils, coinciding with a region experiencing some of the nation’s highest rates of development. As changes in land use and climate continue to occur, DOM composition from natural to anthropogenically impacted systems can …

Determination Of Structure-Function Relationships In Hybrid Catalysts On Metal Oxide Supports, Joseph John Kuchta

Theses and Dissertations

Transition metal catalysis has revolutionized chemical synthesis, enabling efficient and selective transformations critical to the pharmaceutical, agricultural, and materials industries. However, traditional methods often rely on expensive, non-sustainable metals and harsh reaction conditions that generate significant waste. This dissertation explores a series of innovations aimed at bridging the gap between homogeneous and heterogeneous catalysis through the development of hybrid catalysts. These systems combine the molecular precision of homogeneous catalysts with the stability and practicality of heterogeneous supports, offering a pathway to more sustainable and scalable catalytic processes.

The first area of focus investigates nickel-based hybrid catalysts as a cost-effective and …

Rapid Charging Lithium-Ion Batteries: Structure, Morphology, And Methodology, Sean Cade Wechsler

Theses and Dissertations

The initial commercialization and subsequent development of the lithium-ion battery (LIB) in 1991 has revolutionized the way that humans power devices, cars, and homes and led to the advent of many technologies that seemed impossible just half a century ago. As LIBs are integrated into more of daily life through handheld devices, wearable medical devices, transportation, and grid-level energy storage, the demand for fast charging and high energy density increases rapidly. To design a battery with these favorable qualities, an understanding of the effect of electrode crystal structure and electrode morphology on the ionic/electronic transport and failure modes must be …

Hardware Accelerated Simulation Of Buck Converters Using Physics-Informed Neural Networks, James Clayton Crews

Theses and Dissertations

Physics-informed neural networks (PINNs) are an emerging machine learning method for learning the behavior of physical systems described by governing differential equations. Dc-dc power-electronic converters are used in a variety of industry applications such as motor drives or power supplies where real-time simulation is critical for control and safety. This thesis investigates physics-informed machine learning as an approach to develop a real-time digital twin for dc-dc power converters. Traditional numerical integration methods are used to approximate discretized behavior, and the results are compared with a trained PINN model. Modern ML frameworks (such as PyTorch and TensorFlow/Keras) are used to quickly …

Explorations In Extremal Combinatorics: Graph Spectra, Codegree Squared Sum Of Hypergraphs And Lin-Lu-Yau Ricci Curvature, George Henry Brooks

Theses and Dissertations

This dissertation explores a variety of extremal problems in spectral graph theory, hypergraph Tur\'an theory in the $\ell_2$-norm, and Lin-Lu-Yau Ricci curvature. We begin by studying the maximization of linear combinations of eigenvalues in relation to the adjacency matrix of a graph. For a graph $G$ on $n$ vertices, we order its eigenvalues $\lambda_1 \geq \dots \geq \lambda_n$. First, we study a generalization of the maximum spread. Specifically, we consider the $(i,j)$-spread, defined as $\lambda_{i+1}-\lambda_{n-j}$, and aim to maximize that quantity over all simple graphs on $n$ vertices. We establish asymptotic bounds for all $i,j\geq 0$ and identify infinitely many …

Mo Isotopes In The Aleutian And Costa Rican Arcs: Source Variability And Juvenile Crust Formation, Ekaterina Rojas Kolomiets

Theses and Dissertations

Chemical and physical transfer between the surface, lithosphere and asthenosphere at subduction zones leads to arc magmatism and continental crust (CC) production. Subduction zones magmas and associated volcanic products sample a variety of magmatic sources that contribute to their chemical compositions in various proportions. This dissertation contributes to the study of subduction zones magmatism by assessing the relative role of subduction inputs (sediments, altered oceanic crust – AOC – and serpentinite) as flux agents in the arc magmatism and in CC formation in subduction zones under the scope of Mo isotope systematics.

I present the first Mo isotope analyses form …

Exploring The Self-Assembly Of Functional Bis-Urea Macrocycles: M-Terphenyl Bis Urea Macrocycles And Triphenylamine Bis-Urea Macrocycles, Gamage Isuri Pramodya Wijesekera

Theses and Dissertations

Porous materials have gained significant attention due to their diverse applications in catalysis, separation, and molecular storage. Among them, self-assembled macrocycles represent a unique class of functional materials that leverage non-covalent interactions to form well-defined architectures with pores of controlled size. This thesis explores the design, synthesis, and self-assembly of bis-urea macrocycles in both solid-state and solution-phase environments, with a particular focus on supramolecular polymerization mechanisms and the emergence of kinetically trapped states.

The first chapter of this thesis presents a detailed overview of self-assembled porous materials, categorizing them based on pore dimensions and discussing their significance in catalysis, separation, …

Two Dimensional Van Der Waals Magnet, Cheongheon Lee

Theses and Dissertations

Conventional charge-based memory has reached its limits in improving energy efficiency while scaling down size. Consequently, memory utilizing 2D magnetic materials has emerged as an alternative. 2D Van der Waals (VdW) magnets are ultrathin magnets with unique properties that make them optimal for this purpose. Utilizing the weak interlayer coupling via VdW interaction has enhanced the possibility of integrating diverse materials to create heterostructures. The integration of spintronics requires not only stable magnetization but also an effective switching mechanism. Various external influences have been experimentally tested, such as the proximity effect, external magnetic field, gate voltage, and temperature dependence. This …

Physics Oriented Deep Learning For Material Prediction And Generation, Nihang Fu

Theses and Dissertations

The discovery of new materials is critical to advancing various industries, but traditional experimental methods for materials discovery remain slow and resource-intensive. Recent advances in machine learning (ML), particularly deep learning (DL), have greatly improved and accelerated two main aspects of modern computational material discovery: material design (e.g., material generation) and material screening (e.g., property prediction). However, a key challenge remains: standard ML models often struggle to perform domain-specific tasks effectively. Incorporating domain-specific knowledge, specifically the underlying physics of materials, into ML/DL models is key to improving the accuracy and reliability of material generation and prediction models.

This dissertation discusses …

Elevating Next Generation Wireless Devices Towards Contactless Sensing For Healthcare Applications, Aakriti Adhikari

Theses and Dissertations

There is an increasing interest in technologies that can understand and perceive at-home human activities to provide personalized healthcare monitoring, aimed at early detection of disease markers and assisting physicians in making clinical decisions. Existing approaches, such as wearables, require users to wear sensors that can be cumbersome and cause discomfort. Vision based solutions, such as optical cameras, IRs, LiDARs, etc., can be used to design contactless at-home monitoring systems. However, these systems are limited by poor lighting and occlusion, and they are privacy-invasive. Fortunately, high-frequency millimeter-wave wireless devices provide an effective alternative to the existing systems to enable fine-grained …

The Role Of Symmetries In Atomic, Electromagnetic, And Particle Physics, Joshua Martin O'Connor

Theses and Dissertations

Symmetries in atomic, electromagnetic, and weak interaction physics are explored to understand symmetry-breaking extensions of the Standard Model of particle physics. Lorentz-violating field theories are extremely interesting theoretically, since they possess many new features that are absent in Lorentz-invariant models. We outline the formalism and experimental status of the Lorentz- and CPT-violating Standard Model Extension, in both the classical and quantum regimes. Processes such as vacuum Cerenkov radiation, which are kinematically forbidden when Lorentz symmetry is exact may become allowed when this symmetry is weakly broken. Particle decays, such as pion and kaon decays, although allowed in Lorentz-invariant theories, are …

On A Conjecture On Covering Systems And An Irreducibility Question On Sparse 0,1-Polynomials, Alexandros Kalogirou

Theses and Dissertations

In 1952, H. Davenport posed the problem of determining a condition on the minimum modulus $m_0$ in a finite distinct covering system that would imply that the sum of the reciprocals of the moduli in the covering system is bounded away from 1. In 1973, P.~Erd\H os and J.~Selfridge indicated that they believed that $m_0$ > 4 would suffice. We provide a proof that this is the case in Chapter 2. Chapters 3 and 4 are dedicated to showing that $0,1$-polynomials of high degree and few terms are irreducible with high probability. Formally, let $k\in\mathbb{N}$ and $F(x)=1+\sum_{i=1}^kx^{n_i}$, where $ 0

A Spatial Scan Statistic For Group Testing Data, Vincent Onyame

Theses and Dissertations

Group testing involves pooling specimens from multiple individuals and offers an efficient means to surveil low-prevalence pathogens, but poses challenges for spatial cluster detection when only pooled results are observed. In this thesis, we develop a spatial scan statistic tailored to group-testing data with variable pool sizes. The statistic compares a null hypothesis of a homogeneous infection rate across all clusters to an alternative hypothesis that infection probabilities differ inside and outside a candidate cluster, with both models fitted by maximum likelihood estimation. We approximate the null distribution of the maximum likelihood ratio test via Monte Carlo simulation.

Through a …

In Vivo Analysis Of Fe-S Cluster Assembly And Iron Homeostasis In Escherichia Coli, Dexter Mclaurin Reasons

Theses and Dissertations

Iron-sulfur (Fe-S) clusters are an essential cofactor for a wide range of cellular processes, and their assembly and storage require tight regulation.

In Escherichia coli (E. coli), there are two pathways of Fe-S cluster assembly, the Isc and the Suf pathways. The Isc pathway is used under good growth conditions, and the Suf pathway is used under iron starvation and oxidative stress conditions. Once the cluster has been assembled on the scaffold protein of either pathway, it is transferred to Fe-S cluster trafficking proteins. In E. coli, the monothiol glutaredoxin GrxD and the BolA-type proteins BolA and IbaG …

Some Likelihood-Based Methods For Clustering Functional Data, Tong Shan

Theses and Dissertations

The analysis of functional data is an increasingly relevant part of statistics. The exploratory data analytic method of cluster analysis plays a very important role in different fields. Over the years, researchers have developed many clustering approaches, striving to achieve more accurate and efficient clustering. In Chapter 1, we aim to improve the accuracy of our outcome when clustering functional data. To achieve this goal, we use a predictive likelihood function which serves as an objective function to optimize in order to determine the most appropriate clusters. To optimize the objective function over the space of clustering partitions, we produce …

On Berge Pancyclicity For Uniform Hypergraphs, Teegan Cole Bailey

Theses and Dissertations

An $n$-vertex graph $G$ is \textit{hamiltonian} if it contains a length $n$ cycle as a subgraph. A stronger notion of hamiltoncity is pancyclicity. A graph $G$ is \textit{pancyclic} if $G$ contains a cycle of length $k$ for every $3\leq k \leq n$. Dirac's classical result on hamiltonicity states that if an $n$-vertex graph $G$ has minimum degree $\delta(G)\geq \frac{n}{2}$, then $G$ is hamiltonian. Under the same minimum degree condition as Dirac, J. A. Bondy showed that $G$ must also be pancyclic or the exceptional graph $K_{\frac{n}{2}, \frac{n}{2}}$. In 1971, Bondy proposed a so called meta-conjecture claiming that \textit{``almost any nontrivial …

Multi-Task Deep Learning Approach For Segmenting And Classifying Competitive Swimming Activities Using A Single Imu, Mark Shperkin

Theses and Dissertations

Competitive swimming performance analysis has traditionally relied on manual video review and multi-sensor systems, both of which are resource-intensive and impractical for everyday training use. This study investigates whether a single wrist-worn inertial measurement unit (IMU) can be used to automatically segment and classify swimming activities with high accuracy. We propose a multi-task deep learning pipeline based on the MTHARS (Multi-Task Human Activity Recognition and Segmentation) architecture introduced by Duan et al. to perform stroke classification, lap segmentation, stroke count estimation, and underwater kick count estimation. Data were collected from eleven collegiate-level swimmers wearing left-wrist-mounted IMUs, each performing five 100-yard …

Graph Convolutional Networks Enable Fast Hemorrhagic Stroke Monitoring With Electrical Impedance Tomography, J. Toivanen, V. Kolehmainen, A. Paldanius, A. Hänninen, A. Hauptmann, Sarah J. Hamilton

Mathematical and Statistical Science Faculty Research and Publications

Objective: To develop a fast image reconstruction method for stroke monitoring with electrical impedance tomography with image quality comparable to computationally expensive nonlinear model-based methods. Methods: A post-processing approach with graph convolutional networks is employed. Utilizing the flexibility of the graph setting, a graph U-net is trained on linear difference reconstructions from 2D simulated stroke data and applied to fully 3D images from realistic simulated and experimental data. An additional network, trained on 3D vs. 2D images, is also considered for comparison. Results: Post-processing the linear difference reconstructions through the graph U-net significantly improved the image quality, resulting in images …

Enhancing Proof-Of-Learning Security Against Spoofing Attacks Using Model Watermarking, Ozgur Ural

Doctoral Dissertations and Master's Theses

With the rapid expansion of machine learning (ML) technologies across diverse domains such as healthcare, finance, and autonomous systems, ensuring secure and trustworthy training methodologies has become more critical than ever. Proof-of-Learning (PoL) has recently emerged as a foundational mechanism for verifying the computational effort invested in training ML models, thereby certifying the authenticity and reproducibility of the training process. Yet PoL, when deployed in isolation, remains vulnerable to sophisticated spoofing attacks that manipulate its subset-verification pathways and tolerance parameters. In parallel, model watermarking has become indispensable for safeguarding intellectual property and detecting unauthorized model usage. Motivated by these complementary …

Stability Analysis Of The Eulerian-Lagrangian Finite Volume Methods For Nonlinear Hyperbolic Equations In One Space Dimension, Yang Yang, Jiajie Chen, Jing Mei Qiu

Michigan Tech Publications

In this paper, we construct a novel Eulerian-Lagrangian finite volume (ELFV) method for nonlinear scalar hyperbolic equations in one space dimension. It is well known that the exact solutions to such problems may contain shocks though the initial conditions are smooth, and direct numerical methods may suffer from restricted time step sizes. To relieve the restriction, we propose an ELFV method, where the space-time domain was separated by the partition lines originated from the cell interfaces whose slopes are obtained following the Rakine-Hugoniot junmp condition. Unfortunately, to avoid the intersection of the partition lines, the time step sizes are still …

Mtu-Llm: Llm-Based Multi-Robot Task Allocation And Path Planning For Heterogeneous Robots In Search And Rescue Operations, Kaushik Kannan, Jungyun Bae

Michigan Tech Publications

Urban Search and Rescue operations after natural disasters involve locating and assisting victims in hazardous environments, which is challenging. Classical Multi-Robot Task Allocation (MRTA) and path planning approaches have been used to deploy heterogeneous robot teams in unsafe areas. However, existing methods often lack focus on workload balance and requirement fulfillment and struggle to generalize across different scenarios. To address these challenges, we propose Multi-robot Task allocation Utilizing LLMs (MTU-LLM), a framework designed to reduce the development time for task allocation and path planning approaches, enabling faster robot deployment. The framework uses an LLM-based “prompt engineering” approach that generates task …

Sepsis: I Can Catch Your Lies – A New Paradigm For Deception Detection, Anku Rani, Dwip Dalal, Shreya Gautam, Pankaj Gupta, Vinija Jain, Aman Chadha, Amitava Das, Amit P. Sheth

Publications

Deception is the intentional practice of twisting information. It is a nuanced societal practice deeply intertwined with human societal evolution, characterized by a multitude of facets. This research explores the problem of deception through the lens of psychology, employing a framework that categorizes deception into three forms: lies of omission, lies of commission, and lies of influence. The primary focus of this study is specifically on investigating only lies of omission. We propose a novel framework for deception detection leveraging NLP techniques. We curated an annotated dataset of 876,784 samples by amalgamating a popular large-scale fake news dataset and scraped …