Theory and Algorithms Commons^™

A Specification-Driven Framework For Self-Supervised Learning In Specialized Vision Domains, Mahmut S. Gokmen

Theses and Dissertations--Computer Science

Self-supervised learning (SSL) has emerged as a principled approach to visual representation learning that derives supervisory signal directly from unlabeled data, enabling foundation models to be trained at scale without manual annotation. Deployments in medical imaging and biometric recognition have demonstrated the potential of this paradigm, yet the assumptions that make SSL effective on natural image benchmarks fail systematically in specialized domains. Generic SSL pipelines encode a tacit assumption that the most informative correspondence is spatial proximity within a single acquisition. In specialized domains this assumption breaks at the level of the data-generating process: the signal that carries domain-specific information …

Evaluating Hybrid Quantum-Classical Models For Image Classification In The Nisq Era, Utku Binkanat

Theses and Dissertations

This thesis presents a systematic empirical evaluation of quantum machine learning performance under noisy intermediate-scale quantum (NISQ) era constraints. Through 670 controlled experiments, it evaluated quantum kernel support vector machines and variational quantum classifiers against classical baselines on MNIST binary and multiclass classification tasks with systematic variation of problem difficulty, feature dimensionality (4, 8 qubits), and training set size (n ∈{100, 250, 400, 500, 2000, 4000}). Statistical rigor was ensured through five random seeds per condition and comprehensive significance testing. During the testing with binary datasets, classical methods (SVM, logistic regression, k-NN, neural networks) achieved 85.9% to 99.6% accuracy with …

An Empirical Framework For Evaluating Semantic Preservation Using Hugging Face, Nan Jia, Anita Raja, Raffi Khatchadourian

Publications and Research

As machine learning (ML) becomes an integral part of high-autonomy systems, it is critical to ensure the trustworthiness of learning-enabled software systems (LESS). Yet, the nondeterministic and run-time-defined semantics of ML complicate traditional software refactoring. We define semantic preservation in LESS as the property that optimizations of intelligent components do not alter the system's overall functional behavior. This paper introduces an empirical framework to evaluate semantic preservation in LESS by mining model evolution data from HuggingFace. We extract commit histories, $\textit{Model Cards}$, and performance metrics from a large number of models. To establish baselines, we conducted case studies in three …

Multi-Objective Optimization Of Energy Costs And Ev Battery Health In V2g Enabled Homes, Dzifa M. Hodey

Theses and Dissertations--Computer Science

Electric vehicles (EVs) and rooftop solar photovoltaic (PV) systems are increasingly being integrated into residential settings, creating new opportunities for vehicle-to-grid (V2G) and vehicle-to-home (V2H) operations. In these systems, the EV battery functions as a controllable energy storage unit that can charge from the grid or PV and discharge energy to supply household load or export to the grid for a profit. By intelligently scheduling this bidirectional power exchange, households can reduce electricity costs and enhance PV utilization. Realizing these benefits requires optimization strategies that balance cost reduction with EV battery health preservation. However, existing V2G/V2H studies largely emphasize cost …

Toward Efficient And Scalable Scientific Data Management Through Quality-Oriented Data Compression, Pu Jiao

Theses and Dissertations--Computer Science

Scientific simulations and instruments now produce data at rates that overwhelm the storage, memory, and network subsystems of modern high-performance computing (HPC) facilities. Error-bounded lossy compression reduces data movement costs while bounding reconstruction error, yet three barriers limit its adoption in mission-critical workflows: existing compressors cannot guarantee the accuracy of domain-specific quantities of interest (QoIs) derived from compressed data; compression-induced artifacts such as posterization, blocking, and interpolation banding erode user confidence in decompressed fields; and significant compressibility in the quantization index arrays of interpolation-based pipelines remains unexploited. This dissertation addresses all three barriers through four contributions, with the artifact barrier …

Machine Learning-Based Lifetime Prediction Of Lithium Batteries: A Comparative Assessment For Electric Vehicle Applications, Abdelilah Hammou, Raffaele Petrone, Demba Diallo, Boubekeur Tala-Ighil, Philippe Makany Boussiengue, Hicham Chaoui, Hamid Gualous

Electrical & Computer Engineering Faculty Publications

This paper evaluates and compares four data-driven methods (Gaussian Process Regression (GPR), echo state network (ESN), gated recurrent unit (GRU), and long short-term memory (LSTM)) for lithium-ion capacity prognostics adapted to electric vehicle conditions. This comparison aims to find the most efficient prognosis method considering two constraints: the limitation of computational power and the unavailability of on-board capacity measurement that requires full charge and discharge conditions. The machine learning models are trained using capacity values estimated under vehicle conditions. The ageing data is collected from cycling tests of two battery chemistries, Lithium Fer Phosphate (LFP) and Nickel Manganese Cobalt (NMC), …

Beyond Full Fine-Tuning: The New Playbook For Adapting Deep Neural Networks, Cristian S. Mcgee

Honors Undergraduate Theses

Fine-tuning is the process of teaching and specializing a pre-trained neural network on a downstream task. Fine-tuning is a rapidly growing topic in artificial intelligence domains; however, many fine-tuning endeavors are highly specialized without a coherent framework connecting them. This work presents a unified perspective on fine-tuning methods and performance metrics. Our perspective organizes the methods in terms of how they are applied to fine-tuning. This framework showcases methods that (i) update effective subspaces of the pre-trained model, (ii) change the adaptation optimization procedure, and (iii) alter the representations of the embedded input. Additionally, we present unconventional metrics such as …

Clinical Subtypes Of Co-Morbid Insomnia And Obstructive Sleep Apnea (Comisa): Results Of A Cluster Analysis, Yuan Shi, Xujun Feng, Fengyi Hao, Yuru Nie, Yihui Zhang, Zhaohua Chen, Siqi Guan, Larry D. Sanford, Michael V. Vitiello, Xiangdong Tang

Department of Pathology & Anatomy Faculty Publications

Background

Variations in the bidirectional relationship between obstructive sleep apnea (OSA) and insomnia in co-morbid insomnia and OSA (COMISA) may form distinct subtypes of COMISA, which have not been previously characterized. This study aims to identify and characterize subtypes of COMISA.

Methods

From a community-recruited COMISA cohort 256 individuals who met diagnosis for COMISA were used to identify subtypes using a two-step clustering methodology. Demographics and multidimension clinical characteristics were collected and compared among obtained subtypes. Logistic models were used to evaluate whether these subtypes were associated with cardiometabolic and mental disorders. A clinical cohort of 1816 COMISA patients was …

Reconstructing Lost Voices, Lana Tamim

Williams Honors College, Honors Research Projects

This project uses digital text mining tools (OCR, NLP, sentiment analysis, and topic modeling) to analyze 19th–20th-century newspaper archives, focusing on how marginalized groups (women, immigrants, or labor workers) were historically portrayed. Many historical newspapers were dominated by elite voices, so this project aims to recover silenced or misrepresented perspectives by identifying hidden patterns in language, frequency of coverage, sentiment, and shifts in public perception over time. Using machine learning and visualization tools, the project will create interactive maps and timelines showing how representation evolved across regions.

Machine Learning For Economists, John Luke Gallup

Economics Faculty Publications and Presentations

Explication of machine learning algorithms and their usefulness for economic research. The prediction algorithms of Random Forest, Gradient Boost Machines, Neural Networks and Support Vector Machines are built from simple steps applied at large scale to generate surprisingly precise nonlinear estimates. Although useful for processing and interpreting new forms of data, their application to economics research is limited because they do not provide readily interpretable evidence of the causes of outcomes.

Wearable Sensor-Based Phase Segmentation Analysis Of Front Crawl Swimming: A Scoping Review, Jonathan Simoes, Samuel Aylward, Daniel Hamze, Daniel James Goble, Daniel M. Russell, Joshua Haworth

Exercise Science Faculty Publications

Front crawl swimming stroke phase segmentation has historically relied on video analysis, but the development of wearable sensor technology has created new opportunities for automated phase segmentation. This scoping review mapped the available evidence on wearable sensor-based stroke phase segmentation methods in front crawl swimming, following PRISMA-ScR guidelines. A systematic search of SPORTDiscus, Web of Science, and IEEE Xplore conducted from January to June 2026, identified 15 eligible peer-reviewed studies published between 2000 and 2024. The review revealed an emerging field of research that has converged methodologically around inertial measurement units (IMUs) and the Chollet phase segmentation framework while remaining …

Early Icu Physiological Subtyping From Time-Series Data: A Comparative Study Of Feature Complexity, Predictive Performance, And Model Interpretability, Rojeena Khadka

College of Graduate Studies: Theses & Dissertations

Intensive Care Unit (ICU) patients do not follow a single uniform physiological pattern. Patients admitted with the same diagnosis show different clinical trajectories over time making standardized classification and treatment approaches insufficient. The increasing availability of large-scale electronic health records in MIMIC-IV makes it possible to investigate such heterogeneity through data-driven approach that captures how physiology evolves during the early phase of ICU admission. This thesis compares two analytical pipelines designed to identify physiological subtypes from the first 48 hours of ICU time series data. This study then assesses how well these subtypes predict in-hospital mortality. The first approach, referred …

Cogram: A Computational Pipeline For Genome Assembly And Reconstruction Using Graph Neural Networks, William Coggins

College of Graduate Studies: Theses & Dissertations

Genome assembly — the reconstruction of a complete DNA sequence from short, overlapping reads — remains a fundamental challenge in computational biology. A central difficulty is distinguishing true genomic overlaps from spurious connections arising from repetitive sequences, a task that traditional assemblers address through hand-tuned heuristic rules applied to de Bruijn or overlap graphs. This thesis introduces COGRAM (Coggins–Ramasamy Assembly Method), a genome assembly pipeline that reframes sequence reconstruction as an edge classification task on a k-mer overlap graph, replacing heuristic graph cleaning with a learned model.

COGRAM constructs a directed overlap graph from raw sequencing reads using a k-mer …

Ai-Driven Penetration Testing For Arm Systems: A Comprehensive Framework With Experimental Validation, Matthew Ragsdale

College of Graduate Studies: Theses & Dissertations

The convergence of artificial intelligence and cybersecurity presents new opportunities for automated penetration testing capable of discovering, prioritizing, and remediating vulnerabilities at machine speed. However, deployment on resource-constrained ARM platforms remains unexplored despite ARM’s dominance in mobile, IoT, and edge computing with over 280 billion chips deployed globally. This thesis presents systematic experimental evaluation of AI-driven penetration testing across four paradigms—traditional machine learning, deep learning, large language models, and reinforcement learning—on three ARM platform tiers: Raspberry Pi 5 (8GB, Cortex-A76), Radxa ROCK 5B Plus (16GB LPDDR5 with NPU), and NVIDIA Jetson Nano (4GB with Maxwell GPU). The experimental framework generates …

Optimizing Maintenance Routes For Highway Infrastructure Using Leader-Follower Autonomous Vehicles, Qing Tang, Chenxi Chen, Xianbiao Hu, Yuxin Ding, Tianjia Yang

Civil & Environmental Engineering Faculty Publications

The Autonomous Truck Mounted Attenuator (ATMA), a leader–follower style connected and automated vehicle system, enhances safety during transportation infrastructure maintenance in work zones. However, the significantly lower speed of ATMA, compared to regular vehicles, causes moving bottlenecks that reduce roadway capacity and prolong queuing, leading to further delays. Different ATMA routes lead to varying patterns of time-dependent capacity drop, affecting the user equilibrium traffic assignment and resulting in differing system costs. This study aims to optimize ATMA routing within a network to minimize the system cost associated with its slow-moving operation. To this end, a queuing-based traffic assignment approach is …

Towards Sample-Efficient Deep Reinforcement Learning, Guang Yang

Theses and Dissertations

Deep reinforcement learning (DRL), combining reinforcement learning and high-performance function approximations such as deep neural networks (DNN), is a powerful approach to solving complex sequential decision-making problems. However, due to the complex solution space of the sequential decision-making problems and the inefficient design of the DRL algorithms, DRL algorithms usually require a prohibitively large number of data samples to train effective strategies. Consequently, it is difficult to apply these DRL algorithms to complex real-world problems that require high costs to collect a large volume of data samples. This dissertation proposes new mechanisms to address this sample inefficiency issue, realizing sample-efficient …

Untrained Position-Encoded Multilayer Perceptron Network For Structured Illumination Microscopy Reconstruction, Sahil Sharma, Leonidas Zimianitis, Krishnendu Samanta, Balpreet Singh Ahluwalia, Joby Joseph, Dushan N. Wadduwage

Computer Science Faculty Publications

Structured Illumination Microscopy (SIM) enables super-resolution imaging by encoding high-frequency spatial information through patterned light. While traditional Fourier-based reconstruction methods are prone to artifacts under suboptimal conditions, recent deep learning approaches often require large training datasets and lack adaptability across different imaging setups. In this work, we present Position Encoded Multi-Layer Perceptron (PEM) network that leverages implicit neural representations (INRs) and SIM forward-model-driven modeling to reconstruct super-resolved images without any training data. PEM-SIM represents each spatial coordinate as a combination of sinusoidal functions across multiple frequencies, enabling rich encoding of fine spatial detail. A forward model grounded in SIM image …

Design And Analysis Of Modern Quantum Neural Network Architectures For Intelligent Systems, Lakshmi Chandrakanth Kasireddy, Prabhakara Rao Kapula, Dineshkumar Rajendran, Neha Bharani, Srikanth Pulipeti, Islombek Khushvaktov

Computer Science Faculty Publications

Quantum neural networks (QNNs) offer a principled pathway for integrating quantum computation with machine learning through superposition- and entanglement-based representations. This chapter proposes an architecture-aware design and evaluation framework for modern QNNs, emphasizing robustness and system feasibility alongside predictive performance. Multiple architectures variational QNNs, quantum convolutional neural networks, tensor-network hybrids, and fully quantum models—are assessed under a unified protocol. Experimental analysis shows that the proposed architecture-search–guided QNN achieves 91.8% classification accuracy and an F1-score of 0.914, outperforming fixed-template variational QNNs by approximately 5.6 percentage points. Under depolarizing noise with probability p = 0.10, the proposed model retains 85.3% accuracy, whereas …

Quantum Machine Learning Models: Principles, Frameworks, And Computational Challenges, K. A. Jayabalaji, S. Venkata Anand, Dineshkumar Rajendran, Prasanta Chatterjee Biswas, Sardor Omonov, Rubaid Ashfaq

Computer Science Faculty Publications

Quantum machine learning (QML) has become an optimistic avenue of harnessing quantum computation in data-driven modeling, especially of issues with high dimensionality and complicated correlations. Current methods are generally based on fixed or over-parameterized quantum circuits, and hence restricted to scalability as well as unproductive optimization in real-world hardware. This chapter introduces a hybrid quantum-classical learning system that is adaptive and provides principled quantum data encoding, architecture-conscious variational circuit design and resource-optimal optimization. The technique is based on the concepts of quantum architecture search and subspace-preserving transformations to trade expressiveness with trainability, and discretize the quantum model into a classical …

Maxgrnet: A Multi-Axis Vision Transformer With Improved Generalization For Eye Disease Classification Using Explainable Ai With Insertion-Deletion Operations On Fundus Images, Md Mehedi Hasan Santo, Fuyad Hasan Bhoyan, Fuad Ibne Jashim Farhad, Fahmid Al Farid, Sovon Chakraborty, Md Humaion Kabir Mehedi, Jia Uddin, Hezerul Bin Abdul Karim

Computer Science Faculty Publications

Eye diseases, including diabetic retinopathy (DR), glaucoma, and cataracts, represent a major global health concern and can lead to severe visual impairment or blindness if not identified in a timely manner. This study proposes a novel eye disease classification framework based on a multi-axis vision transformer (MaxViT) applied to color fundus images with Explainable Artificial Intelligence (XAI) techniques to enhance model transparency. The proposed architecture integrates transformer-based attention mechanisms with Global Response Normalization (GRN)-based multi-layer perceptron (MLP) layers to capture complex spatial and contextual relationships within fundus images effectively. The model was evaluated on a publicly available eye disease classification …

The Crucial Role Of Machine Learning Models In Predicting Current Childhood Asthma: Model Comparison, Calibration, And Shap-Based Interpretation, Aditya Chakraborty, A. K.M. Raquibul Bashar

Epidemiology, Biostatistics, & Environmental Health Faculty Publications

Background: Asthma is one of the most prominent chronic diseases in children and one of the most challenging ailments to diagnose in infants and preschoolers in the United States. Predictive models can be instrumental in improving early diagnosis, personalized treatment strategies, and disease progression. By utilizing nationalized data, this study focuses on building and comparing high-performing analytical predictive models based on the relevant risk factors and identifying the most influential predictors.

Methods: We analyzed cross-sectional BRFSS Asthma Call-Back Survey data (2011-2020; N = 9,813) and randomly split participants into training and testing sets. An XGBoost model (hyperparameters tuned via grid …

Information-Theoretic Path Planning For Safe And Adaptive Nanobot Drug Delivery, Nagesh Bheesetty, John H. Park, Sujatha Alla, Winifred M. Lo, Aditya Nimmagadda, Mohamadmahdi Samandari, Jae H. Lee

Engineering Management & Systems Engineering Faculty Publications

We present a safe and efficient path planning framework for nanobot navigation in complex vascular networks, enabling precise drug delivery to hard-to-reach tumor regions such as those found in the lungs. The proposed method introduces a safe and efficient path planning strategy that integrates a utility-based function to balance two key goals: exploring uncertain areas to gather valuable information and avoiding hazardous regions to ensure safe and reliable delivery. We evaluate a simplified swarm-based nanobot navigation scenario using synthetic vascular maps that mimic the structural complexity of lung tumor blood vessels. Environmental uncertainty is modeled from vessel topology, blockage density, …

Explainable Physics-Based Constraints On Reinforcement Learning For Accelerator Optimization, Jonathan Colen, Malachi Schram, Kishansingh Rajput, Armen Kasparian

Data Science Faculty Publications

We present a reinforcement learning (RL) framework for optimizing particle accelerator experiments that builds explainable physics-based constraints on agent behavior. The goal is to increase transparency and trust by letting users verify that the agent’s decision-making process incorporates suitable physics. Our algorithm uses a learnable surrogate function for physical observables, such as energy, and uses them to fine-tune how actions are chosen. This surrogate can be represented by a neural network or by an interpretable sparse dictionary model. We test our algorithm on a range of particle accelerator optimization environments designed to emulate the Continuous Electron Beam Accelerator Facility at …

Markov Chain Wave Generative Adversarial Network For Bee Bioacoustic Signal Synthesis, Kumudu Samarappuli, Iman Ardekani, Mahsa Mohaghegh, Abdolhossein Sarrafzadeh

Electrical & Computer Engineering Faculty Publications

This paper presents a framework for synthesizing bee bioacoustic signals associated with hive events. While existing approaches like WaveGAN have shown promise in audio generation, they often fail to preserve the subtle temporal and spectral features of bioacoustic signals critical for event-specific classification. The proposed method, MCWaveGAN, extends WaveGAN with a Markov Chain refinement stage, producing synthetic signals that more closely match the distribution of real bioacoustic data. Experimental results show that this method captures signal characteristics more effectively than WaveGAN alone. Furthermore, when integrated into a classifier, synthesized signals improved hive status prediction accuracy. These results highlight the potential …

Variational Autoencoder Inverse Mapper For Extraction Of Compton Form Factors: Benchmarks And Conditional Learning, Douglas Adams, Md Fayaz Bin Hossen, Joshua Bautista, Gia-Wei Chern, Simonetta Liuti, Marie Boër, Marija Čuić, Michael Engelhardt, Gary R. Goldstein, Huey-Wen Lin, Yaohang Li

Computer Science Faculty Publications

Deeply virtual exclusive scattering processes (DVES) serve as precise probes of nucleon quark and gluon distributions in coordinate space. These distributions are derived from generalized parton distributions (GPDs) via Fourier transform relative to proton momentum transfer. QCD factorization theorems enable DVES to be parameterized by Compton form factors (CFFs), which are convolutions of GPDs with perturbatively calculable kernels. Accurate extraction of CFFs from DVCS, benefiting from interference with the Bethe–Heitler (BH) process and a simpler final state structure, is essential for inferring GPDs. This paper focuses on extracting CFFs from DVCS data using a variational autoencoder inverse mapper (VAIM) and …

Toward An Event-Level Analysis Of Hadron Structure Using Differential Programming, Kevin Braga, Markus Diefenthaler, Steven Goldenberg, Daniel Lersch, Yaohang Li, Jian-Wei Qiu, Kishansingh Rajput, Felix Ringer, Nobuo Sato, Malachi Schram

Computer Science Faculty Publications

Reconstructing the internal properties of hadrons in terms of fundamental quark and gluon degrees of freedom is a central goal in nuclear and particle physics. This effort lies at the core of major experimental programs, such as the Jefferson Lab 12 GeV program and the upcoming Electron-Ion Collider. A primary challenge is the inherent inverse problem: converting large-scale observational data from collision events into the fundamental quantum correlation functions (QCFs) that characterize the microscopic structure of hadronic systems within the theory of QCD. Recent advances in scientific computing and machine learning have opened new avenues for addressing this challenge using …

Deep Incomplete Multi-View Clustering Via Hierarchical Imputation And Alignment, Yiming Du, Ziyu Wang, Jian Li, Rui Ning, Lusi Li

Computer Science Faculty Publications

Incomplete multi-view clustering (IMVC) aims to discover shared cluster structures from multi-view data with partial observations. The core challenges lie in accurately imputing missing views without introducing bias, while maintaining semantic consistency across views and compactness within clusters. To address these challenges, we propose DIMVC-HIA, a novel deep IMVC framework that integrates hierarchical imputation and alignment with four key components: (1) view-specific autoencoders for latent feature extraction, coupled with a view-shared clustering predictor to produce soft cluster assignments; (2) a hierarchical imputation module that first estimates missing cluster assignments based on cross-view contrastive similarity, and then reconstructs missing features using …

Enlem: Ensemble Learning-Based Model To Detect Phishing Websites, Most Nilufa Yeasmin, Md Abu Rumman Refat, Bikash Chandra Singh, Zulfikar Alom, Zeyar Aung, Mohammad Azim

School of Cybersecurity Faculty Publications

Phishing involves manipulating individuals into revealing private data, e.g., user IDs, bank details, and passwords. The observed surge in fraud is related to increased deception, impersonation, and advanced online attacks. Thus, effective phishing detection methods are required to mitigate escalating global phishing threats. Existing methods (e.g., heuristics-based, signature-based, and visual similarity-based methods) attempt to detect phishing sites, and machine learning (ML) and deep learning (DL) methods are effective in the cybersecurity context in terms of learning from data, offering insights, and forecasting. However, independent ML algorithms are limited when handling complex data, and DL techniques surpass traditional ML methods in …

A New Parallel-In-Time Direct Inverse Method For Nonlinear Differential Equations, Nail K. Yamaleev, Subhash Paudel

Mathematics & Statistics Faculty Publications

We propose a new method for parallelization of the first-order backward difference discretization (BDF1) of the first-order time derivative in nonlinear partial differential equations, such as conservation law equations. The time derivative term is discretized by using the method of lines based on the implicit BDF1 scheme, while the inviscid and viscous terms are approximated by conventional 2nd-order central discretizations of the 1st- and 2nd-order derivatives in each spatial direction. The global system of nonlinear discrete equations in the space-time domain is solved by the Newton method for all time levels simultaneously. For the BDF1 discretization, this all-at-once system at …

Mg-Spair: Multi-Grade Sparse-Guided Implicit Representation For Training-Data-Free Image Restoration, Jianmin Liao, Lei Huang, Ronglong Fang, Ashley Prater-Bennette, Lixin Shen, Yuesheng Xu

Mathematics & Statistics Faculty Publications

MG-SpaIR is a training-data-free framework for restoring a clean image from a single observation corrupted by a mixture of blur, downsampling, noise, and missing pixels. Building on implicit neural representations (INRs), we introduce a multi-grade residual hierarchy that progressively refines the reconstruction from low to high spatial frequencies across grades, improving representational fidelity and mitigating spectral limitations. To stabilize reconstruction optimization and suppress INR-induced artifacts, we further propose an explicit sparse proximal regularization (e.g., ℓ0 type) applied directly in the high-resolution image domain, which discourages spurious high-frequency patterns while preserving sharp structures. The resulting optimization is solved efficiently via a …