Digital Commons Network^™

Deep Learning Approaches For Ctenophore Identification And Tracking, Anagha Bharadwaj

Theses

Ctenophores are translucent marine organisms with nearly invisible tentacles and pose significant challenges due to their transparent morphology and ambiguous structural features. This research addresses the classification and tracking of these organisms and evaluates the performance of current computer vision models under sparse-data environments.

A dataset from the NJIT Life History Lab consisting of microscopic laboratory videos and photographs of different growth stages is used to train and assess a number of convolutional neural network designs, including VGG16, ResNet, BioCLIP2, YOLO, and DeepLabCut. Additionally, a web-based interface is developed to evaluate expert-labeled ground truth with the model's performance.

The findings …

Sound Detection Of Memory Leaks In Llvm Ir Programs Using Accumulation Analysis, Robert Blacha

Theses

Resource leaks occur when a limited resource such as memory is allocated by a program and needlessly held past the point of use. Leaks can lead to a degradation of services which can be specifically triggered with malicious behavior, for example abusing a memory leak in a program to cause a server to slow down and crash for a denial-of-service attack.

Prior work has demonstrated that accumulation analysis provides a sound detection of resource leaks with a working implementation for programs written in Java. While useful, current implementations are limited to programs written in Java, which has a garbage collector, …

Adaptive Multimodal Smart Home Control On A Raspberry Pi 5 Using Hand Gestures, Voice Cues, And User Feedback, Vaibhav Bora

Theses

A real time multimodal smart home control system deployed on a Raspberry Pi 5 is presented. The system combines hand gestures, short voice cues, and proximity aware interaction to execute household commands such as light brightness control, fan speed adjustment, and stop or kill switch actions. Lightweight gesture and keyword spotting voice classifiers were trained offline and exported to TensorFlow Lite for efficient on device inference. For more natural spoken phrases, the system additionally integrates a locally deployed pretrained offline ASR component rather than a speech recognizer trained from scratch. Using a USB camera and microphone, the system operates fully …

Evaluation Of Medical Instrument Reliability For The Heath And Maddox Components Of The Accommodative-Vergence System, Jacob Chabuel

Theses

Binocular vision relies on the coordination of near response triad composed in part by the vergence and accommodative systems. Binocular dysfunctions linked to these systems impact the quality of life of those affected by complicating day-to-day tasks and leading to further health concerns. Clinical evaluations that diagnose dysfunctions and tailor therapies rely on subjective methods, creating a need for a reliable, quantitative, measurement tool. This is achieved using a haploscope, a tool that quantitatively measures and observes binocular vision to identify deficiencies within the eye. Modernization of a haploscope system, measurement of the Heath and Maddox components of the visual …

Robustness Of Ai-Driven Histopathology Under Real-World Adversarial Examples, Ruchik N. Yajnik

Theses

This robustness of histopathology classification models under adversarial and real-world perturbations resembling clinical artifacts is being investigated.

Using whole-slide images from the CAMELYON17 cohort, four representative architectures—ResNet-18, ResNet-50, HIPT-2MLP, and ViT-B/16 —are benchmarked across controlled pixel-level distortions and artifact-like transformations. Adversarial methods include iterative Fast Gradient Sign, Projected Gradient Descent, Salt-and-Pepper noise, and the Adversarial Watermark—Stain Shift (AWSS). Three defense strategies—Randomized Smoothing, Adversarial Training, and an Artifact Detector—are evaluated for their ability to preserve diagnostic accuracy and model reliability. Structured perturbations consistently degrade performance, with transformer-based models showing the greatest sensitivity. The benchmark developed here offers a reproducible framework for …

The Effects Of Osha State Plans And State Gdp On Occupational Injuries And Illnesses In The United States, Ahmad Abdel Rahman Mohammad Amoorah

Theses

Workplace safety in the United States is governed by a system in which some states operate under federal OSHA oversight, while others administer their own OSHA-approved safety and health plans. This duality raises questions about whether state-level control leads to variation in safety and health outcomes. Economic conditions have also been shown to influence workplace injury rates, yet the interaction between safety and health regulations and local economies remains underexplored. Understanding these relationships is critical to protecting workers in occupational settings. The effects of OSHA state-plan status and state-level economic activity on occupational injury and illness rates across the United …

Polarimetric Terahertz Imaging For The Measurement Of Birefringence In Plastic, Rachel Cohen

Theses

Birefringence offers a promising way to observe stress concentration in materials such as glass and plastic, and thereby to identify weaknesses. Polarimetric imaging can be used to measure the birefringence of material, so long as the material is transparent to the light being used for the imaging. In this research, 2D Terahertz imaging was investigated as a means of measuring the birefringence of plastics that are opaque to visible light but transparent to THz radiation, for the eventual purpose of analyzing the residual stress present. In order to do so, two separate terahertz cameras were characterized for potential use in …

Autonomous Exploration Of An Environment With Static Obstacles Using A Ppo Agent, Brandon Knight

Theses

Research in autonomous exploration has created many effective algorithms that have been tested and proven to work in many different virtual and physical environments. Many optimizations have also been developed to reduce computational effort and increase exploration speed.

However, despite optimizations, these algorithms can still require considerable computational effort and time to explore even small environments. To obtain further improvements in computation and exploration speed, a reinforcement learning agent using actor-critic style proximal policy optimization (PPO) is trained to explore various environments efficiently, then compared to an algorithm using contemporary exploration methods.

Testing is performed in virtual environments with ideal …

Pypitfall: Dependency Chaos And Supply Chain Vulnerabilities In Python, Jacob Mahon

Theses

Python software development heavily relies on third-party packages. Direct and transitive dependencies create a labyrinth of software supply chains. While it is convenient to reuse code, vulnerabilities within these dependency chains can propagate through dependencies, potentially affecting downstream packages and applications. PyPI, the official Python package repository, hosts many packages and lacks a comprehensive analysis of the prevalence of vulnerable dependencies. PyPitfall, a quantitative analysis of vulnerable dependencies across the PyPI ecosystem, is introduced. The dependency metadata of 378,573 PyPI packages is analyzed. 4,655 packages that explicitly require a known vulnerable package version and 141,044 packages that permit a vulnerable …

Retinomorphic Mid-Wave Infrared In-Sensor Processing Engine: Device-To-Architecture Co-Design, Hemalatha Nagaraju

Theses

Conventional frame-based CMOS image sensors acquire full-frame pixel data at discrete time intervals, resulting in substantial spatial redundancy and loss of temporal information between frames. The repeated conversion and transfer of redundant pixel data increases bandwidth and power consumption in machine vision systems. Retinomorphic sensing architectures address these limitations by enabling programmable, analog-domain processing directly at the sensor interface. A compact behavioral model of the PbSe device is developed in HSPICE based on calibrated TCAD simulation data to capture gate-controlled photocurrent modulation under varying illumination and gate bias conditions. Error analysis is performed to quantify the deviation between TCAD-generated photocurrent …

Context-Aware Vulnerability Scoring For Dubai Immigration Systems: Enhancing Cvss With Exposure And Asset Risk Factors, Saeed Adnan Saeed Alkhatibi Alsuwaidi

Theses

This paper explores the drawbacks of Common Vulnerability Scoring System (CVSS) usage in case of mission critical government infrastructures with special attention to Dubai Immigration systems. Even though the widely used tool against evaluating the severity of technical vulnerability is the CVSS, it fails to consider the organisational factors like the exposure of the asset, the criticality of the system, the number of users and the sensitivity of data. Such contextual blindness may contribute to prioritisation being off-kilter and ineffective resource assignment in high-risk and highly sensitive settings. The researchers systematically analyse the potential to incorporate contextual features in CVSS …

Machine Learning–Based Spatio-Temporal Analysis And Prediction Of Urban Air Quality Using Global Aqi And Geolocation Data, Rashed Ibrahim Almheiri

Theses

The research problem addressed in this study involves the use of machine learning approach in the spatio-temporal analysis and prediction of urban air quality by relating Air Quality Index (AQI) and geolocation data on Air Quality across a global dataset. The study is informed by the increased concern on the effects of air pollution both on human health and the environment, whereby specific attention is given to comprehending the determinants of AQI in various regions. In the study, four main research questions guide the research: what key factors play an effective role on AQI, the efficiency of machine learning models …

Social, Economic, And Environmental Sustainability Of Small-Scale Hydroponic Farms, Alexa Genevieve Kaminski

Theses

Controlled environmental agriculture (CEA) is well-positioned to contribute to a more sustainable food system. It has the potential to offset some of the negative impacts of conventional agriculture through its ability to optimize the crop growing environment, locate production closer to population centers, and take advantage of non-arable land. The focus of this dissertation is one type of CEA: the hydroponic container farm (HCF). The HCF grows crops using only water and fertilizer inside a 40-foot shipping container that can be located anywhere in the world. Manufacturers are optimistic about this farm’s abilities, but little research exists that investigates the …

Smartdesk: Automatic Ticket Classification And Resolution Prediction Using Data Analytics, Dananir Almheiri

Theses

Public and service-oriented organizations increasingly rely on digital ticketing systems to man- age large volumes of citizen and customer requests. Despite this, many ticket management processes remain partially manual, leading to delays in case routing, inefficient resource al- location, and inconsistent resolution times. These challenges can negatively impact service quality, operational efficiency, and user satisfaction, particularly in large-scale public sector environments. This study proposes SmartDesk, a data-driven framework for automatic ticket classification and resolution time prediction using data analytics and natural language process- ing (NLP) techniques. The research leverages publicly available helpdesk and service ticket datasets to simulate real-world service …

Modeling Passenger Accumulation And Identifying Hidden Demand Patterns At Bus Stops Using Afc Data And Machine Learning, Diya Khalil

Theses

Public transport systems increasingly rely on data-driven approaches to understand passenger demand and improve operational efficiency. However, conventional bus stop classification methods are typically static and fail to capture variations in passenger accumulation patterns over time. As a result, certain bus stops may experience high levels of congestion without being identified as critical nodes within the network. This study addresses this gap by developing a data-driven framework to model passenger accumulation and identify hidden demand patterns at bus stops using Automated Fare Collection (AFC) data. The research investigates whether Regular Bus Stops exhibit homogeneous demand behavior and to what extent …

Comparative Analysis Of Standard Building Materials In Earth-Sheltered Architecture, Austin Greifenkamp

Theses

In an industry that significantly contributes to the ever-increasing environmental destruction witnessed globally, architects are responsible for ensuring human comfort without sacrificing environmental health. Earth-sheltering, an architectural design technique that uses earth to partially or fully cover a building, results in reduced operational energy consumption but introduces structural components to increased loads and higher levels of humidity. Using the material properties and life cycle data of wood, concrete, and steel, this study analyzes the viability of each material in a below-grade environment and the resulting embodied impact of a typical earth-sheltered structure. To align the results of this research with …

Automated Contact Pattern Extraction And Evaluation For Gears, Tom Abraham

Theses

The tooth contact pattern is a crucial indicator of overall performance for many gear geometries, especially spiral bevel and hypoid gears. It is directly associated to the loaded function of transmission errors, a primary contributor to gear noise and vibration. This is especially relevant in electric vehicles, where gear noise is more pronounced due to the absence of masking noise from internal combustion engines. Consequently, the inspection and control of the contact pattern are essential aspects of gear design and manufacturing. Traditionally, contact patterns are evaluated using a manual process known as the tooth contact roll test. This test is …

The Impact Of Employment On Sense Of Belonging And Metacognitive Awareness: A Mixed-Methods Study Of Undergraduate Students’ Mathematical Performance, Erin Ryan

Theses

This study investigated how employment intensity affects two critical factors for academic success: a student’s sense of belonging and their metacognitive awareness (the ability to monitor and manage their own learning). Using a mixed-methods approach at the Rochester Institute of Technology, we analyzed survey data through multi-level modeling and conducted qualitative interviews to capture the personal experiences of employed students. Results reveal that students working off-campus for more than eleven hours a week showed significantly lower sense of belonging and metacognitive awareness scores than unemployed students. However, on-campus employment did not show the same effect. Both quantitative and qualitative results …

Toward Autonomous Wireless Networks: Spatio-Temporal Prediction Via Physics-Aware Generative Ai Models, Rahul Gulia

Theses

The realization of fully autonomous Industry 4.0 environments depends on wireless networks that are not merely connected, but predictively aware—capable of anticipating channel degradation before it disrupts mission-critical operations. In dynamic industrial environments such as automated warehouses, radio frequency propagation is governed by dense metallic infrastructure, continuously moving obstacles, and frequent line-of-sight to non-line-of-sight transitions that render the channel non-stationary and spatiotemporally complex. Conventional approaches face a fundamental dichotomy: deterministic simulators such as ray-tracing and NS-3 achieve high physical fidelity but require up to 38 hours to generate a single high-resolution SINR heatmap, making real-time adaptation computationally infeasible; empirical and …

Redefining Capital Cities: A Smart Growth Evaluation Of Capital Cities And How Albany Can Learn From Them, Richard Turoski Iii

Theses

Mid-sized American capital cities face distinct development challenges determined by historical growth patterns, economic restructuring, and evolving urban priorities. This study examines Albany, New York, through the lens of Smart Growth, a planning framework that emphasizes compact development, mixed land use, multimodal transportation, and reinvestment in existing urban areas. Using comparative policy analysis, Albany is evaluated alongside Columbus, Ohio; Hartford, Connecticut; and Harrisburg, Pennsylvania, enabling consistent cross-case comparison based on similar roles as state capitals and overlapping comprehensive planning timelines. The research studies Smart Growth principles by structured policy analysis centered on downtown revitalization, mixed-use development, transportation connectivity, waterfront redevelopment, …

Confederate Women In The Field Of Nursing And Their Impact On Southern Women’S Roles In Society, Laura Leigh L. Prater

Theses

During the Civil War, Confederate women had the opportunity to go to work as nurses. The majority of these women had never been allowed to take on roles beyond the domestic sphere in antebellum society.  Despite most of these women having limited medical training, they developed an expertise in nursing, extraordinary organization skills and gained respect for their achievements.  Their achievements proved that women were able to do far more than many in the South believed prior to the war.  This paper will show how the demands of war opened doors of greater opportunity for women in the South for …

Thoughts, Lately, Thomas L. Reid

Theses

Swift changes in government occur through several avenues. One option involves quick decisive action that entails violence. These set of poems exhibit a reaction to suddenly changing political and social structures in America during the second term of a divisive executive administration. Alongside this change—the author’s personal experiences as queer individual in a historic area of the deep South.

A Comparative Static Analysis Of Identifier Clones And Homonyms In Open Source Projects, Jose Palomino Lau

Theses

Identifier naming is a core element of software engineering and program comprehension. While existing literature suggests that naming consistency is ideal, there is limited empirical data on identifier homonyms, instances where the same name is used for different behaviors. This thesis investigates these naming patterns through a manual analysis inspired by grounded theory, supported by static analysis with srcML across three open source projects in Java, C and Python. By establishing a behavioral framework through axial coding, this research classifies 771 identifiers into functional categories to document their presence and role within the code. The results reveal that naming redundancy …

As I Live And Breathe, Jessica Fitzgerald

Theses

This thesis employs the unique materiality of glass as a means of investigating interconnection and worth. Through glass, I explore the value of attention, and how directing it informs a sense of what matters. By allowing the fundamental forces of heat and gravity to lead the work, I explore connection, and the hidden ways in which Process influences Piece. The particular malleability of warm glass enables me to capture moments of making. It is the lens through which I focus my investigations, highlighting phenomena in process as the evidence of its creation.

Uncovering Cytoskeletal Length Control From Growth Trajectories Using Sparse Dynamical Modeling, Carson Hearn

Theses

Understanding the governing equations of biological filament dynamics is essential for predicting cellular behavior, yet these equations are often difficult or impossible to derive directly from first principles. This thesis investigates the use of Sparse Identification of Nonlinear Dynamics (SINDy) as a unified, data-driven framework for discovering, validating, and refining governing equations from both simulated and experimental data. Focusing on biological filament processes, including growth, disassembly, and severing, this work is designed not only to apply SINDy, but to systematically demonstrate that it is a reliable and generalizable tool for modeling complex biophysical systems. To establish this, SINDy is first …

The Evolution Of Topological Structures In Climate Networks, Kiera Kelly

Theses

We investigate higher-order interactions in climate networks using topological data analysis (TDA) and analyze their evolution since 1948. Using the correlation between surface air temperature (SAT) anomalies, we define relationships between spatial locations and examine the patterns that emerge over time. We extend the framework of temporal climate networks and apply TDA methods, including persistent homology, curvature analysis, and the Euler characteristic, to identify dynamic structural features. Persistent homology tracks the births and deaths of topological features such as connected components and loops. Curvature quantifies a node’s participation in higher- order structures (cliques), while the Euler characteristic captures global trends …

Unfixed Bodies, Soph Shufelt

Theses

This thesis emerges from that tension between protest and living.  It considers what it means to have one’s existence continually framed as resistance, and how that condition reshapes embodiment, temporality, and identity.  By situating my lived experience within broader social and political structures, I examine how bodily autonomy functions not only as a personal necessity, but as a regulated site of power.  The work that follows investigates how queer and transgender bodies navigate visibility and risk, how time is warped through prolonged struggle, and how survival becomes a form of authorship.

The Development Of The Hagiography Of Saint Servatius: From The 6th To 16th Century, David Krista

Theses

This paper follows the development of the hagiography of St. Servatius from its foundation in the sixth century until the sixteenth century. In this analysis eight different hagiographical works on St. Servatius are discussed including a previously unstudied French Vie de Saint Servais produced in the late fifteenth or early sixteenth century. First, the foundational work which introduced St. Servatius to the world of hagiography by Gregory of Tours will be explored in order to understand who St. Servatius was. From here the paper moves onto the Latin vitae tradition which consists of the Vita Antiquissima, the Gesta Antiquiora, and …

Understanding Communication In Green Infrastructure Project Teams In Rochester Ny Region: Coordination, Negotiation, And Constraints, Hayden Berner

Theses

This study explores how communication is perceived and used within multidisciplinary green infrastructure (GI) project teams. As GI continues to grow in the United States, projects increasingly rely on collaboration between professionals from different fields, making communication a critical factor in project success. Using a qualitative research approach, semi-structured interviews were conducted with professionals working on GI projects in the Greater Rochester, New York region. The data were analyzed using an inductive, grounded theory approach to identify key themes related to communication practices, challenges, and outcomes. Results show that communication is not just a tool for sharing information, but a …

Stance Detection On Social Media: The Impact Of Doping On Athlete Reputation, Connor O'Neill

Theses

Doping scandals can have a lasting effect on both athletes' and organizations' reputations, causing athletes to lose money and fans to lose trust in the organizations that govern their favorite sports. This paper investigates the impact a doping scandal can have on an athlete's reputation by  conducting a case study on Jannik Sinner, one of the top tennis players in the world, who ultimately accepted a suspension after testing positive for performance-enhancing drugs, despite being unintentionally exposed. Using data sourced from YouTube comments on tennis-related videos, a fine-tuned Mistral-7B-Instruct-v0.3 model with a classification head was used to carry out stance …