Computational Engineering Commons^™

Building A Long Text Privacy Policy Corpus With Multi-Class Labels, David Stein, Florencia Marotta-Wurgler

Vanderbilt Law School Faculty Publications

Legal text poses distinctive challenges for natural language processing. The legal import of a term may depend on omissions, cross-references, or silence, Further, legal text is often susceptible to multiple valid, conflicting interpretations; as the saying goes: a good lawyer’s answer to any question is “it depends.”This work introduces a new, hand-coded dataset for the interpretation of privacy policies. It includes privacy policies from 149 firms, including materials incorporated by reference. The policies are annotated across 64 dimension that reflect the applicable legal rules and contested terms from EU and US privacy regulation and litigation. Our annotation methodology is designed …

A Unified Multiphase Composite Material Model: An Advanced Computational Continuum-Micro Mechanics Framework, Jaton N. Wince

Doctoral Dissertations and Projects

This work represents a transformational milestone that addresses the complex mechanical behavior of composite material systems within a unified framework for both inorganic and organic constituents. The motivation for this research stems from the need to accurately model and predict the mechanical behavior of these complex material systems, which are widely used in various industries. These materials present a unique challenge due to the intricate interplay of inorganic and organic phases, making them ideal candidates for an Internal State Variable (ISV) multiscale modeling approach.

The proposed model is a comprehensive ISV framework that seamlessly predicts inorganic and organic material behavior. …

Multi-Parameter Optimization Of Brine Desalination Using Machine Learning, Elaf Mman Seif

Theses and Dissertations

Air Gap Membrane Distillation (AGMD) is a promising desalination technology with significant potential for addressing global water scarcity. However, the interplay of operational parameters significantly impacts its performance, making optimization a challenging task. This research focuses on brine desalination as a means to mitigate the negative environmental impacts of brine disposal which will eventually help in provide a sustainable solution for handling brine while producing freshwater. The study seeks to develop a predictive model and optimize the AGMD process for efficient brine desalination. To achieve this, Response Surface Methodology (RSM) and Artificial Neural Networks (ANNs) were utilized to develop predictive …

Data-Driven Product Recommendations: A Decision Support Framework Utilizing Customer Reviews, Tyler A. Lopez

Master's Theses

With the considerable presence of e-commerce in society, vast number of purchasable goods, and increasing brand variety, consumers are faced with the challenge of buying products that they perceive to be of greatest value to them. To assist consumers with making better informed decisions, e-commerce websites allow individuals to post their own experiences and score the products that they purchase. Despite this information, the variety of experiences and feedback that consumers share do not always lead to clarity on whether a product is best suited for the purchaser. To help guide customers through a simplified purchasing process from the perspective …

How Argentina Won The 2022 Fifa Men's World Cup: A Data Story, Aniruddha Parthasarathy

Dissertations, Theses, and Capstone Projects

This project analyzes Argentina’s 2022 FIFA Men’s World Cup win using open-source football (soccer) data. The project evaluates the team’s performance at a micro-level across three domains: without possessing the ball, possessing the ball and the team’s in-game management tactics. A statistical framework, i.e., multiple linear regression modeling, was used to identify the five key defensive actions influencing the Argentinian team’s intensity of pressure applied, and visualized by heatmaps and time-segmented plots. More specifically, an Expected Threat (xT) analysis quantified the threat or danger from passes and progressive carries (moving the ball at least 10 meters), revealing that Lionel Messi’s …

A Data-Driven Approach To Smart Shopping: Optimizing Grocery Trips Using Geolocation And Store Inventory Data, Kien T. Giang

Honors Theses

This project presents a data-driven web-based application, Smart Shopping, designed to help customers optimize their grocery purchases based on location and store inventory information. The application allows users to add items to a shopping list and either enter an address or use their browser’s location services to identify nearby stores. It then retrieves product availability and prices from a mock database representing stores at user’s selected locations. The program compares prices across stores to provide users with two optimized options: the cheapest shopping bill from a single store, and the lowest individual item prices across multiple stores. Additionally, the …

Facilitating Design Of Effective, Scalable Digital Mental Health Care, Himanshu Mahesh Patil

Dartmouth College Master’s Theses

This thesis tackles the challenges of designing effective, scalable digital mental health care solutions by integrating psychological research with human-computer interaction (HCI) principles. An exploration of self-care technologies (SCTs) for mental health is conducted to highlight challenges to comparative analysis, like fragmented research outcomes. Two research questions are posed to investigate how mental health interventions can be designed to be effective and overcome practical challenges to implementation. A theoretical framework in clinical psychology is adapted to bridge the gap between psychology and HCI. A methodology for conducting standardized, structured comparative analysis of mental health interventions is identified. The identified method …

Fundus Retinal Images And Glaucoma Detection, Lama Alsabban, Malak Alnahdi, Nema Salem

Effat Undergraduate Research Journal

Abstract. Glaucoma is a severe eye disease that has no symptoms and, globally, it is the second cause of blindness. Glaucoma causes structural changes in the retina that make ophthalmologists detecting the disease in early stage and thus provide the suitable treatment. Fundus camera is an imaging technique that provides the fundus image showing the internal structure of retina. Our project provides an automated system for early detection of Glaucoma. The proposed system based MATLAB starts by acquiring the fundus image, followed by preprocessing stage, going through noise removal, enhancement, segmentation, feature extraction and ends up by the classification stage. …

Assessment Of H2s-Induced Cracking Susceptibility In Steam Line Pipes And Weld Zones During Geothermal Well Construction, Riene Kaelamanda Pragitta, Yudha Pratesa

Journal of Materials Exploration and Findings

The susceptibility of steam line pipes, especially in the HAZ (heat-affected zone) and weldment areas, to hydrogen sulfide in the geothermal industry is crucial to understand from the early stages, particularly during construction. The combination of tensile stress from residual stresses after welding and metallurgical phase transformation makes the joint areas vulnerable to sulfide stress cracking. This condition becomes even more extreme when the equipment operates during the well stimulation phase. This research assesses the severity of H₂S-induced cracking using NACE MR0175 and ISO 15156-1 standards, focusing on the effects of pH and partial pressure of H₂S (p_{H₂S …}

Signal Modeling Of High Purity Germanium Detectors, Brooke Parker Thibodeau

Honors Scholar Theses

Pulse shape analysis can be used to analyze radiation incident on a semiconductor diode detector. Finite element analysis (FEA) can be used to simulate high purity germanium detectors with user-specified geometry, impurity concentration, and bias voltage. Subsequent streamline calculation can be used to conduct pulse shape analysis for single and multiple site gamma-ray interactions within the detector volume. Cross sections of the detector can be visualized by contour plots of the electric field, drift velocity magnitude, and collection time, as well as t30 and t90 rise-time values.

Exploring User Sentiment On Social Issues Via Neural Network Transfer Learning In Digital Communities, Ananya R. Vangoor

Electrical Engineering and Computer Science Undergraduate Honors Theses

Understanding public sentiment on social issues is crucial for gauging the stance of the general population. Traditionally, surveys have been a common approach for this. However, to capture more candid opinions, social media provides a rich source of unadulterated opinions. By analyzing social media statements, we can gain insights into the perspectives of specific groups. More specifically, we will investigate the attitudes of the public into the relationship between hard work and success in the workplace.

Using a neural network trained on tweets from X, formerly known as Twitter, we can categorize each tweet as either pro-luck or pro-meritocracy. But …

Design Considerations Of A Gpu, Nicholas M. Devilliers

Electrical Engineering and Computer Science Undergraduate Honors Theses

With the current era of AI technology, the era of single instruction multiple data has become an increasingly viable solution to accelerate training. The problem is that while software to use GPUs and other hardware accelerators, designing GPUs and ASIC devices has become increasingly more expensive and there aren’t great examples of generic GPUs that anyone can use and modify. In this thesis, there are four design considerations that will be discussed and how they affect the result of a generic GPU. The four considerations that were talked about in the thesis are, word width, arithmetic type, number of stages, …

False Information Attack Detection In A Connected Vehicle Environment With Quantum Inspired Long Short-Term Memory, Jean Michel M. Tine

All Theses

Wireless communication Systems enabling Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) data exchange, supported by technologies such as Cellular-V2X (C-V2X), has introduced significant cybersecurity challenges, particularly the threat of false information attacks that can compromise traffic safety and efficiency. In this thesis, the author focuses on identifying false information cyber-attack on V2I, in which vehicles are sending Basic Safety Messages (BSMs) to a Roadside Unit (RSU) and RSUs are collecting, processing and communicating data back to Connected Vehicles (CVs) to support different CV applications. Despite advances in anomaly detection using Long Short-Term Memory (LSTM) networks, these models often struggle with computational efficiency …

Mechanistic Insights Into Polymer-Assisted Graphene Exfoliation: The Roles Of Velocity, Adhesion, Cohesion, Temperature, Peeling Mode, And Edge Defect Via Coarse-Grained Molecular Dynamics, Linjiale Dai

All Theses

Graphene exfoliation is a critical step in the fabrication of high-quality graphene

layers. However, the underlying fracture mechanisms remain poorly understood. In this

work, I employed coarse-grained (CG) molecular dynamics (MD) simulations to

investigate how factors such as interfacial binding energy, substrate cohesion, temperature,

peeling mode, and edge defects influence the outcome of the exfoliation process. To model

polymer-assisted mechanical exfoliation, I used a finite-size system in which multilayer

graphene (MLG) is sandwiched between two thin polymer films. Leveraging the

spatiotemporal efficiency of the CG model, I performed fifty simulation iterations per

parameter set and analyzed the results from a …

Spin Coater Design With Pid Algorithm Using Polynomial Regression Approach And Bias Tuning For Tio2 Deposition Process, Geo Surya Andika, Nofrijon Sofyan, Donanta Dhaneswara, Akhmad Herman Yuwono

Journal of Materials Exploration and Findings

The thin-film deposition technique using spin coating offers a cost-effective alternative to Chemical Vapor Deposition (CVD) and Physical Vapor Deposition (PVD). The spin-coating process requires precise control of the motor drive system to ensure that the rotational speed, measured in rotations per minute (RPM), aligns with the set point and remains stable. This study presents the design and development of a spin coater prototype to achieve uniform thin-film deposition. The control method employed utilizes a Proportional-Integral-Derivative (PID) algorithm, incorporating a polynomial approach with bias tuning. The PID control was chosen to achieve stable operation in a non-linear system. The performance …

Using Gaussian Process Regression To Learn Thermodynamic Equations Of State With Uncertainty Quantification, Austen T. Lee

Chemical Engineering Undergraduate Honors Theses

This study investigates the use of derivative-informed Gaussian Process (GP) models to estimate thermodynamic behavior across temperature and density by building a Helmholtz-based equation of state. Argon, a stable monatomic gas, was chosen as a case study within the vapor region. The GP model was trained using values of experimentally measurable properties found by taking first and second derivatives of the original potential function. Results show that while the GP model offered uncertainty quantification and informed thermodynamic behavior, it predicted values that deviated from the ground truth depending on the property. The model exhibited high confidence in regions with substantial …

Urban-Rural Dynamics And Dui Fatalities In The Inland Empire: A Neural Network Analysis Of Traffic Safety Disparities, Armando Ceja-Lua

Electronic Theses, Projects, and Dissertations

This study examines the disproportionately high traffic fatality rates in California's Inland Empire region through neural network analysis of over 500,000 accidents (2013-2022). We argue that the Inland Empire's unique hybrid urban-rural landscape creates a multiplicative risk environment unlike other California regions. Our analysis reveals that San Bernardino County's fatality rate (1.920 per 100 million VMT) significantly exceeds neighboring regions, with alcohol-impaired driving fatalities (0.586) substantially higher than California's average (0.390). Neural network models (92% validation accuracy) identify pedestrian-involved collisions (correlation value 0.164) and alcohol involvement (0.075) as the strongest predictors of fatality in urban areas, while rural crash patterns …

Toward The Application Of Natural Language Processing In Electronic Health Record Analysis For Taxonomy Development, Latoya Mcdonald

All Dissertations

Electronic health records (EHRs) are pivotal resources for nurse practice because they increase the timeliness and reliability of patient information at the point of care and support access by multiple healthcare providers and the individual patients themselves. However, it is widely recognized that data extraction from EHRs is challenging due to the variability in the language used in clinical care notes and the lack of standardized terminology across healthcare systems. The broad objective of this dissertation is to develop taxonomy-based classification models for nursing care by applying feature engineering approaches to EHRs that include nursing care of ostomy patients following …

A Comparison And Investigation Of 2d Axisymmetric And 3d Models For The Wave Augmented Varicose Explosions Atomizer, Caleb Miller

Senior Honors Theses

Atomization of non-Newtonian, high-viscosity fluids is a challenging task with many applications. One method of atomizing these types of flows is the Wave Augmented Varicose Explosions (WAVE) atomizer. Using this framework, the study establishes an analysis methodology, investigates the relationship between 2D axisymmetric (2DA) and 3D models, and provides analysis of geometric, non-geometric, and non-dimensional parameter influences on the atomizer characterization in 2DA models. The study found that 2DA models can provide viable predictions of certain 3D model characteristics, established several mathematical models for parameter relationships among 2DA models, and identified certain metrics as inadequate predictors of atomizer characteristics in …

Advancing Solar Farm Resilience: Cfd-Driven Wind Load Optimization, Aly Mousaad Aly

Faculty Publications

This study investigates wind load design methods for ground-mounted solar panels and arrays by comparing Computational Fluid Dynamics (CFD) simulations with design standards. A case study of a solar farm impacted by Hurricane Maria examines the effects of elevation height, tilt angle, and variations in the American Society of Civil Engineers (ASCE) standards on wind loads and structural failure. Turbulence models, including Reynolds Stress Model, k–ε Model, and Large Eddy Simulation (LES), are used to analyze wind pressures, lift, drag, and peak pressures. Results show Phase 1 experienced higher wind loads than Phase 2 due to design differences. A cost-benefit …