Digital Commons Network^™

Classification Of Indonesian Sign Language (Sibi) Using Data Mining Algorithms K-Nearest Neighbor And Random Forest, Muhammad Zaki Wirawan, Achmad Afif, Anik Nur Handayani, Imanuel Hitipeuw, Osamu Fukuda

Knowledge Engineering and Data Science

This study aims to address the communication hallenges faced by the Indonesian deaf community by developing an automatic classification model for Sistem Bahasa Isyarat Indonesia (SIBI) using data mining techniques. The main objective is to identify a practical algorithm for recognizing SIBI hand gestures to enhance accessibility and inclusiveness in digital communication. A comprehensive dataset consisting of 32,850 gesture samples representing SIBI alphabet signs was collected and processed through feature extraction, data cleaning, and normalization using Z-Transform and Min-Max methods. Two classification algorithms, K-Nearest Neighbor (KNN) and Random Forest, were implemented and evaluated using metrics such as accuracy, precision, recall, …

Comparative Analysis Of Deep Learning Algorithms For Predicting Enso Based On Non-Sequential Sampling Procedure Algorithms, Ria Faulina, Siti Hadijah Hasanah, Nuramaliyah Nuramaliyah, Ika Nur Laily Fitriana

Knowledge Engineering and Data Science

The El Niño–Southern Oscillation (ENSO) is a major climate phenomenon that significantly influences global weather patterns, particularly rainfall and temperature variability across different regions. Accurate ENSO forecasting is therefore essential to support disaster risk mitigation and strategic decision-making in climate-sensitive sectors such as agriculture, fisheries, and water resource management. This study investigates the performance of deep learning approaches for ENSO prediction using a non-sequential sampling procedure on historical climate data. Three models are comparatively evaluated: Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and a hybrid CNN–LSTM architecture. The results demonstrate that the hybrid CNN–LSTM model outperforms the standalone CNN …

The Relationship Between Pillar[5]Arene And Pillar[6]Arene In The Synthetic Route To A Water-Soluble Pillar[6]Arene: A Case Of Kinetic And Thermodynamic Products Or Two Distinct, Competing Reactions, Helice A. Gillis

Open Access Dissertations

Pillar[n]arenes, discovered in 2008, have already made their mark as a formidable addition to the field of supramolecular chemistry, largely due to their host-guest chemistry. While the synthesis of pillar[5]arene is well established, the synthesis of pillar[6]arene, with its larger core, has not been so straightforward and mainly accomplished through the use of bulky solvents. Here we present an optimized method for a reproducible, acid-catalyzed synthesis for a brominated pillar[6]arene, starting with a brominated monomer and using chloroform as the templating solvent. Our studies have demonstrated the ratio of brominated pillar[6]arene to brominated pillar[5]arene increases with both decreasing concentration of …

Characterization Of Methodological Variability In Compound Specific Isotope Analysis Of Amino Acids (Csia-Aa), Audreyana Brown-Nash

Open Access Dissertations

The use of isotopes in the natural sciences stems from the principle that chemical reactions predictably alter the isotopic composition of a given sample. Recent advances in compound specific isotope analysis of amino acids (CSIA-AA) have paved the way for studies of increasingly complex ecological relationships, including the identification and characterization of organismal physiology, consumer-resource linkages, biogeochemical cycling, and movement ecology. The analytical power of CSIA-AA has caused an exponential increase in the number of application-based studies since its inception in the 1990s. With the technique constantly evolving to accommodate new research goals, it is important to understand how variation …

Essays On Human Decisions Related To Water Quality Problems In The United States, Sonia M. Refulio Coronado

Open Access Dissertations

Water pollution remains a pervasive and inequitable environmental threat in the United States, with mounting evidence that its burdens - whether in recreational or drinking water contexts - are unevenly distributed across communities. Urbanization, aging infrastructure, and industrial contamination have degraded both coastal waters and drinking water systems, posing serious public health and welfare concerns. At the same time, the extent to which water quality influences behavioral decisions, such as beach recreation or household adoption of water filters, remains poorly understood. Although drinking water pollution is widely ranked as a top environmental concern in national surveys, public knowledge of specific …

Six Rivers National Forest Hazardous Fuels And Fire Management Project 2025 Orleans Complex Fire Effects From 9/13/25 - 9/14/25, James L. Parr, Nosheen Maung, Darby J. Lewis, Javier E. Margarito, Giancarlo Golloti

Environmental Science & Management Senior Capstones

The 2025 Orleans Complex affected the Klamath National Priority Landscape, designated by Congress as a priority to reduce fuel load and mitigate wildfire risk near rural, at-risk communities. To address the threat of large destructive wildfires, the 2023 Six Rivers Hazardous Fuels and Fire Management Project identified desired ecological conditions, using the right type of fire at the right time and place.

Physicists As Environmental Experts, Rachel Rothschild

Articles

The question of which scientists are qualified to provide expert guidance in legal controversies is a perennial debate among scholars, judges, and lawyers. Scientists who participate in legal disputes can achieve enormous power and influence, not only over the case at hand but over long-term developments in legal doctrine. While these issues arise in many areas of the law, environmental litigation has been a particularly active site of contestations over epistemic authority. Courts have frequently relied on scientists to understand whether the government is justified in regulating pollution and who may be liable for environmental and public health harms.

This …

The Future Of Ai Regulation In Drug Development: A Comparative Analysis, Gabriela Lenarczyk, Timo Minssen, W. Nicholson Price Ii, Arti Rai

Articles

As artificial intelligence (AI) transforms drug development, regulatory frameworks are evolving to oversee its implementation, particularly at the US Food and Drug Administration (FDA) and the European Medicines Agency (EMA). This paper makes three contributions to understanding emerging regulatory approaches. First, we offer a comparative analysis of how these agencies have responded to AI-driven advances, incorporating new US executive orders and the European Union (EU)’s AI Act. Second, we propose a novel analytical framework to understand regulatory divergence: the FDA’s flexible, dialog-driven model contrasts with the EMA’s structured, risk-tiered approach, reflecting broader institutional and political-economic differences. While the former encourages …

Deep Learning For Irish Garden Bird Identification: Exploring The Role Of Cnn-Lstm In Video-Based Recognition, Antonina Dolynenko

ICT

Bird populations are widely used as indicators of ecosystem health, but traditional monitoring based on manual observation is labour-intensive and difficult to scale. Recent advances in deep learning and low-cost edge hardware offer new opportunities for automated, real-time bird identification in gardens and other local habitats. This thesis investigates whether video-based deep learning models can reliably classify common Irish garden birds from short motion-triggered clips and how temporal modelling compares to image-based models.

A primary dataset of 20-second clips was collected in a private garden in Ireland using a Raspberry Pi with a high-resolution camera and a YOLO-based trigger to …

A Comparative Analysis Of The Performance Of Customised And Pre-Trained Convolutional Neural Networks In The Classification Of Facial Expressions., Guilherme Soares Da Costa

ICT

Facial expression recognition (FER) is a highly relevant problem in the field of computer vision, with applications in various areas. Although this topic has made significant progress in recent years with deep learning, facial expression recognition continues to face significant challenges when faced with a noisy, imbalanced database, and low-resolution images, as is the case with the widely used FER2013 database. This work investigates the usability of different approaches based on Convolutional Neural Networks (CNNs) for the task of facial expression classification.

First, a custom CNN was developed and trained from scratch, using FER2013 as database. Subsequently, three well-known pre-trained …

Exogenous Variables In Time Series Forecasting During Economic Volatility: A Cross-Sector And Cross-Crisis Evaluation., Orla Kavanagh

ICT

Economic disruptions pose challenges for time series forecasting, but also offer opportunities to evaluate the value of exogenous information. This study investigates the role of external indicators during the COVID-19 pandemic and the 2025 U.S. tariff shock, using data from Dell (technology) and Boeing (aerospace/manufacturing). ARIMA, SARIMA, and LSTM models were tested with candidate exogenous variables. Results indicate that the benefit of external signals is highly context-dependent: sector, disruption type, and forecast horizon all influence effectiveness. LSTM models generally excel at longer horizons with exogenous inputs, while ARIMA-based models perform better short-term. Findings emphasize that careful variable selection, ongoing evaluation, …

Understanding Model Behaviour And Interpretability In Time Series Forecasting: A Deep Dive Into Lstm And Gru With Xai Techniques., Federico Ariton

ICT

Time-series forecasting is widely used in data analytics, yet the interpretability of deep learning models remains a key challenge. This study compares Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models using a dual interpretability framework that combines attention mechanisms and SHAP analysis. Two feature sets were evaluated across assets with different volatility regimes: Solana and Shiba Inu (high volatility), Bitcoin (moderate volatility), and Apple (low volatility). Results show that autoregressive features achieved the lowest forecasting errors, while volatility- and momentum-based indicators provided stronger interpretability. GRU performed best in moderate-volatility conditions, whereas LSTM demonstrated more consistent performance across varying …

Enhancing Fake News And Rumor Detection Using Metadata, Context, And User Interaction With A Hybrid Gcn-Transformer., Lucas Romulo Zuin Gigli

ICT

The increasing influence of social media has significantly impacted how news spreads among users, making the detection of misinformation, including fake news and rumours, a critical task. Previous research has explored content-based and metadata-driven approaches, while recent advancements have leveraged Graph Neural Networks (GNNs) such as GCNs, GATs, and SAGE to analyse user interactions and propagation patterns. This thesis investigates the effectiveness of a Hybrid Graph-Transformer Convolutional Neural Network (GCN-Transformer) for fake news detection, combining graph-based learning with Transformer attention mechanisms. Through in-depth data analysis and advanced detection techniques, this model aims to enhance predictive performance and mitigate the spread …

An Enhanced Deep Learning Framework For Crop Disease Detection Using Gan-Based Data Augmentation., Andrew Mc Guinn

ICT

Plant disease detection is a critical challenge in agriculture, where limited annotated datasets often hinder the training of robust deep learning models. This thesis explores the application of generative adversarial networks for data augmentation in the classification of six classes of sorghum diseases, addressing the scarcity of real training data. A lightweight convolutional neural network  (CNN) was employed as the classifier, trained under three experimental conditions: using only real images, a stratified mix of real and DCGAN-generated samples, and a stratified mix of real and WGAN-GP-generated samples.

The baseline CNN, trained on 279 real images, achieved an accuracy of 89.7%, …

Leaf Classification Using Convolutional Neural Networks And Vision Transformers, Louis Wilkie

ICT

This study investigates deep learning techniques for plant image classification using four publicly available datasets: Folio, Flavia, Swedish, and Sugarcane. Three modelling approaches—Convolutional Neural Networks (CNN), Vision Transformers (ViT), and hybrid CNN-ViT ensembles—are evaluated. Models leverage PyTorch implementations and pretrained weights from the Hugging Face hub, with hyperparameter tuning applied to optimize accuracy. Transfer learning with pretrained ViT models achieved the highest performance, attaining 100% accuracy on Folio, Flavia, and Swedish datasets, and 94.07% on Sugarcane. CNN and CNN-ViT models showed comparable results, but pretrained CNN-ViTs were more resource-efficient. The findings highlight the importance of evaluating multiple pretrained architectures to …

Exploring The Determinants Of Life Expectancy At Birth: Predicting And Forecasting Global Health Trends Using Statistical, Machine Learning, And Deep Learning Models., Emma Rath

ICT

Accurate life expectancy forecasting is essential for health policy planning, yet research comparing statistical, machine learning, and deep learning approaches under real-world constraints remains limited. This study evaluates ARIMA/ARIMAX, tree-based, and neural network models using Irish and global datasets, considering small samples, missing data, and COVID-19 shocks. ARIMAX with lagged socioeconomic variables outperformed LSTM and other ML/DL methods. Income-based stratification improved predictive accuracy and interpretability, with SHAP analysis highlighting GDP per capita for developed countries and school enrolment and trade indicators for developing contexts. Results provide practical guidance for policymakers and establish limits for model complexity under constrained health data.

Improving The Completeness Of Food Composition Databases Using Predictive Analysis., Carla Arenhart

ICT

This study investigates the use of machine learning regression models to impute missing micronutrient values in Food Composition Databases (FCDBs), focusing on the FAO/INFOODS dataset. A cascading prediction methodology leverages nutrient interdependencies to systematically estimate missing values. Four models—Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting Machines (GBM), and Deep Neural Networks (DNN)—were evaluated using MAE, MSE, RMSE, and R². RF and GBM achieved the highest predictive accuracy for protein, phosphorus, calcium, and magnesium, demonstrating that ML-based predictive analytics can provide a more reliable alternative to traditional imputation methods. These findings support improved dietary assessments, nutritional research, and data-driven …

Towards Developing Glut2 Specific Probes For Biochemical And Biomedical Applications, Abdelrahman Ismail

Dissertations, Master's Theses and Master's Reports

Facilitated Glucose transporters (GLUTs) are membrane proteins responsible for the uptake of simple sugars and other structurally similar metabolites in all mammalian cells. One of the hallmarks of cancer is dysfunctional sugar metabolism, known as the Warburg effect, and one of the manifestations of that effect is abnormal GLUT expression. There are 14 known GLUT proteins with different expression patterns in different tissues, and tumors tend to express certain GLUTs that are not present in surrounding healthy tissue. Therefore, selective targeting of GLUTs presents a potentially powerful tool for diagnostics and treatment of cancer and other diseases. This has been …

Microwave Assisted Syntheses And Characterizations Of Near-Infrared Ratiometric Probes For Mitochondrial Ph Detection And Monitoring, Ronald J. Schwandt

Dissertations, Master's Theses and Master's Reports

Within the field of biochemistry, there has been a significant development of ratiometric fluorescent probes designed for mitochondrial pH detection; however, many of these probes have emissions within the visible spectrum and require long synthesis times with low-yield reactions. However, in recent years, microwave-assisted syntheses of organic molecules have led to significant increases in reaction yields and quicker reaction times. In this work, two common reactions in probe synthesis, Heck coupling, and Knoevenagel condensations are investigated using microwave-assisted synthesis. It was found the low-concentration Heck coupling reactions using palladium (II) acetate led to extremely efficient Heck coupling. Also, a novel …

Generalizing Medical Image Segmentation Task With Efficient Deep Learning Models, Abel A. Reyes-Angulo

Dissertations, Master's Theses and Master's Reports

Medical Image Segmentation is a critical task in the field of medical imaging, playing a crucial role in diagnostics, treatment planning, and disease monitoring. The emergence of Deep Learning (DL) has ushered in a new era in Artificial Intelligence (AI), propelling remarkable advancements in key domains like language translation, object recognition, and recommendation systems. This evolution has been accompanied by continuous enhancements in computational efficiency and improvements in predictive accuracy. The introduction of sophisticated algorithms, such as convolutional neural networks (CNNs) and transformers, exemplifies these advancements. DL algorithms have demonstrated exceptional efficacy in medical image segmentation tasks, showcasing the potential …

Dam It All: A Multi-Scalar Investigation Into The Ecological Role And Function Of Beaver Dams, Kenneth Larsen

Dissertations, Master's Theses and Master's Reports

The central theme of this dissertation is ecological scaling, which examines how small, localized features, such as beaver ponds, contribute to large-scale watershed processes and how different modeling approaches at various scales reveal distinct insights. Through a combination of probabilistic modeling and high-resolution empirical research, this work demonstrates that small ponded systems, particularly those created by beavers (Castor canadensis), serve as critical biogeochemical control points, whose contributions to sediment and nutrient dynamics have been historically underestimated.

In Chapter 1, I contextualize this research within the broader fields of freshwater ecology, watershed modeling, and ecological restoration. I introduce the …

Comparing Custom And Transfer-Learning Cnn Models For Chest X-Ray Classification: Evaluating Performance And Scalability With Kubernetes Orchestration., Christopher Anich

ICT

Chest radiography (CXR) is the primary imaging tool for respiratory diseases, but interpretation can be time-consuming and requires expertise. This study compares a small custom CNN (Victorio) with three transfer-learning models (MobileNetV2, EfficientNet-B0, ResNet-50) for three-class CXR classification (normal, pneumonia, tuberculosis) and evaluates deployment on a Kubernetes cluster. Using a balanced dataset of ~13,500 CXRs, models were trained with ImageNet pre-training and from scratch. Transfer-learning models achieved near-perfect accuracy (99–100%) and AUROC, while the custom CNN reached 87–91%. Explainability analyses confirmed models focused on relevant pulmonary regions. Kubernetes deployment showed low latency, with most delays due to service overhead rather …

Predicting S&P Corporate Credit Ratings Using Financial Ratios And Machine Learning: An Analysis Of European Non-Financial Companies., Gabriele Frattaroli

ICT

This study investigates the prediction of multi-class S&P corporate credit ratings for European non-financial firms from 2010 to 2024 using a machine learning framework grounded in financial fundamentals. To ensure robustness and generalizability, the analysis excluded the Year variable, which was identified as a source of data leakage. After this correction, non-linear ensemble models demonstrated a clear advantage over linear baselines. The top-performing Random Forest model achieved a weighted F1-score of approximately 0.60, more than doubling the performance of the Logistic Regression benchmark used as a baseline (0.26), with most misclassifications concentrated in adjacent rating categories. This indicates that while …

Spatial Vulnerability Towards Flooding And Mitigation Of Three Coastal Cities: Charleston, South Carolina | Passaic City, New Jersey| Virginia Beach, Virginia, Kory Abbott

All Graduate Theses, Dissertations, and Other Capstone Projects

This meta-analysis investigates the impact of flooding on three coastal communities along the Atlantic Coast: Charleston, South Carolina; Passaic City, New Jersey; and Virginia Beach, Virginia. One goal of this paper is to determine the adequacy or inadequacy in the flood mitigation responses of these communities so that future actions can be taken to improve flood mitigation measures. Another goal is to consider whether the cities experience environmental injustice in terms of flooding mitigation. This paper draws from governmental documents, news reports, local experiences, updated storm management systems, and scholarly articles. The methodology used in this meta-analysis is as follows: …

Analysis Of Sled Dog Biomechanics, Natalie Bender

Williams Honors College, Honors Research Projects

This paper is an analysis of data collected by Dr Rachel Olson and her team. The data was collected from the same set of sled dogs before and after training for the Iditarod race. The goal of this paper is to draw conclusions on whether the gait of sled dogs’ change with fitness level. The data was cleaned in R to find the average peak for forelimb joint angles per run for each dog. The data was analyzed with 3 different ANOVAs – one including both the shoulder and carpus, one for just the shoulder, and one for just the …

Time Series Modeling Of Akron Air Quality Index (Aqi) Data, Mason Yurich

Williams Honors College, Honors Research Projects

With the increase in population and industrialization around the world, climate has become a major concern for many researchers. One measure that has drawn much interest is air quality. There are available resources that track the Air Quality Index (AQI) in most large cities, but there is a general lack of information regarding Air Quality forecasts, even for one day in the future. This project aims to find a useful statistical model for representing and predicting the AQI measure in Akron, Ohio over time. By using historical air quality data from the United States Environmental Protection Agency and AQI.in, an …

Advancing The Characterization Of Geophysical Signals Through Array Processing And Artificial Intelligence, Miro Ronac Giannone

Earth Sciences Theses and Dissertations

In geophysics, seismic and infrasound observations are routinely employed to constrain the nature and origin of events. Seismoacoustics, as a discipline, is built upon the simultaneous detection and integrated analysis of these data types. This joint approach is critical not only for advancing scientific understanding but also for supporting global monitoring efforts in hazard mitigation and nuclear explosion treaty verification. The data analyzed in this dissertation were recorded by array deployments, which consist of multiple sensors arranged in predetermined configurations to enhance signal detection, resolve directionality, and quantify waveform coherence. Leveraging these array recordings, I introduce novel approaches which combine …

The Signal Of Airplane Combustion In Soil At A Small Airport In Ohio, Rachel Engels

Williams Honors College, Honors Research Projects

Leaded gas has been banned for automobile use in the interest of public health since 1996. However, leaded gas is still used for small piston aircraft so the engine can run safely. To investigate potential environmental impacts of leaded gas, 90 soil samples were taken from around a small airport in Ohio. Soil elemental composition was measured by X-ray fluorescence (XRF), soil organic content determined by Loss-on-Ignition (LOI), and soil ferrimagnetic content measured by magnetic susceptibility. There is an unmistakable airplane fuel combustion signal in the soil at the ends of the runway, where aircraft wait to take off on …

Integrating Spatial Statistics And Decision Analysis For Wildfire Risk Mapping: A Case Study Of The Kootenai National Forest, Elijah Kordieh Mensah

Graduate Student Theses, Dissertations, & Professional Papers

Wildfire risk in the western United States has intensified in recent decades due to intersecting forces of climate change, systematic fire suppression, and expanding human settlement in fire-prone regions. This thesis presents a comprehensive spatial assessment of wildfire risk in the Kootenai National Forest (KNF) and its surrounding landscape in northwestern Montana, integrating wildfire likelihood, suppression difficulty, evacuation vulnerability, and building exposure into a unified spatial statistical framework. The research addresses a critical gap in spatial wildfire risk modeling by focusing on the need to assess fire threats in relation to local operational constraints and community vulnerabilities.
Drawing on geospatial …

Improving System-Level Outcomes Via Artificial Intelligence Decision Support In Kidney Utilization, Casey I. Canfield, Cihan H. Dagli, Daniel Burton Shank, Krista Lentine, Mark Schnitzler, Henry Randall, V. Sriram Siddhardh Nadendla, Brendon Cummiskey

Engineering Management and Systems Engineering Faculty Research & Creative Works

Transplantation provides patients suffering from end-stage kidney disease a better quality of life and long-term survival. However, over 20% of deceased donor kidneys are not utilized and never transplanted. While this is sometimes medically appropriate, this also reflects missed opportunities. We are designing Artificial Intelligence decision support for the kidney offer process to support both demand at the transplant center and supply at the organ procurement organization. This includes (1) developing deep learning models, (2) evaluating the effect of explainable interfaces, (3) improving fairness in the model output, (4) identifying factors that influence adoption decisions, and (5) conducting a randomized …