Digital Commons Network^™

Predictive Maintenance For Manufacturing Equipment, Paloma De Andrade Batista

ICT

Unplanned equipment downtime is a significant challenge in manufacturing, resulting in substantial productivity losses and operational costs. Predictive maintenance, enabled by machine learning and big data analytics, offers an opportunity to identify potential equipment failures before they occur and improve maintenance efficiency. This report extends a previous capstone project that applied Random Forest and Logistic Regression to the AI4I 2020 Predictive Maintenance Dataset. The current study expands the analysis by incorporating XGBoost, systematic hyperparameter optimisation, cross-validation, and SHAP-based model interpretability. In addition, SWOT and PESTLE analyses, alongside a legal and ethical assessment, examine the broader strategic and responsible implementation of …

Predicting Loneliness Among Older Adults In Ireland Using Supervised Machine Learning, Ariadne Chaves Miranda

ICT

Over the last two decades, technology has grown exponentially and has facilitated communication that helps individuals remain connected. However, this has also contributed to social isolation and lack of physical interaction. One consequence of this phenomenon is loneliness, which is understood as an unpleasant subjective state of discrepancy between the desired amount of companionship or emotional support and what is available in the person’s environment (Prohaska and Burholt, 2020). In the European context, Ireland has emerged as the loneliest country in Europe with 20% of its population that have reported feeling lonely most or all the time (Schnepf et al., …

Active Galactic Nuclei Across Scales: From Blazar Jets To Dark Matter Halos, Stephanie Ann Podjed

Dartmouth College Ph.D Dissertations

Within ΛCDM, galaxies form and evolve within dark matter halos, with both central and satellite galaxies contributing to the total stellar mass content. Virtually every massive galaxy harbors a supermassive black hole (SMBH) at its center, with a small fraction of the population growing by actively accreting material; we call this an active galactic nucleus (AGN). The processes giving rise to an AGN phase (i.e., growth of a SMBH) releases enormous amounts of energy in the form of radiation, outflows, and relativistic jets that are able to significantly affect the formation and evolution of galaxies. Blazars are an extreme class …

Designing Narrative-Based Ai Assistance For Sensemaking In Collaborative Environments: Case Studies In Education And Dementia Care, Dylan Edward Moore

Dartmouth College Ph.D Dissertations

This thesis addresses a gap in the human-computer interaction literature regarding the design, development, and evaluation of narrative-based AI assistance for collaborative, complex problem solving. I explore this design space through three case studies across the domains of education and dementia care. This work encompasses multi-year industry partnerships and longitudinal fieldwork, user-centered design, dataset curation, model training, and system evaluation.

Specifically, the first case study considers a story-based web platform for teaching AI literacy through peer-generated, personalized narrative scaffolding. Learners on the platform showed significant knowledge gains and other learning-related outcomes. To describe the novel design of this system, I …

A Simple Statistical Tool To Correct The Daily Temperature Effect On Dielectric Soil Matric Potential Sensor Readings, Sebastián Bravo Peña, Meindert Commelin, Ole O. Wendroth

Plant and Soil Sciences Faculty Publications

High-resolution time series recorded by soil water dielectric sensors are often affected by other processes. Dielectric soil matric potential sensors, such as the TEROS 21, exhibit temperature sensitivity, resulting in deviations of readings from the true value due to soil temperature fluctuations. However, methods for correcting this effect remain limited. The objective of this study was to create a straightforward, scale-based statistical approach to mitigate the influence of daily temperature oscillations on matric potential dielectric readings. The temperature sensitivity correction function (TSCF) identifies, quantifies, and smooths diurnal fluctuations caused by soil temperature dynamics. We provide a detailed description of the …

Adversarial Robustness In Biomedical Time-Series Models, Rohan Tiwari

Bioengineering Theses

This study investigates adversarial vulnerabilities in deep learning models for biomedical time-series classification across two clinically important modalities: electrocardiography (ECG) and electroencephalography (EEG). Using the MIT-BIH Arrhythmia and CHB-MIT seizure datasets, I evaluate time-domain attacks (FGSM, PGD), Fourier-domain constrained attacks, and learned spectral perturbations designed to reveal modality-specific sensitivity patterns. Across both tasks, a consistent trend emerges low-frequency components (0–5 Hz) constitute a dominant axis of adversarial vulnerability, with perturbations in this range producing the steepest degradation in classification performance. In ECG models, protecting the physiologically relevant QRS band (5–20 Hz) significantly improves robustness, whereas EEG models remain highly sensitive …

Drivers Of Phytoplankton Bloom Interannual Variability In The Amundsen And Pine Island Polynyas, Guillaume Liniger, Delphine Lannuzel, Sébastien Moreau, Michael S. Dinniman, Peter G. Stutton

CCPO Publications

The Amundsen Sea Embayment (ASE) experiences both the highest ice shelf melt rates and the highest biological productivity in West Antarctica. Using 19 years of satellite data and modelling output, we investigate the long-term influence of environmental factors on the phytoplankton bloom in the Amundsen Sea (ASP) and Pine Island (PIP) polynyas. We test the prevailing hypothesis that changes in ice shelf melt rate could drive interannual variability in the polynyas' surface chlorophyll-a (chl a) and Net Primary Productivity (NPP). We find that the interannual variability and long-term change in glacial meltwater may play an important role in …

Results Of The Second Ice Shelf-Ocean Model Intercomparison Project (Isomip+), Claire K. Yung, Xylar S. Asay-Davis, Alistair Adcroft, Christopher Y. S. Bull, Jan De Rydt, Michael S. Dinniman, Benjamin K. Galton-Fenzi, Daniel Goldberg, David E. Gwyther, Robert Hallberg, Matthew Harrison, Tore Hattermann, David M. Holland, Denise Holland, Paul R. Holland, James R. Jordan, Nicolas C. Jourdain, Kazuya Kusahara, Gustavo Marques, Pierre Mathiot, Adele K. Morrison, Yoshihiro Nakayama, Olga Sergienko, Robin S. Smith, Alon Stern, Ralph Timmermann, Qin Zhou

CCPO Publications

Ocean-driven basal melting of Antarctic ice shelves plays an important role in the mass loss of the Antarctic Ice Sheet. Ice shelf cavity-resolving ocean models are a valuable tool for understanding ice shelf-ocean interactions and for simulating projections of ice shelf and ocean states under future climate. Designed to assess the current state of ice shelf–ocean modelling, the second Ice Shelf–Ocean Model Intercomparison Project, ISOMIP+, consists of 12 ocean model configurations submitted with a common, idealised experimental setup. Here, we focus on the experiments Ocean0–2 (Asay-Davis et al., 2016), which are ocean models with idealised, static ice …

Accounting For Spatial Effects And Social Norms In Making Algorithmic Law: Insights From And Applications In Urban Mobility, Jingkang Gao

Journal of Law and Mobility

This Article examines a prominent idea in the law and technology literature: that algorithms and big data can be used to make law dynamic and personalized. As currently envisioned by legal scholars, “algorithmic law” entails laws that adjust in real time to changing conditions and vary across individuals, improving welfare by tailoring legal rules and standards to personal characteristics.

This Article argues that this vision of algorithmic law is incomplete—and often counterproductive. Existing proposals treat personalization as a function of individual attributes alone, overlooking the fact that effects of individual behavior are fundamentally interactive. Individual behavior is shaped by spatial …

Artificial Intelligence–Enabled Revenue Cycle Management And Financial Performance In Healthcare Organizations, K’Reesa Webster

Theses, Dissertations and Capstones

The purpose of this review was to examine how artificial intelligence–enabled revenue cycle management (AI-enabled RCM) systems have been associated with financial performance outcomes in healthcare organizations. A literature review following a systematic process consistent with PRISMA 2020 guidelines was conducted to identify quantitative studies published between 2015 and 2026. Eligible studies were required to report at least one financial outcome related to claim denial rate, days in accounts receivable, or operating margin. Twenty-seven studies met all inclusion criteria. Findings across these studies indicated that AI-enabled RCM systems have been associated with lower denial rates, shorter accounts receivable timelines, and …

Distilling The Complexity Of Agent-Based Simulations Into Textual Explanations Via Large Language Models, Noé Y. Flandre, Philippe J. Giabbanelli

VMASC Publications

Communicating the design and results of agent-based models (ABMs) to subject matter experts is challenging, which hinders participation and limits trust in simulation-based decision support. Large language models (LLMs) can communicate ABMs as textual summaries, thus complementing traditional disclosure through statistical and visualization techniques. While prior work translated the structure of conceptual models into narratives via LLMs, our extension covers the dynamics of simulation models via an automated simulation-to-text method that extracts contextual information from NetLogo ABMs, performs repeated simulations, and generates narrative descriptions (including the model’s purpose, parameters, and simulation dynamics) using mutimodal LLMs. Furthermore, four summarization algorithms spanning …

An Analysis Of Volcanic Lightning And Its Controlling Factors, Nathan Stamford

Honors Theses

Volcanic lightning, first documented during the 79 AD eruption of Mount Vesuvius, includes any electrical discharge that is generated during a volcanic eruption rather than a thunderstorm. By analyzing individual eruptions and performing laboratory experiments, previous research has identified multiple controlling factors that influence the charging mechanisms and generation of volcanic lightning. While the previous research has made significant discoveries about the phenomenon, the exact relationship between many of these controlling factors and volcanic lightning generation has been poorly quantified. In this study, we investigate these controlling factors and show that they have a wide range of influence over volcanic …

Representations Of Finite Groups And Diagrammatic Algebras, Hudson Yeend

CMC Senior Theses

Representation theory allows mathematicians to study abstract mathematical objects using the powerful and concrete tools of linear algebra. This thesis aims to present some foundational concepts in representation theory and apply these concepts to specific groups and algebras. We begin by examining representations of finite groups, culminating with a proof of Maschke's theorem. We then use the correspondence between a group and its group algebra to segue into a study of representations of diagrammatic algebras, where we introduce analogous notions of decomposition. We end with a study of quiver representations, noting that Gabriel's theorem and the kQ-modular structure transcend …

Investigations Toward A Unified Reaction Pathway Of Thermal And Tbsotf-Mediated Oxidopyrylium-Alkene (5 + 2) Cycloadditions, Adam J. Youman, Samantha N. Rokey, Wentao Guo, Jacob P. Grabowski, Susanna N. Angles, Jacob J. Bulandr, Qing Sun, John R. Goodell, Dean J. Tantillo, T. Andrew Mitchell

Faculty Publications – Chemistry

Oxidopyrylium-based (5 + 2) cycloadditions are crucial reactions to construct seven-membered carbocycles containing an ether bridge (i.e. oxabicyclo[3.2.1]octanes). Intramolecular silyloxypyrone-based (5 + 2) cycloadditions were investigated and revealed several features: (1) the TBDPS thermal process proceeds via a zwitterionic oxidopyrylium intermediate similar to previously reported TBS variants; (2) the TBSOTf-mediated reaction proceeds through a cationic oxidopyrylium intermediate; (3) quantum chemical calculations predict a stepwise process for an electron-rich dipolarophile for each set of conditions. The thermal silyloxypyrone-based (5 + 2) cycloadditions were extremely dependent on the nature of the dipolarophile and the silyl transfer group. The TBDPS enhances the …

Federated Data Engineering And Learning For Edge Intelligence Systems, Afsaneh Mahanipour

Theses and Dissertations--Computer Science

The rapid proliferation of Internet of Things (IoT) devices and cyber–physical systems (CPS) in domains such as smart healthcare, intelligent transportation, and industrial automation has led to unprecedented volumes of heterogeneous data. While advances in deep learning and large-scale foundation models have enabled powerful data-driven decision making, their deployment in real-world distributed environments remains fundamentally constrained by limited computation, communication bandwidth, energy resources, and data privacy requirements. This dissertation addresses these challenges by developing novel federated learning frameworks and efficient federated data-processing pipelines that make large-scale artificial intelligence practical, scalable, and trustworthy in resource-constrained settings. This dissertation identifies data preprocessing …

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 …

A Literature Review On Ethics In Medical Diagnostic Ai & Analysis Therein, Connor J. Turetzky

Master's Theses

Artificial Intelligence presents a very promising future in medicine. Being able to diagnose and recommend treatments quickly is vital in ensuring positive patient outcomes. However, the new technology is not without risk. In this narrative literature review, the risks of AI in terms of bias, ethics, and environmental impact will be explored through existing research. This paper will focus on research published between 2019 and 2026, highlighting the major ethical and systematic problems currently facing diagnostic AI. Historical bias in medical data has led to AI that share those biases, and humans inherit that bias creating a potential negative feedback …

Mat 1500 Calculus I Syllabus, Tian Cai

Open Educational Resources

No abstract provided.

Mat 1600 Syllabus Ii Syllabus, Tian Cai

Open Educational Resources

No abstract provided.

Mat 2100 Calculus Iii Syllabus, Mei Xing

Open Educational Resources

No abstract provided.

Part Sm: Statistical Mechanics, Konstantin Likharev

Essential Graduate Physics

Includes: Review of Thermodynamics; Principles of Physical Statistics; Ideal and Not-So-Ideal Gases; Phase Transitions; Fluctuations; Elements of Kinetics

Laser Beam Shaping Using A Neural Network, Azeem A. Hakim

Honors Undergraduate Theses

Multiphoton lithography (MPL) is a method of laser-based 3D-printing for fabricating micron-scale structures point-by-point in a photopolymerizable medium. MPL’s high-resolution capabilities have made it a powerful method for the fabrication of many devices, such as microelectromechanical systems (MEMS) and tissue scaffolds.  The throughput of MPL processes can be increased by using spatially shaped laser beams that expose large areas or volumes simultaneously. A laser beam can be reshaped by passing it through a spatial light modulator (SLM) displaying a pre-designed phase mask. One type of laser beam profile used for this purpose is the Bessel beam, a type of structured …

Alexander Duals Of Symmetric Simplicial Complexes And Stanley-Reisner Ideals, Ayah Almousa, Kaitlin Bruegge, Martina Juhnke-Kubitzke, Uwe Nagel, Alexandra Pevzner

Mathematics Faculty Publications

Given an ascending chain (I_n)_n∈N of Sym-invariant squarefree monomial ideals, we study the corresponding chain of Alexander duals (I_n^∨)_n∈N. Using a novel combinatorial tool, which we call avoidance up to symmetry, we provide an explicit description of the minimal generating set up to symmetry in terms of the original generators. Combining this result with methods from discrete geometry, this enables us to show that the number of orbit generators of I_n^∨ is given by a polynomial in n for sufficiently large n. The same is true for …

Using Ai To Analyze Survey Data, Sara Martucci

Open Educational Resources

This assignment in Methodology in Sociology/Criminology engages students in the full research process by guiding them through variable selection, data analysis, interpretation, and critical reflection on AI-assisted decision-making. Using a class-generated survey dataset (or an existing dataset), students develop a research question, identify independent and dependent variables, and formulate a hypothesis. They then compare their selections with those suggested by an AI tool, analyzing differences in reasoning and variable choice. Through SPSS, students generate frequency tables, charts, and scatterplots to examine relationships between variables, including potential intervening factors. The assignment culminates in a group presentation and reflective analysis on the …

The Shoreline Protection Potential Of Oyster Reefs: A Systematic Review And Meta-Analysis, Jessica R. Fergel, Robert E. Isdell, Gabriella Dipetto, Karinna Nunnez, Sean T. Gregory, Evan Hill, Donna Marie Bilkovic

Biological Sciences Faculty Publications

Nature-based solutions for erosion control that incorporate oyster reefs, alone or in combination with other habitats, are an increasingly popular approach due to their potential to protect shorelines and enhance oyster production. However, the extent to which natural or constructed oyster reefs provide shoreline protection remains unclear. We conducted a global systematic literature review and meta-analysis to summarize and evaluate the potential of oyster reefs in attenuating waves, promoting sediment accretion, and/or reducing shoreline erosion. Factors extracted from studies included shoreline protective measures examined, oyster reef structure type, and oyster reef tidal location. The results of the meta-analysis showed generally …

Differences In Biologic Clinical Trials For Chronic Rhinosinusitis With Nasal Polyps—Are We Comparing Apples With Oranges?, Marjolein Cornet, Peter W. Hellings, Martin Desrosiers, Martin Wagenmann, Richard Follows, Laura Walrave, Luz Adriana Jimenez, Lee Tombs, Dawn Edwards, Peter Howarth, Joseph K. Han

Department of Otolaryngology (ENT) Faculty Publications

In recent years, several biologics targeting Type 2 inflammation have been developed for treating chronic rhinosinusitis with nasal polyps (CRSwNP). These have been studied in registrational randomized controlled trials (RCTs), which vary in their patient populations, trial design, endpoints, geography, timing, or data-handling processes. While (in)direct treatment comparisons and meta-analyses have been carried out to compare efficacy results from RCTs, often these fail to properly account for these between-study differences. Here, we summarize the key between-study differences that can influence trial outcomes and highlight the resulting challenges faced when comparing outcomes from different Phase III RCTs of biologics in CRSwNP.

Celebrating Faculty Scholarship 2026, Smith College Libraries

Celebrating Faculty Scholarship: Bibliographies

Bibliography of selected scholarly and creative work produced by Smith College faculty and submitted by faculty for the 2026 celebration in the Neilson Library Skyline Reading Room, Smith College on September 14, 2026.

A Comprehensive Survey Of Prompt Engineering Techniques In Large Language Models, Tonmoy Debnath, Md Nurul Absar Siddiky, Muhammad Enayetur Rahman, Prosenjit Das, Antu Kumar Guha, Muhammad Rezaur Rahman, H. M. Dipu Kabir

Electrical & Computer Engineering Faculty Publications

Prompt engineering has arisen as a pivotal discipline in optimizing the performance of Large Language Models (LLMs) by structuring inputs to enhance coherence, accuracy, and task alignment. This paper comprehensively surveys various prompting techniques, systematically categorizing them according to their application domains and methodological foundations. Fundamental approaches like zero-shot and few-shot prompting are examined along with advanced strategies, including chain-of-thought reasoning, retrieval-augmented generation, and self-consistency mechanisms. A rigorous qualitative analysis is conducted to evaluate each technique's strengths, limitations, and optimal use cases, offering a structured framework for selecting the most effective prompting strategies. Theoretical insights and empirical findings are consolidated …

Physics-Informed Temperature Prediction Of Lithium-Ion Batteries Using Decomposition-Enhanced Lstm And Bilstm Models, Seyed Saeed Madani, Yasmin Shabeer, Michael Fowler, Satyam Panchal, Carlos Ziebert, Hicham Chaoui, François Allard

Electrical & Computer Engineering Faculty Publications

Accurately forecasting the operating temperature of lithium-ion batteries (LIBs) is essential for preventing thermal runaway, extending service life, and ensuring the safe operation of electric vehicles and stationary energy-storage systems. This work introduces a unified, physics-informed, and data-driven temperature-prediction framework that integrates mathematically governed preprocessing, electrothermal decomposition, and sequential deep learning architectures. The methodology systematically applies the governing relations to convert raw temperature measurements into trend, seasonal, and residual components, thereby isolating long-term thermal accumulation, reversible entropy-driven oscillations, and irreversible resistive heating. These physically interpretable signatures serve as structured inputs to machine learning and deep learning models trained on temporally …